Qualification: 
Ph.D, MSc, BE

Dr. Peeta Basa Pati currently served as Professor in the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Bengaluru.

He has completed Ph.D. from Indian Institute of Science Bangalore in 2007. His research interests include Intelligent Document Processing, Machine Learning. He has over 20 years of research experience and has 14 years of industrial experience. He has over 20 research papers published in Journals and Conferences; he is also inventor of 3 patents granted by USPTO and another published patent.

Education

  • 2007: Ph.D.
    Indian Institute of Science, Bangalore
  • 2001: M.Sc. (Engg.)
    Indian Institute of Science, Bangalore
  • 1998: B.E. Electrical Engineering
    NIT (REC) Rourkela

Professional Appointments

Year Affiliation
June 2021- Present Professor, Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Bengaluru
2007 – 2021 Chief Architect, Cognizant Technology Solutions

Research & Management Experience

  • 22 years of research experience
  • 14 years of experience in project, people and product management

Major Research Interests

  • Document Image Processing, Machine Learning, Text Engineering and Natural Language Processing

Membership in Professional Bodies

  • Senior Member - IEEE

Publications

Publication Type: Patent

Year of Publication Title

2019

Peeta Basa Pati, “System and method for automated processing of electronic documents”, 2019.

2019

Peeta Basa Pati, “A System and a Method for Developing a Tool for Automated Data Capture”, 2019.

2014

Peeta Basa Pati, “Data extraction confidence attribute with transformations”, 2014.

2013

Peeta Basa Pati, “Automatic data validation and correction”, 2013.

Publication Type: Book Chapter

Year of Publication Title

2010

R. S. Umesh, Peeta Basa Pati, and Ramakrishnan, A. G., “Design of a Bilingual Kannada–English OCR”, in Book Chap in Guide to OCR in Indic Scripts, Springer-Verlag, V. Govindaraju and Setlur, S. (Ranga), Eds. London: Springer London, 2010, pp. 97–124.[Abstract]


India is a land of many languages and consequently one often encounters documents that contain elements in multiple languages and scripts. This chapter presents an approach towards designing a bilingual OCR that can process documents containing both English and Kannada scripts which are used by the Kannada language of the southern Indian state of Karnataka. We report an efficient script identification scheme for discriminating Kannada from Roman script. We also propose a novel segmentation and recognition scheme for Kannada, which could possibly be applied to many other Indian languages as well.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2009

S. Sivananda, Sathyanarayana, V., and Peeta Basa Pati, “Industry-Academia Collaboration via Internships”, 2009 22nd Conference on Software Engineering Education and Training. 2009.[Abstract]


IT industry in India has witnessed high growth in the last few years. This rapid growth has created human resource demand supply mismatch. IT industry is continuously on the lookout for fresh and young talents. While the campus recruitment of fresh graduates can provide the required numbers, it has been widely recognized that such recruits lack the skills which are essential for a successful career in the corporate world. Internship is proving to be a valuable approach of identifying talent early on, enriching their technical skills, nurturing them with the requisite domain knowledge, and subsequently hire them into the organization.This paper shares the experiences of the authors at First Indian Corporation (FIC) on establishing an internship model and leveraging it to meet the organizationpsilas strategic needs

More »»

2007

F. Nourbakhsh, Peeta Basa Pati, and Ramakrishnan, A. G., “Automatic Seal Information Reader”, 2007 International Conference on Computing: Theory and Applications (ICCTA'07). pp. 502-505, 2007.[Abstract]


Seals contain a lot of vital information about the document. Seal detection is a necessary step to gain access to that information. In the present paper, we present a correlation based technique which exploits the existence of some constant character strings and their topology for detection of seals. We also present a technique which separates the false positives from the actual seals. We achieved an accuracy of about 98% for extraction of such kind of seals. Once the seal is extracted from a page image, an OCR has been employed to read the contextual information present in the seal. A knowledge based post-processing step is employed to enhance the accuracy of the recognized text strings

More »»

2007

Peeta Basa Pati and Ramakrishnan, A., “A Blind Indic Script Recognizer for Multi-script Documents”, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007). pp. 1248-1252, 2007.

2006

Peeta Basa Pati and Ramakrishnan, A. G., “HVS Inspired System for Script Identification in Indian Multi-script Documents”, Document Analysis Systems VII. Springer Berlin Heidelberg, Berlin, Heidelberg, 2006.[Abstract]


Identification of the script of the text, present in multi-script documents, is one of the important first steps in the design of an OCR system. Much work has been reported relating to Roman, Arabic, Chinese, Korean and Japanese scripts. Though some work has already been reported involving Indian scripts, the work is still in its nascent stage. For example, most of the work assumes that the script changes only at the level of the line, which is rarely an acceptable assumption in the Indian scenario. In this work, we report a script identification algorithm, which takes into account the fact that the script changes at the word level in most Indian bilingual or multilingual documents. Initially, we deal with the identification of the script of words, using Gabor filters, in a bi-script scenario. Later, we extend this to tri-script and then, five-script scenarios. The combination of Gabor features with nearest neighbor classifier shows promising results. Words of different font styles and sizes are used. We have shown that our identification scheme, inspired from the Human Visual System (HVS), utilizing the same feature and classifier combination, works consistently well for any of the combination of scripts experimented.

More »»

2006

F. Nourbakhsh, Peeta Basa Pati, and Ramakrishnan, A. G., “Text Localization and Extraction from Complex Gray Images”, Computer Vision, Graphics and Image Processing. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 776-785, 2006.[Abstract]


We propose two texture-based approaches, one involving Gabor filters and the other employing log-polar wavelets, for separating text from non-text elements in a document image. Both the proposed algorithms compute local energy at some information-rich points, which are marked by Harris' corner detector. The advantage of this approach is that the algorithm calculates the local energy at selected points and not throughout the image, thus saving a lot of computational time. The algorithm has been tested on a large set of scanned text pages and the results have been seen to be better than the results from the existing algorithms. Among the proposed schemes, the Gabor filter based scheme marginally outperforms the wavelet based scheme.

More »»

2006

Peeta Basa Pati, R, A. K., and Ramakrishnan, A. G., “Horizontal Projection Profiles for extraction of Text Paragraphs from Document Images”, IEEE Intl. Conf. on Sig. & Im. Proc. 2006.

2006

K. R. Arvind, Peeta Basa Pati, and Ramakrishnan, A. G., “Automatic text block separation in document images”, 2006 Fourth International Conference on Intelligent Sensing and Information Processing. pp. 53-58, 2006.[Abstract]


Separation of printed text blocks from the non-text areas, containing signatures, handwritten text, logos and other such symbols, is a necessary first step for an OCR involving printed text recognition. In the present work, we compare the efficacy of some feature-classifier combinations to carry out this separation task. We have selected length-normalized horizontal projection profile (HPP) as the starting point of such a separation task. This is with the assumption that the printed text blocks contain lines of text which generate HPP's with some regularity. Such an assumption is demonstrated to be valid. Our features are the HPP and its two transformed versions, namely, eigen and Fisher profiles. Four well known classifiers, namely, nearest neighbor, linear discriminant function, SVM's and artificial neural networks have been considered and efficiency of the combination of these classifiers with the above features is compared. A sequential floating feature selection technique has been adopted to enhance the efficiency of this separation task. The results give an average accuracy of about 96%.

More »»

2006

F. Nourbakhsh, Peeta Basa Pati, and Ramakrishnan, A. G., “Document Page Layout Analysis Using Harris Corner Points”, 2006 Fourth International Conference on Intelligent Sensing and Information Processing. pp. 149-152, 2006.[Abstract]


Extraction of text areas from the document images with complex content and layout is one of the challenging tasks. Few texture based techniques have already been proposed for extraction of such text blocks. Most of such techniques are greedy for computation time and hence are far from being realizable for real time implementation. In this work, we propose a modification to two of the existing texture based techniques to reduce the computation. This is accomplished with Harris corner detectors. The efficiency of these two textures based algorithms, one based on Gabor filters and other on log-polar wavelet signature, are compared. A combination of Gabor feature based texture classification performed on a smaller set of Harris corner detected points is observed to deliver the accuracy and efficiency.

More »»

2006

B. Antony, Peeta Basa Pati, and Ramakrishnan, A. G., “Binarization and Localization of Text Images Captured on a Mobile Phone Camera”, 2006 Fourth International Conference on Intelligent Sensing and Information Processing. pp. .224 – 229, 2006.

2006

Peeta Basa Pati and Ramakrishnan, A. G., “Can Biological Motion be a Biometric?”, 2006 Fourth International Conference on Intelligent Sensing and Information Processing. pp. 2-4, 2006.[Abstract]


Biological motion has successfully been used for analysis of a person's mood and other psychological traits. Efforts are made to use human gait as a non-invasive mode of biometric. In this reported work, we try to study the effectiveness of biological gait motion of people as a cue to biometric based person recognition. The data is 3D in nature and, hence, has more information with itself than the cues obtained from video-based gait patterns. The high accuracies of person recognition, using a simple linear model of data representation and simple neighborhood based classifiers, suggest that it is the nature of the data which is more important than the recognition scheme employed.

More »»

2005

S. S. Raju, Peeta Basa Pati, and Ramakrishnan, A. G., “Text Localization and Extraction from Complex Color Images”, Advances in Visual Computing. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 486-493, 2005.[Abstract]


Availability of mobile and hand-held imaging devices, such as, cell phones, PDA's, still and video cameras have resulted in new applications, where the text present in the acquired images is extracted and interpreted for various purposes. In this paper, we present a new algorithm for automatic detection of text in color images. Proposed system involves Gabor function based multi-channel filtering on the intensity component of the image along with Graph-Theoretical clustering applied on the color space of the same image, there-by utilizing the advantages of texture analysis as well as those of connected component for text detection. Our approach performs well on images with complex background.

More »»

2004

Peeta Basa Pati, S. Raju, S., Pati, N., and Ramakrishnan, A. G., “Gabor filters for document analysis in Indian bilingual documents”, International Conference on Intelligent Sensing and Information Processing, 2004. Proceedings of. pp. 123-126, 2004.

2004

S. S. Raju, Peeta Basa Pati, and Ramakrishnan, A. G., “Gabor filter based block energy analysis for text extraction from digital document images”, First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings. pp. 233-243, 2004.[Abstract]


Extraction of text areas is a necessary first step for taking a complex document image for diameter recognition task. In digital libraries, such OCR'ed text facilitates access to the image of document page through keyword search. Gabor filters, known to be simulating certain characteristics of the human visual system (HVS), have been employed for this task by a large number of scientists, in scanned document images. Adapting such a scheme for camera based document images is a relatively new approach. Moreover, design of the appropriate filters to separate text areas, which are assumed to be rich in high frequency components, from nontext areas is a difficult task. The difficulty increases if the clutter is also rich in high frequency components. Other reported works, on separating text from nontext areas, have used geometrical/structural information like shape and size of the regions in binarized document images. In this work, we have used a combination of the above mentioned approaches for the purpose. We have used connected component analysis (CCA), in binarized images, to segment nontext areas based on the size information of the connected regions. A Gabor function based filter bank is used to separate the text and the nontext areas of comparable size. The technique is shown to work efficiently on different kinds of scanned document images, camera captured document images and sometimes on scenic images.

More »»

2000

Peeta Basa Pati and Ramakrishnan, A. G., “Printed Odiya Character recognition System”, Proc. of Conf. of Information Technology, Dec’2000. . 2000.

Publication Type: Journal Article

Year of Publication Title

2008

Peeta Basa Pati and Ramakrishnan, A. G., “Word level multi-script identification”, Pattern Recognition Letters, vol. 29, pp. 1218-1229, 2008.[Abstract]


We report an algorithm to identify the script of each word in a document image. We start with a bi-script scenario which is later extended to tri-script and then to eleven-script scenarios. A database of 20,000 words of different font styles and sizes has been collected and used for each script. Effectiveness of Gabor and discrete cosine transform (DCT) features has been independently evaluated using nearest neighbor, linear discriminant and support vector machines (SVM) classifiers. The combination of Gabor features with nearest neighbor or SVM classifier shows promising results; i.e., over 98% for bi-script and tri-script cases and above 89% for the eleven-script scenario.

More »»

2005

Peeta Basa Pati and Ramakrishnan, A. G., “OCR in Indian Scripts: A Survey”, IETE Technical Review, vol. 22, pp. 217-227, 2005.[Abstract]


India is a multi-lingual country. A significantly large number of scripts are used to represent these languages. A desire of vision researchers is to develop an integrated Optical Character Recognition (OCR) system which will be able to process all such scripts. Such a development, if objectified, will not only enable faster flow of information across the country, but also have a profound impact on its scientific and economic development. Courageous endeavors have been successfully made towards the development of a system capable of recognizing machine-printed, or hand-written characters and/or numerals. However, most Indian scripts do not have an integrated OCR system. Further the development of a unified system which is capable of processing all Indian scripts is still a dream. This article presents a survey of the current literature on the development of OCR's in Indian scripts. Reviewing the basics of and the motivation towards the development of OCR system, the article analyzes the various methodologies employed in general purpose pattern recognition system. A critical analysis of the work towards OCR system in Indian languages, with pointers towards possible future work is also presented.

More »»

2002

D. Dhanya and Ramakrishnan, A. G., “Script Identification in Printed Bilingual Documents”, Document Analysis Systems V, vol. 27, pp. 73-82, 2002.[Abstract]


Identification of script in multi-lingual documents is essential for many language dependent applications suchas machine translation and optical character recognition. Techniques for script identification generally require large areas for operation so that sufficient information is available. Suchassumption is nullified in Indian context, as there is an interspersion of words of two different scripts in most documents. In this paper, techniques to identify the script of a word are discussed. Two different approaches have been proposed and tested. The first method structures words into 3 distinct spatial zones and utilizes the information on the spatial spread of a word in upper and lower zones, together with the character density, in order to identify the script. The second technique analyzes the directional energy distribution of a word using Gabor filters withsuitable frequencies and orientations. Words withv arious font styles and sizes have been used for the testing of the proposed algorithms and the results obtained are quite encouraging.

More »»

Keynote Addresses/Invited Talks/Panel Memberships

  • Tutorials
    • “Image Analysis with optimal space-frequency filters,” along with Prof. A G Ramakrishnan at Intl. Conf. on Systemic, Cybernetics and Informatics – 2007, Hyderabad, Jan’07.
    • “Gabor Filters for Image Processing,” along with Prof. A G Ramakrishnan at Intl. Conf. on Info. Tech. – 2006, Bhubaneswar, Dec’06.
    • “OCR and Handwriting Analysis” along with Prof. A G Ramakrishnan at Intl. Conf. on Systemic, Cybernetics and Informatics (ICSCI 2005), Hyderabad, Jan’05.
    •  “Biometric based Person Identification System,” along with Prof. A G Ramakrishnan at Conf. on Info. Tech. 2003, Bhubaneswar, Dec’03.
  • Invited Talks
    • “Introduction to Data Mining Techniques and Applications,” delivered a lecture series at Cognizant, Apr – May 2012.
    • “Image Restoration,” PES College of Engg., Bangalore, Sep’12.
    • “Introduction to Color Image Processing,” PES College of Engg., Bangalore, Oct’11.
    • “Image Analysis: Prospective and Challenges,” PES College of Engg., Bangalore, Jul’11.
    • “Challenges before Intelligent Document Analysis – An Overview,” at Institute of Technology and Education Research, Bhubaneswar, Nov’09.
    • “Document Image Analysis,” at Silicon Inst. of Tech., Bhubaneswar, Dec’08.
    •  “Text Localization in Complex Color Images,” at HP-Labs India, Bangalore, Feb’06.
    • “Document Image Analysis,” at NMAM Inst. of Tech., Nitte, Karnataka, Feb’06.
    • “Image Enhancement Techniques,” at MSR School of Advanced Studies, Mar’03.
    • “Principal Component Analysis (PCA) for Human Face Recognition,” at Regional College of Management, Bhubaneswar, Feb’03.
    • “Linear Techniques of Face Detection and Recognition,” at Institute of Technology and Education Research, Bhubaneswar, Feb’03.
  • Technical chair in international conferences
    • Member Program committee for ISED 2010
    • Member Program Committee for Summer school on Document Image Processing – 2008, conducted at CCE, IISc. Bangalore.
    • Tutorial Chair of the International Conf. on Info. Tech – 2006 & Publicity chair for ICIT – 2007.
    • Member of program or technical review committee for ISVC - 2005, 06, 07, 08, 09 & 2010 and ICIT – 2006, 07, 08 & 09
  • Reviewed research papers for journals and conferences
    • Springer Journal on Circuits, Systems & Signal Processing
    • IEE Proc. Vision, Image & Signal Processing journal
    • ISVC, USA - 2005, 06, 07, 08, 09 & 2010
    • ICIT, India – 2006, 07, 08 & 09

Courses Taught

  • Digital Image Processing
  • Introduction to Data Mining & Machine Learning
  • Biomedical Signal and Image Processing
  • Basic Electrical Engineering

Student Guidance

Postgraduate Students

Sl. No. Name of the Student(s) Topic Status – Ongoing/Completed Year of Completion
1 Sabari Raju S. Text Extraction of Complex Color Documents Completed 2004
2 Farshad Nourbakhsh Extraction of text, seal and handwritten in document images Completed 2006