Dr. Tapas Kanungo Profile

Dr. Tapas Kanungo

Research Staff Member at Yahoo Inc

SPIE Involvement:

Author

Proceedings Article | 13 January 2003 Paper

Document structure analysis algorithms: a literature survey

Song Mao, Azriel Rosenfeld, Tapas Kanungo

Proceedings Volume 5010, (2003) https://doi.org/10.1117/12.476326

KEYWORDS: Image segmentation, Detection and tracking algorithms, Optical character recognition, Error analysis, Image processing algorithms and systems, Analytical research, Stochastic processes, Rule based systems, Prototyping, Visualization

Read Abstract +

Proceedings Article | 18 December 2001 Paper

Stochastic language model for analyzing document physical layout

Tapas Kanungo, Song Mao

Proceedings Volume 4670, (2001) https://doi.org/10.1117/12.450736

KEYWORDS: Image segmentation, Detection and tracking algorithms, Stochastic processes, Image processing algorithms and systems, Data modeling, Associative arrays, Performance modeling, Error analysis, Visual process modeling, Mathematical modeling

Read Abstract +

Proceedings Article | 21 December 2000 Paper

TRUEVIZ: a groundtruth/metadata editing and visualizing toolkit for OCR

Tapas Kanungo, Chang Lee, Jeff Czorapinski, Ivan Bella

Proceedings Volume 4307, (2000) https://doi.org/10.1117/12.410825

KEYWORDS: Visualization, Image visualization, Java, Image segmentation, Optical character recognition, Visual analytics, Computer programming languages, Computer programming, Fiber optic illuminators, Databases

Read Abstract +

Proceedings Article | 22 December 1999 Paper

Empirical performance evaluation of page segmentation algorithms

Song Mao, Tapas Kanungo

Proceedings Volume 3967, (1999) https://doi.org/10.1117/12.373507

KEYWORDS: Image segmentation, Optical character recognition, Detection and tracking algorithms, Error analysis, Image processing algorithms and systems, Statistical analysis, Performance modeling, Statistical modeling, Algorithms, Optimization (mathematics)

Read Abstract +

Proceedings Article | 29 January 1999 Paper

Performance evaluation of two Arabic OCR products

Tapas Kanungo, Gregory Marton, Osama Bulbul

Proceedings Volume 3584, (1999) https://doi.org/10.1117/12.339809

KEYWORDS: Optical character recognition, Algorithm development, Visualization, Lithium, Visual analytics, Detector development, Analytical research, Raster graphics, Defense and security, Lawrencium

Read Abstract +

Proceedings Article | 7 January 1999 Paper

OmniPage vs. Sakhr: paired model evaluation of two Arabic OCR products

Tapas Kanungo, Gregory Marton, Osama Bulbul

Proceedings Volume 3651, (1999) https://doi.org/10.1117/12.335808

KEYWORDS: Optical character recognition, Image resolution, Visualization, Systems modeling, Image processing, Data modeling, Statistical modeling, Performance modeling, Statistical analysis, Defense and security

Read Abstract +

Characterizing the performance of Optical Character Recognition (OCR) systems is crucial for monitoring technical progress, predicting OCR performance, providing scientific explanations for the system behavior and identifying open problems. While research has been done in the past to compare performances of two or more OCR systems, all assume that the accuracies achieved on individual documents in a dataset are independent when, in fact, they are not. In this paper we show that accuracies reported on any dataset are correlated and invoke the appropriate statistical technique--the paired model--to compare the accuracies of two recognition systems. Theoretically we show that this method provides tighter confidence intervals than methods used in OCR and computer vision literature. We also proposed a new visualization method, which we call the accuracy scatter plot, for providing a visual summary of performance results. This method summarizes the accuracy comparisons on the entire corpus while simultaneously allowing the researcher to visually compare the performances on individual document images. Finally, we report on the accuracy and speed performances as a function of scanning resolution. Contrary to what one might expect, the performance of one of the systems degrades when the image resolution is increased beyond 300 dpi. Furthermore, the average time taken to OCR a document image, after increasing almost linearly as a function of resolution, suddenly becomes a constant beyond 400 dpi. This behavior is most likely because the OCR algorithm samples the images at resolutions 400 dpi and higher to a standard resolution. The two products that we compare are the Arabic OmniPage 2.0 and the Automatic Page Reader 3.01 from Sakhr. The SAIC Arabic dataset was used for the evaluations. The statistical and visualization methods presented in this article are very general and can be used for comparing accuracies of any two recognition systems, not just OCR systems.

Proceedings Article | 7 January 1999 Paper

The Bible, truth, and multilingual OCR evaluation

Tapas Kanungo, Philip Resnik

Proceedings Volume 3651, (1999) https://doi.org/10.1117/12.335806

KEYWORDS: Optical character recognition, Binary data, Image processing, Data modeling, Image compression, Lanthanum, Algorithm development, Associative arrays, Model-based design, Licensing

Read Abstract +

Proceedings Article | 2 October 1998 Paper

Approximating large convolutions in digital images

Tapas Kanungo, David Mount, Nathan Netanyahu, Christine Piatko, Ruth Silverman, Angela Wu

Proceedings Volume 3454, (1998) https://doi.org/10.1117/12.323258

KEYWORDS: Convolution, Binary data, Image processing, Fourier transforms, Computer science, Mathematical morphology, Algorithm development, Data centers, Krypton, Imaging arrays

Read Abstract +

Proceedings Article | 28 March 1995 Paper

Estimation of morphological degradation parameters

Tapas Kanungo, Robert Haralick

Proceedings Volume 2424, (1995) https://doi.org/10.1117/12.205268

KEYWORDS: Statistical analysis, Statistical modeling, Binary data, Computer simulations, Printing, Adaptive optics, Visualization, Intelligence systems, Optical character recognition, Polonium

Read Abstract +

Proceedings Article | 23 June 1993 Paper

Statistical morphology

Robert Haralick, Edward Dougherty, Jaekyu Ha, Tapas Kanungo, S. Karasu, Chang Lee, Larry Rystrom, Visvanathan Ramesh, Ihsin Phillips

Proceedings Volume 2030, (1993) https://doi.org/10.1117/12.146659

KEYWORDS: Process modeling, Lithium, Intelligence systems, Imaging systems, Statistical analysis, Binary data, Interference (communication), Image segmentation, Electrical engineering, Coastal modeling

Read Abstract +

Statistical Morphology is concerned with the statistical characterization of the four morphological operations — dilation, erosion, opening and closing. By statistical characterization of a morphological operator we mean the statistical characterization of the output in terms of the statistical characteristics of the input. Characterization of operators allows us to predict the characteristics of the output of an algorithm composed of a sequence of morphological operations in terms of the statistical characteristics of the input and the sequence of morphological operators used. Furthermore, such statistical analyses of morphological algorithms is necessary for evaluating the algorithm's performance. In this paper we describe what we have learned about one way to characterize the dilation and opening morphological operators in a one dimensional setting. That is, the input to each of these operators is assumed to be binary one-dimensional. The input is modeled as a union of randomly translated discrete lines of a fixed length. The line segments can overlap and result in line segments of various lengths. Thus the final output appears as an unordered pattern of lines and gaps of various lengths. This input is characterized by giving its line and gap length distribution and the distribution of the number of line and gap segments of various lengths. The characterization of a morphological operator, therefore, entails a similar characterization of the output. There has been a recent interest in the area of statistical morphology and some results have been published in the literature. Morales and Acharya {MA92} analyzed the statistical characteristics of a morphological opening on grayscale signals perturbed by Gaussian noise. Stevenson and Arce {SA92] studied the effects of opening for a class of structuring elements. Atola, Koskinen and Neuvo [ALN93] studied the output distributions of one dimensional grayscale filtering. Costa and Haralick {CH92} came up with an empirical description of the output graylevel distributions of morphologically opened signals. Dougherty and Loce [DL93] used libraries of structuring elements to restore corrupted signals in the case when a noise model is available. In the following section we set up the notation and definitions used in this paper. In section 3 we give a formal statement of the random process used to generate random sequences. In section 4 we give a maximum likelihood algorithm for estimating the model parameters. The four morphological operators are characterized in section 5.

Proceedings Article | 1 March 1991 Paper

Experimental methodology for performance characterization of a line detection algorithm

Tapas Kanungo, Mysore Jaisimha, Robert Haralick, John Palmer

Proceedings Volume 1385, (1991) https://doi.org/10.1117/12.25352

KEYWORDS: Detection and tracking algorithms, Signal to noise ratio, Machine vision, Edge detection, Sensors, Computer vision technology, Cerium, Algorithm development, Psychophysics, Corner detection

Read Abstract +

Proceedings Article | 1 November 1990 Paper

B-code dilation and structuring element decomposition for restricted convex shapes

Tapas Kanungo, Robert Haralick, Xinhua Zhuang

Proceedings Volume 1350, (1990) https://doi.org/10.1117/12.23609

KEYWORDS: Image processing, Binary data, Aluminum, Image segmentation, Computing systems, Electrical engineering, Computer engineering, Algorithm development, Mathematical morphology, Feature extraction

Read Abstract +