Pattern recognition techniques are widely used in computer vision, classification of radio signals, and voice recognition. The fractional Fourier transform is used to recognize patterns using binary rings masks and segment images. This technique has the characteristic of being invariant to position and rotation and finally obtaining a one-dimensional signature. On the other hand, Neural Networks are used for pattern recognition based on a deep neural network algorithm. It has the characteristic of training large datasets with millions of images. Artificial Neural Networks(ANNs) are used for several applications such as pattern recognition and classification of input data. In particular, the ANN has been used to evaluate medical images from the brain to assess if the image corresponds to Alzheimer's disease. One disadvantage of the neural network is a large amount of time to learn depending on the number of patterns to be identified or classified and the ability to adapt and recognize patterns. Besides, the fractional Fourier transform cannot analyze a large amount of information. In this work, a comparison between the Artificial Neural Network and the Fractional Fourier Transform is presented to determine which will be the best for recognizing a batch of selected medical images. We propose a reconstruction method using both techniques for precise image recognition and the evaluation of their respective metrics such as accuracy, precision, sensitivity, and specificity. The medical images regarding Alzheimer's disease are no dementia, very mild dementia, mild dementia presenting the best performance regarding the receiver operating characteristics and moderate dementia was the worst classified related to the number of images of the dataset.
Noise often corrupts images; therefore, it is essential to know the performance capability of a pattern recognition algorithm for images affected by it. In this work, a complete analysis of two methodologies is performed when images are affected by Gaussian and salt and pepper noise. The two methods use the nonlinear correlation of signatures. A signature is a onedimensional vector that represents each image, and it is obtained using a binary mask created based on the fractional Fourier transform (FRFT). In the first methodology, a spectral image it is used as the input to the system. The spectral image is the modulus of the Fourier transform (FT) of the image processed. The binary mask is generated from the real part of the FRFT of the spectral image. The signature is constructed by sampling the modulus of the FRFT of the spectral image with the mask. In the second methodology, the image is the input to the system, and the binary mask is obtained from the real part of the FRFT of the image. The signature, in this case, is obtained by sampling the modulus of the FT of the image with the binary mask. Each method was tested using the discrimination coefficient metric.
Diatoms are unicellular algae that have as characteristic to be composed mainly of silice. Currently, its study has become relevant due to its multiple applications that include forensic medicine, palaeoenvironmental reconstructions and its use as biological bioindicators of water quality. It is estimated that there are around 100,000 different diatom species, showing a high similarity between some of them. For these reasons, their identification is slow and often unreliable. Additionally, the number of specialists capable of carrying out an identification is not sufficient in comparison to the number of samples that usually have to be analyzed. It is for these reasons that there is a need to have automated systems that perform this task. In the present work, an automatic identification system was created for 46 diatom species with different morphology using images obtained with optical microscopy. This system was designed by calculating descriptors in the plane of frequencies using three different methodologies: the Fourier Mellin transform, the concentric ring binary masks and the fractional Fourier transform. The methods used for the identification system has as main characteristics to be robust to changes of scale, rotations, translations, and lighting. Additionally, the number of images used as reference images compared to other techniques found in the literature is lower, which gives a higher possibility that it can be extended to other species.
In this work is presented a pattern recognition image descriptor invariant to rotation, scale and translation (RST), which classify images using the Z-Fisher transform. A binary rings mask is generated using the Fourier transform. The normalized analytic Fourier-Mellin amplitude spectrum is filtered with that mask to build 1D signature. The signatures comparison of the problem image and the target are done by the Pearson correlation coefficient (PCC). In general, those PCC values do not satisfy a normal distribution, hence the Fisher’s Z distribution is employed to determine the confidence level of the RST invariant descriptor. The descriptor presents a confidence level of 95%.
Eye tracking has many useful applications that range from biometrics to face recognition and human-computer interaction. The analysis of the characteristics of the eyes has become one of the methods to accomplish the location of the eyes and the tracking of the point of gaze. Characteristics such as the contrast between the iris and the sclera, the shape, and distribution of colors and dark/light zones in the area are the starting point for these analyses. In this work, the focus will be on the contrast between the iris and the sclera, performing a correlation in the frequency domain. The images are acquired with an ordinary camera, which with were taken images of thirty-one volunteers. The reference image is an image of the subjects looking to a point in front of them at 0° angle. Then sequences of images are taken with the subject looking at different angles. These images are processed in MATLAB, obtaining the maximum correlation peak for each image, using two different filters. Each filter were analyzed and then one was selected, which is the filter that gives the best performance in terms of the utility of the data, which is displayed in graphs that shows the decay of the correlation peak as the eye moves progressively at different angle. This data will be used to obtain a mathematical model or function that establishes a relationship between the angle of vision (AOV) and the maximum correlation peak (MCP). This model will be tested using different input images from other subject not contained in the initial database, being able to predict angle of vision using the maximum correlation peak data.
It has been realized an estimation of variance of the sea surface slopes through the variances on images that consist of bright and dark regions that are called glitter pattern. The probability distribution of the sea surface slopes has been used considering a non-Gaussian case taking in account the skewness and the kurtosis of the sea surface slopes. These relationships of variance have been calculated for five different angles of light incidence on the sea surface and for four different heights of the image sensor. The brightness in the glittern pattern has been modeled using a Gaussian function with information of the incident and reflection light angle in its argument. Some computational aspects and applications for optical engineering are mentioned.
The reflection of the sunlight over the sea surface is called glitter pattern. In previous works where the one-dimensional case was analyzed, the glitter function was mathematically described by a rect function. This rect function has proven to be a very good representation of the glitter pattern. A Gaussian glitter function is used like a first approximation to the rect function. The statistical relationship between the variance and the correlation function of the intensities of the image, the glitter pattern, and the variance of the sea surface slopes are obtained and analyzed. The analytical solutions for these relationships are given by different equations; however, the graphic representations are very similar.
In this work a new methodology to recognize objects is presented. This system is invariant to position, rotation and scale by using identity vectors signatures Is obtained for both the target and the problem image. In this application, Is are obtained by means of a simplification of the main features of the original image in addition of the properties of the Fourier transform. The nonlinear correlation by using a kth law is used to obtain the digital correlation providing information on the similarity between different objects besides their great capacity to discriminate them even when are very similar. This new methodology recognizes objects in a more simple way providing a significant reduction of the image information of size m x n to one-dimensional vector of 1 x 256 consequently with low computational cost of approximately 0.02 s per image. In addition, the statistics of Euclidean distances is used as an alternative methodology for comparison of identity vectors signatures. Also, experiments were carried out in order to find the noise tolerance. The invariant to position, rotation and scale of this digital system was tested with different species of fish (real images). The results obtained have a confidence level above 95.4%.
The effects of illumination variations in digital images are a trend topic of the pattern recognition field. The luminance information of the objects help to classify them, however the environment illumination could cause a lot of problem if the system is not illumination invariant. Some applications of this topic include image and video quality, biometrics classification, etc. In this work an illumination analysis for a digital system invariant to position and rotation based on Fourier transform, Bessel masks, one-dimensional signatures and linear correlations are presented. The digital system was tested using a reference database of 21 fossil diatoms images of gray-scale and 307 x 307 pixels. The digital system has shown an excellent performance in the classification of 60,480 problem images which have different non-homogeneous illumination.
The reflection of the sunlight over the sea surface is called glitter pattern. In previous works, when the onedimensional case is analyzed, the glitter function was mathematically described like a rect function. This rect function has proved to be a very good representation of the glitter pattern. In this paper a Gaussian glitter function is used like a first approximation to the rect function. The statistical relationship between the variance of the intensities of the image, the glitter pattern, and the variance of the sea surface slopes is obtained and analyzed. The analytical solutions in this relationship are mathematical different but the graphics are very similar.
We present a nonlinear correlation methodology to recognize objects. This system is invariant to position, rotation, and scale by using vectorial signatures obtained from the target such as those from problem images. Vectorial signatures are calculated through several mathematical transformations such as scale and Fourier transform. In this application, vectorial signatures are compared using nonlinear correlations. Also, experiments were carried out in order to find the noise tolerance. The discrimination coefficient was used as a metric in performance evaluation in presence of noise. In addition, spectral index and vectorial signature index are obtained in order to recognize objects in a simpler way. This technique has low computational cost. The invariance to position, rotation, and scale digital system was tested with 21 different fossil diatoms images. The results obtained are good, and the confidence level is above 95.4%.
Digital systems of invariant non-linear correlation to position and scale based on adaptive binary mask of concentric
rings and unidimensional signatures are useful tool in pattern recognition. With the modulus of the Fourier transform of
the image we obtain the invariance to translation. Using the Scale transformation and adaptive binary ring masks the
scale invariant is calculated. The discrimination between objects is done by non-linear correlation of the unidimensional
signatures assigned to the problem image and the target. In addition, working with unidimensional signatures reduce the
computational time considerably, achieving a step toward the ultimate goal, which is developing a simple digital system
that accomplishes recognition in real time at low cost.
In this paper a non-linear correlation methodology to recognize objects is used. This new system is invariant to position,
rotation and scale. This digital system has a low computational cost to achieve a significant reduction of processed
information by using vectorial signatures. The invariant vectorial signatures are obtained from the information from both
the target image as well as problem image. In this way, each image has its rotational and scale vectorial signature
obtained through several mathematical transformations such as scale and Fourier transform. So, this method uses the
great capacities from the non-linear filters to discriminate between similar objects. Vectorial signatures are compared
using non-linear correlation. The result of this comparison is shown in a bi-dimensional plane where the x axis is the
result of the rotation correlation and the y axis is the result of the scale correlation. In addition, spectral index and
vectorial signature index are obtained through several mathematical transformations in order to recognize the objects in a
more simple way. 21 different fossil diatoms images were used. The results obtained are analyzed and discussed.
A nonlinear correlation digital algorithm invariant to position, rotation and scale using a binary mask is presented. In
order to analyze this new identification digital system binary and gray images are used. The problem images had a
±30% of maximum scale variation with respect to the target. Some composite filters had a very good performance in
this range. The rotation goes from 0° to 359°. Concentric binary rings masks were elaborated, from the Fourier
transform, using the real or the imaginary part. The signatures of the problem image and the target were obtained from
the ring mask. The objective is identifying a specific target no matter the position, rotation or scale presented in the
problem image. A statistical analysis was done to know the mean correlation confidence level. In this work, a new, fast
and functional position, scale and rotation invariance pattern recognition digital system was obtained.
We use nonlinear composite filters in object recognition, even when they have rotation, scale, noise, and illumination distortions. We generated 936 images of the letters E, F, H, P, and B. The images consisted of these letters scaled from 70% to 130% and rotated 360 deg. The maximum number of images supported by these filters was determined by a numerical experiment. Considering a system confidence level of at least 80%, the maximum number of images is around 216. We found a "rotation problem" when the filter contained the letter rotated 360 deg, since circles were artificially introduced, and this creates complications when working with images that also have circles in their spectrum. Due to this, we propose a segmented filter that breaks the circular symmetry. Experiments where carried out in order to find the noise tolerance of each filter, and the use of Spearman's rank correlation (in conjunction with the nonlinear method, SNM) is proposed in order to increase that tolerance. We also made an assessment of the impact that illumination changes had in the correlation output, in the problem image, and we propose the use of SNM to obtain illumination invariance. We tested these filters with two real-life problems; nonlinear composite filters can recognize the target in the presence of distortions.
In this work we use non linear composite filters in object recognition, even when they have rotation, scale and noise
distortions. We generated 936 images of the letters E, F, H, P and B. The images consisted of these letters scaled from 70% to 130% and rotated 360°. The maximum number of images supported by these filters was determined by a numerical experiment. This was done by generating filters with different amount of images each. We have images at 13
scales and each scale with 72 different angles, tests were done to two different kinds of filters, one where all the scales were present and we add more angles to increase the number of images, and another where all of the angles were present and more scales were added to increase the number of images. Considering a system confidence level of at least 80%, the maximum number of images allowed by the filter is around 216. In one type of filter we have the letter rotated 360°. We found a "rotation problem", since circles were introduced in the Fourier plane, in other words first order Bessel functions were introduced in the image spectrum, which creates complications when working with images that also have circles in their spectrum. Due to this we propose a segmented filter which breaks the circular symmetry. Non-linear composite filters can recognize the target in presence of distortions.
A new rotational invariance computational filter is presented. The filter was applied to a problem image, in this case, an image of 256 by 256 pixels of black background with a centered white Arial letter. The complete alphabet is represented in those images. The image is rotated one degree by one degree until complete 360 degrees; hence, for each alphabet letter we are generating 360 images. To achieve the rotational invariance, first of all, a translational invariance is applied and then a 256 by 256 binary mask of concentric circular rings of three pixels of thickness and separation is used. The sum of the information in the circular rings represents the signature of the image. The average of the signature of the 360 images of a selected letter is the filter used to compute the phase correlation with all alphabet letter and their rotated images. The confidence level is
calculated by the mean value with two standard errors (2SE) of those 360 correlation values for each letter. The confidence level shows that this system works efficiently on the discrimination between letters.
This paper describes an image recognition system designed to inspect the standards quality of electronic assemblies. The essence of the present algorithm is the location of electronics components, at the input image, that disrupt the acceptance requirements for the manufacture of printed circuit board assemblies, which have been adopted by association connecting electronics industries. To this end, image processing modules, based on a nonlinear composite filter are employed with the objective to discriminate between the electronics components that meet the acceptance condition and those that are in defect condition. The proposed recognition system is based on nonlinear composite filter, which is obtained from a training set of reference images. Then, the optimal filter is used in a digital correlator, which results in a simple and robust inspection system.
An invariant correlation digital system using a nonlinear filter is presented. The invariance to position, rotation and scale
of the target is achieved via Fourier transform, mapping polar and Scale transform, respectively. We analyzed the
performance of this filter with different nonlinearities k values according to the peak-to-correlation energy (PCE) metric.
We found experimentally the best k value for rotation and scale and the confidence levels of the filters. The filter was
applied to the complete alphabet letters where each letter is a problem image of 256x256 pixels in size. The results are
presented and show a better performance when they are compared with linear filters.
This work presents the development and utilization of vectorial signatures filters obtained from the application of properties of the scale and Fourier transform for images recognition. The filters were applied to different input scene, which consisted in the 26 letters of the alphabet. Each letter is an image of 256 × 256 pixels of black background with a centered white Arial letter. The image was rotated 360 degrees in increment of 1o and scaled from 70% to 130% in increment of 0.5%. In order to find a new invariant correlation digital system we obtained two unidimensional vector after to achieve different mathematical transformation in the target as well as the input scene. To recognize a target, signatures were compared, calculating the Euclidean distance between the target and the input scene; then, confidence levels are obtained. The results demonstrate that this system has a good performance to discriminate between letters.
The vectorial shearing interferometer includes a pair of wedge prisms as a shearing system. Perfect alignment of the shearing system is crucial for the optimal detection and analysis of asymmetrical wave fronts. This paper describes a recognition algorithm for optical misalignment detection and prisms orientation based in the intensity pattern obtained in the calibration process. The key of the present algorithm is the comparison of a reference intensity pattern, against a sheared interferogram that depends on the wedge prism position. First, an optimum phase only filter is obtained from a set of reference images with the objective to discriminate between different phase changes. Then, the optimal filter is used in a digital correlator, which results in a simple and robust calibration system.
Recently, within the cytogenetic analysis, the evolutionary relations implied in the content of nuclear DNA in
plants and animals have received a great attention. The first detailed measurements of the nuclear DNA
content were made in the early 40's, several years before Watson and Crick proposed the molecular structure
of the DNA. In the following years Hewson Swift developed the concept of "C-value" in reference to the
haploid phase of DNA in plants. Later Mirsky and Ris carried out the first systematic study of genomic size
in animals, including representatives of the five super classes of vertebrates as well as of some invertebrates.
From these preliminary results it became evident that the DNA content varies enormously between the
species and that this variation does not bear relation to the intuitive notion from the complexity of the
organism. Later, this observation was reaffirmed in the following years as the studies increased on genomic
size, thus denominating to this characteristic of the organisms like the "Paradox of the C-value". Few years
later along with the no-codification discovery of DNA the paradox was solved, nevertheless, numerous
questions remain until nowadays unfinished, taking to denominate this type of studies like the "C-value
enigma". In this study, we reported a new method for genome size estimation by quantification of
fluorescence fading. We measured the fluorescence intensity each 1600 milliseconds in DAPI-stained nuclei.
The estimation of the area under the graph (integral fading) during fading period was related with the genome
size.
An adaptive phase-input joint transform correlator for real-time pattern recognition is presented. A reference
image for the correlator is generated with a new iterative algorithm based on synthetic discriminant functions.
The obtained reference image contains the information needed to discriminate reliably a target against known
false objects and a cluttered background. Calibration look-up tables of all used opto-electronic elements are
included in the design of the adaptive phase-input joint transform correlator. The resulting joint input image for
the correlator is a real-valued bipolar image, which cannot be directly displayed with a conventional amplitudeonly
spatial light modulator. Commonly two optical correlations and post-processing are used. We utilize
a phase-only spatial light modulator in the input plane. A new phase-only joint input image is obtained by a
monotonic mapping the intensity to phase information. The phase-only image is easily introduced into an optical
setup. In this case we need just one correlation and no post-processing. Experimental results are provided and
compared with those obtained with computer simulations.
One of the main problems in visual image processing is incomplete information owing an occlusion of objects by other objects. Since correlation filters mainly use contour information of objects to carry out pattern recognition then conventional correlation filters without training often yield a poor performance to recognize partially occluded objects. Adaptive correlation filters based on synthetic discriminant functions for recognition of partially occluded objects imbedded into a cluttered background are proposed. The designed correlation filters are adaptive to an input test scene, which is constructed with fragments of the target, false objects, and background to be rejected. These filters are able to suppress sidelobes of the given background as well as false objects. The performances of the adaptive filters in real scenes are compared with those of various correlation filters in terms of discrimination capability and robustness to noise.
New adaptive correlation filters based on a conventional synthetic discriminant function (SDF) for reliable recognition of an object in cluttered background are proposed. The information about an object to be recognized, false objects, and a background to be rejected is utilized in an iterative training procedure to design a correlation filter with a given value of discrimination capability. Computer simulation results obtained with the proposed adaptive filter in test scenes are discussed and compared with those of various correlation filters in terms of discrimination capability, tolerance to input additive noise that is always present in image sensors, and to small geometric image distortions.
In observation by confocal or conventional fluorescence microscopy, the retardation of the lost in fluorescence, from highest signal of fluorescence to lowest intensity are important factors in order to obtain accurate images. This problem is very common in fluorochromes for nuclear DNA and especially for DAPI stain. The fluorescence of DAPI is rapidly lost when it is exposure to excitation by ultra violet (UV) light, and especially under optimal condition of observation. Although the fading process could be retardate by using of mounting medium with antifading solutions, the photochemical process underlying the fluorescence decay has not yet been fully explained. In addiction, neither relationship has been tested between the fluorescence fading and nuclear DNA content. However, the capacity of the DNA to absorb UV light is knows. In order to test this relationship we measured by means of image analysis the fluorescence intensity in several nuclei types during a fading period. The analysis was performed by an algorithm specifically built in MATLAB software. The relationship between nuclear DNA content and DAPI-fluorescence fading was found equal to 99%. This study demonstrates the feasibility for estimates genome size by quantification of fluorescence fading. In this context, the present method allows to measure nuclear DNA content in several medical applications (cancer, HIV, organ transplants, etc). Nowadays, for measuring DNA content, flow cytometry is widely used; however, with the flow cytometry method it is not possible to select a specific group of cells, such as from a specific region of a tumor. Moreover, the using of image analysis allows automatizing diagnostics procedures.
In this paper we present an algorithm to determine the multifocus image fusion from several color microbiological images captured from the best focusing region. This focusing region is built by including several images up and down starting from Z position of the best image in focus. The captured RGB images are converted to YCbCr color space to have the color CbCr and intensity Y channels separated with the objective to preserve the color information of the best in focus image. However this algorithm utilizes the Fourier approach by using the Y channel frequency content via analyzing the Fourier coefficients for retrieving the high frequencies in order to obtain the best possible characteristics of every captured image. After this process, we construct the fused image with these coefficients and color information for the optimum in focus image in the YCbCr color space, as a result, we obtain a precise final RGB fused image.
One of the most important performance measures for pattern recognition systems is the discrimination capability, or how well a system can recognize objects of interest as well as reject wrong objects and the background. In real time opto-digital pattern recognition systems the light efficiency (how much of the input light energy passes trough the system) and parameters of optical setup should also taken into account. In this work we propose a new adaptive composite correlation filters based on synthetic discriminant functions, which are able to improve significantly the discrimination capability and which yield a high light efficiency. An iterative design procedure is used for the digital design of phase-only filter. A desired value of the discrimination capability is obtained by exploiting information about the target signal, background, and objects to be rejected. Next the designed filter with a high light efficiency is implemented in an optical setup. We use real scenes to test the proposed filter in a real-time opto-digital system. Experimental results obtained in the system are compared with those obtained with computer simulation.
One of the main problems in visual signal processing is incomplete information owing an occlusion of objects by other objects. It is well known that correlation filters mainly use contour information of objects to carry out pattern recognition. However, in real applications object contours are often disappeared. In these cases conventional correlation filters without training yield a poor performance. In this paper two novel methods based on correlation filters with training for recognition of partially occluded objects are proposed. The methods improve significantly discrimination capability of conventional correlation filters. The first method performs training of a correlation filter with both a target and objects to be rejected. In the second proposal two different correlation filters are designed. They deal independently with contour and texture information to improve recognition of partially occluded objects. Computer simulation results for various test images are provided and discussed.
We propose a new algorithm to determine the multifocus image fusion from several polychromatic images captured from the best focusing region where the best in focus image is included from a biological sample. This focusing region is built by including several images up and down starting from the Z position of the best image in focus. These captured RGB images are converted to YCbCr color space to have the color CbCr and intensity Y channels separated with the objective to preserve the color information of the best in focus image. Several approaches have been developed to fuse images, like those algorithms based on the wavelets transform, Laplacian, ratio, contrast or morphological pyramids selection, fusion by averaging, Bayesian methods, fuzzy sets, and artificial networks. However, this algorithm utilizes the Fourier approach by using the Y channel frequency content via analyzing the Fourier coefficients to retrieve the high frequencies to obtain the best possible characteristics of every captured image. After the completion of this process, we continue to construct the fused image with these coefficients and color information for the optimum in focus image in the YCbCr color space; as a result, we obtain a precise final RGB fused image.
We present a new algorithm to determine, quickly and accurately, the best-in-focus image of biological particles. The algorithm is based on a one-dimensional Fourier transform and on the Pearson correlation for automated microscopes along the Z axis. We captured a set of several images at different Z distances from a biological sample. The algorithm uses the Fourier transform to obtain and extract the image frequency content of a vector pattern previously specified to be sought in each captured image; comparing these frequency vectors with the frequency vector of a reference image (usually the first image that we capture or the most out-of-focus image), we find the best-in-focus image via the Pearson correlation. Numerical experimental results show the algorithm has a fast response for finding the best-in-focus image among the captured images, compared with related autofocus techniques presented in the past. The algorithm can be implemented in real-time systems with fast response, accuracy, and robustness; it can be used to get focused images in bright and dark fields; and it offers the prospect of being extended to include fusion techniques to construct multifocus final images.
Adaptive nonlinear filters based on nonparametric Spearman’s correlation between ranks of an input scene computed in a moving window and ranks of a target for illumination-invariant pattern recognition are proposed. Several properties of the correlations are investigated. Their performance for detection of noisy objects is compared to the conventional linear correlation in terms of noise robustness and discrimination capability. Computer simulation results for a test image corrupted by mixed additive and impulsive noise are provided and discussed.
White spot syndrome (WSSV) is a viral disease which affects many crustacean species including commercial shrimps. Adequate, precise and quick methods to diagnose on time the presence of the disease in order to apply different strategies to avoid the dispersion and to reduce mortalities is necessary. Histopathology is an important diagnostic method. However, histopathology has the problem that requires time to prepare the histological slides and time to arrive to some diagnosis because this depend on the nature of the tissues, the pathogen(s) to find, the number of organisms, number of slides to analyze and the skill of the technician. This paper try to demonstrate the sensibility of one digital system of processing and recognition of images using color correlation with phase filters, to identify inclusion bodies of WSSV. Infected tissues were processed to obtain histological slides and to verify that the inclusion bodies observed were of WSV, in situ hybridization were carried out. The sensibility results of the recognition of the inclusion bodies of WSSV with the color correlation program was 86.1%. The highest percentage of recognition was in nervous system and tegument glands with 100%. The values in the stomach epithelium and heart tissue was 78.45% of recognition. Tissues with the lowest recognition values were lymphoid organ and hematopoietic tissue. It is necessary further studies to increase the sensibility and to obtain the specificity.
A new autofocus algorithm based on one-dimensional Fourier transform and Pearson correlation for Z automatized microscope is proposed. Our goal is to determine in fast response time and accuracy, the best focused plane through an algorithm. We capture in bright and dark field several images set at different Z distances from biological organism sample. The algorithm uses the one-dimensional Fourier transform to obtain the image frequency content of a vectors pattern previously defined comparing the Pearson correlation of these frequency vectors versus the reference image frequency vector, the most out of focus image, we find the best focusing. Experimental results showed the algorithm has fast response time and accuracy in getting the best focus plane from captured images. In conclusions, the algorithm can be implemented in real time systems due fast response time, accuracy and robustness. The algorithm can be used to get focused images in bright and dark field and it can be extended to include fusion techniques to construct multifocus final images beyond of this paper.
Tuberculosis is a serious illness which control is mainly based on presumptive diagnosis. A technique commonly used consists of analyzing sputum images for detecting bacilli. However, the analysis of sputum is quite expensive, time consuming and requires highly trained personnel to avoid high errors. Image processing techniques provide a good tool for improving the manual screening of samples. In this paper we present a new bacilli detection technique with the aim to attain a high specificity rate and therefore for reducing the time required to analyze such sputum samples. This technique is based on the neuristic acknowlege extracted from the bacilli shape contour. It uses also the color information for image segmentation and finally a classification tree is used to categorize if a sample is positive or negative.
The Karhunen-Loeve transform based on calculation of the eigenvalues and eigenfunctions of the Karhunen-Loeve integral equation is known to have certain properties which make it optimal for many signal detection and filtering applications. We propose an analytical solution of the equation for a practical case when the covariance function of a stationary process is exponentially oscillating. Computer simulation results using a real aerial image are provided and discussed.
KEYWORDS: Organisms, Phase only filters, Statistical analysis, System identification, Ecology, Oceanography, Climate change, Climatology, Data conversion, Digital image processing
The taxonomic identification of diatom species that constituted phytoplankton communities in remote times is determined in several research fields like ecology, evolution, paleocology and biostratigraphy. In the last 30 years the use of fossil diatoms like environmental indicators has become of prime importance. However the use of these organisms is limited since they are found in sediment samples mostly fragmented or pulverized. This may lead to confusion and loss of information. In this work we used invariant correlation to identify 21 species of fossil diatoms. This correlation method is invariant to position, scale and rotation of the image. With this method we were able to identify the diatom species from only a small fragment of the organisms. Results showed that it is possible to identify some species having a range since 2.12% of information of the image. For example the minimum percentage was for Azpeitia nodulifer var A. This methodology can be used for the development of an automated system of plankton identification. An automatized identification of diatoms would be able to guarantee a faster identification and also would reduce the time necessary for accomplishing analysis of samples highly fragmengted.
The secure identification of parasites can be problematic and yet it is of prime importance. However, the specific identification of the parasites with traditional techniques can be slow and time consuming, requiring quality preparations where each taxonomically important structure can be clearly observed. Color information becomes an important discriminant feature, which we need to include in the whole identification process. Digital images of the monogeneans: Heterobothrium ecuadori and Neobenedenia melleni and, the digeneans Lintonium vibex, Homalometron longisinosum, Bianium plicitum and Phyllodistomum mirandai were processed to obtain their diffraction patterns. A numerical simulation was performed in order to correlate diffraction patterns of parasites species with phase only filters. The position, scale and rotation invariant image recognition was made through the scale transform.
Bacteria segmentation of particular species entails a challenging process. Bacteria shape is not enough as a discriminant feature, because there are many species that share the same shape. We present here two methods for tuberculosis image segmentation using the chromatic information. The first method is based on fuzzy segmentation of the color images based on the information that it is entailed in each separate chromatic histogram. The second method is a simple color filtering account by comparison of the inverse of the yellowish stained bacteria (blue channel) with the product of the other two chromatic channels. The third method is based on the extraction of image signatures by projecting logarithmic-polar mappings onto 1D vectors. This representation provides a very compact description of all image aspects, including shape, texture and color. An achromatic segmentation method is also presented based on the use of gray-level morphological operators only to the green channel. Finally we present the results of different autofocusing algorithms of stained tuberculosis images.
A new technique for local contrast enhancement using rank-order filters with spatially adaptive neighborhoods is proposed. The technique is based on the unsharp masking operation. However, instead a linear lowpass filtering we use various rank-order smoothing operations. The smoothing is performed over the pixels of spatially adaptive neighborhoods of details to be enhanced and their surrounding backgrounds. Various rank-order filters for local enhancement of small and middle-size details are implemented. Computer simulation results using a real aerial image are provided and discussed.
At present, a topic of great interest for the scientific community is to obtain an automatic monitoring system of red tide blooming organisms. The advances in automated monitoring systems have demonstrated that this automation is possible. In this paper, an analysis of the problems in the automated identification of red tide phytoplankton blooming is presented, using an automatic optical-digital system. Specifically, interclass size differences of organisms, different rotation and localization of the organisms in a microscope field and interclass of these same properties. The analysis was done automatically using a liquid crystal display device as interface of the digital with the optical part. This analysis is done for the first time in a hybrid system in real time.
Tuberculosis (TB) and other mycobacteriosis are serious illnesses which control is mainly based on presumptive diagnosis. Besides of clinical suspicion, the diagnosis of mycobacteriosis must be done through genus specific smears of clinical specimens. However, these techniques lack of sensitivity and consequently clinicians must wait culture results as much as two months. Computer analysis of digital images from these smears could improve sensitivity of the test and, moreover, decrease workload of the micobacteriologist. Bacteria segmentation of particular species entails a complex process. Bacteria shape is not enough as a discriminant feature, because there are many species that share the same shape. Therefore the segmentation procedure requires to be improved using the color image information. In this paper we present two segmentation procedures based on fuzzy rules and phase-only correlation techniques respectively that will provide the basis of a future automatic particle' screening.
The taxonomic identification of diatom species that constituted phytoplankton communities in remote times is determining in several research fields like ecology, evolution, paleoecology and biostratigraphy. In the last 30 years the use of fossil diatoms like environmental indicators has become of prime importance. However, the use of these organisms is limited since they are found in sediment samples mostly fragmented or pulverized. This may lead to confusion and loss of information. In this work we used invariant correlation to identify 12 species of fossil diatoms. With this method we were able to identify the diatom species from only a small fragment of the organisms. This methodology can be used for the development of an automated system of plankton identification. An automatized identification of diatoms would be able to guarantee a faster identification of diatoms would be able to guarantee a faster identification and also would reduce the time necessary and also would reduce the time necessary for accomplishing analysis of samples highly fragmented.
A new approach to design rank-order filters based on an explicit use of spatial relations between image elements is proposed. Many rank-order processing techniques may be implemented by applying the approach, such as noise suppression, local contrast enhancement, and local detail extraction. The performance of the proposed rank-order filters for suppression a strong impulsive noise in a test interferogram-like image is compared to conventional rank- order algorithms. The comparisons are made using a mean square error, a mean absolute error, and a subjective human visual error criteria.
The detection of image changes irrespective on geometric transformations are required in many applications. In this paper we present a novel use of the scale transform oriented to image identification and registration. If we translate a signal then all the information appears in the phase of the Fourier transform of the translated signal. Similarly, if we scale or rotate an image all the information about the amount of scaling or rotation appear in the phase of the scale transform. In the present study we report a very precise image identification technique based on the use of the power cepstrum of the scale transform. Cepstral filtering can be considered as a non-linear adaptive prefilter followed by an autocorrelation operation. The accuracy of the cepstrum techniques and the speed of the Fourier transform makes the present method faster and more robust to noise than other existing techniques. Image registration has been accomplished by computing the power cepstrum of the log-polar scale mapping. The performance of the improved method has been experimentally verified in a class of typed characters and diatom images in lighting microscopy.
Application of color correlation optical systems for the recognition of Vibrio cholerae 01 in seawater samples with matched filters and phase only filters recorded in holographic plates in three channels (RGB).
Detection of virus in shrimp tissue using digital color correlation is presented. Phase filters in three channels (red, green and blue) were used in order to detect HPV virus like target. These first results obtained showed that is possible to detect virus in shrimp tissue. More research must be made with color correlation in order to consider natural morphology of the virus, color, scale and rotation and noise in the samples.
Several random bi-dimensional rough surfaces with known Gaussian statistics were made in the laboratory. The surfaces were coated with a thin film of aluminium to increase the surface reflectivity. Light coming from a source is incident to the surface at an angle theta and the light is reflected from the surface according to the distribution of slopes. Glitter patterns were measured with a CCD to differents reflection angles. Statistical properties were obtained and analyzed. At the same time, glitter patterns of sea surface were analyzed in order to obtain statistical properties of the surface heights. The results show that it is possible to obtain statistical properties of the surface heights from their glitter patterns.
In this work, we investigate the influence of the pulse-shape uncertainty on the accuracy of inverse deconvolution algorithms for improving the resolution of long- pulse lidars.
KEYWORDS: Signal detection, Sun, Data modeling, Interfaces, Image processing, Monte Carlo methods, Correlation function, Solids, Fourier transforms, Sensors
The problem of retrieving spatial information of the sea surface heights from aerial images is considered. We proceed, for simplicity, by considering a one-dimensional model of the problem. With some simplifying assumptions, we derive some analytical and numerical results that relate the autocorrelation of the surface heights and those of the sunglint patterns. We assume that the surfaces are such that they constitute approximations to Gaussian random processes. We also assume that the surfaces are illuminated by a source (the sun) of a fixed angular extent and imaged through a lens that subtends a very small solid angle. With these assumptions, we calculate their images, as they would be formed by a signal clipping detector. In order to do this, we define a `glitter function,' which operates on the slope of the surfaces. To test our predictions we have conducted a Monte Carlo type simulation. Random surfaces with two different power spectra have been generated in a computer. We find that under favorable conditions, it is possible to invert the relation numerically and estimate the surface height autocorrelation from the sunglint data. We obtain the wave spectra from the surface height autocorrelation via a Fourier transform.
The question of retrievieng spatial information of sea surface heights from aerial photographs
is considered. With some siiplifying assumptions, a one-dimensional model for
the problem is proposed and a numerical relation between the surface height autocorrelation
and the autocorrelation of the intensity variations in the photograph is found.
Furthermore, it is possible to invert numerically the relation to estimate the former
from the latter. The results are supported with a computer simulated example.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.