Vemulapati Ramanaprasad

A system to read names and addresses on tax forms

The reading of names and addresses is one of the most complex tasks in automated forms processing. This paper describes an integrated real-time system to read names and addresses on tax forms of the U.S. Internal Revenue Service. The Name and Address Block Reader (NABR) system accepts both machine-printed and hand-printed address block images as input. The application software has two major steps: document analysis (connected component analysis, address block extraction, label detection, hand-print/machine-print discrimination) and document recognition. Document recognition has two nonidentical streams for machine-print and hand-print: the key steps are address parsing, character recognition, word recognition, and postal database lookup. (ZIP+4 and City-State-ZIP files.) System output is a packet containing the results of recognition together with database access status file. Real-time throughput (8500 forms/h) is achieved by employing a loosely coupled multiprocessing architecture where successive input images are distributed to available address recognition processors. The functional architecture, software design, system architecture, and the hardware implementation are described. Performance evaluation on machine-printed and handwritten addresses are presented.

Name and Address Block Reader system for tax form processing

The reading of names and addresses is one of the most complex tasks in automated forms processing. The paper describes an integrated real time system to read names and addresses on tax forms of the Internal Revenue Service of the United States. The Name and Address Block Reader (NABR) system accepts both machine printed and hand printed address block images as input. The application software has two major steps: document analysis (connected component analysis, address block extraction, label detection, hand print/machine print discrimination); and document recognition. Document recognition has two non identical streams for machine print and hand print; key steps are: address parsing, character recognition, word recognition and postal database lookup (ZIP+4 and City-State-ZIP files). Real time throughput (8,500 forms per hour) is achieved by employing a loosely coupled multiprocessing architecture. The functional architecture, software design, system architecture and hardware implementation are described. Performance evaluation on machine printed and handwritten addresses are presented.

Text - image separation in Devanagari documents

In this paper we present a top-down, projection-profilebased algorithm to separate text blocks from image blocksin a Devanagari document. We use a distinctive feature ofDevanagari text, called Shirorekha (Header Line) to analyzethe pattern produced by Devanagari text in the horizontalprofile. The horizontal profile corresponding to a textblock possesses certain regularity in frequency, orientationand shows spatial cohesion. The algorithm uses these featuresto identify text blocks in a document image containingboth text and graphics.

Creation of data resources and design of an evaluation test bed for Devanagari script recognition

The Indian subcontinent has a large number of languages, dialects, and scripts with the Devanagari script being the primary and most widely used of all the scripts. To date, much of the Devanagari optical character recognition (OCR) research has been restricted to a handful of groups. So, techniques have not yet been widely disseminated or evaluated independently and automated evaluation tools are currently not available for lack of a standard representation of ground-truth and result data. A key reason for the absence of sustained research efforts in off-line Devanagari OCR appears to be the paucity of data resources. Ground truthed data for words and characters, on-line dictionaries, corpora of text documents and reliable, standardized statistical analyses and evaluation tools are currently lacking. So, the creation of such data resources will undoubtedly provide a much needed fillip to researchers working on Devanagari OCR. This paper describes a National Science Foundation sponsored project under the International Digital Libraries program to create data resources that will facilitate development of Devanagari OCR technology and provide a standardized test bed and evaluation tools for Devanagari script recognition.

A system for segmentation and recognition of totally unconstrained handwritten numeral strings

Proposes a system for the segmentation and recognition of totally unconstrained handwritten numeral strings. The system is composed of several document analysis modules, namely a preprocessing module, a segmentation module and a recognition module. The preprocessing module includes connected component analysis, identifying substrings with touching digits and estimating the number of digits in the substring. The segmentation module is built with a new segmentation algorithm based on a thorough stroke analysis using contour representation of the strokes. In the recognition module, a high-performance digit recognizer is used for the isolated digit images after segmentation, and then a simple postprocessing routine is called for those cases where some punctuation marks or delimiters such as dashes, commas or periods are included in the numeral string. Due to the high performance of the segmentation module, the system is efficient and robust with a high recognition performance.

Document image-processing system for name and address recognition

This article describes a real‐time document image processing system. Its objective is to recognize names and addresses from scanned address block images extracted from various tax forms of the United States Internal Revenue Service. The Name and Address Block Reader (NABR) system accepts both machine‐ and hand‐printed address block images as input. Salient aspects of the system are presented, including document analysis (connected component analysis, address block extraction, label detection, hand‐print/machine‐print discrimination) and document recognition. Document recognition is performed in two nonidentical streams for machine‐and hand‐print; key steps are address parsing, character recognition, word recognition, and postal data base lookup (ZIP+4 and city‐state‐ZIP files). System output is a packet containing the results of recognition together with data base access status file. Real‐time throughput (8500 forms/h) is achieved by employing a loosely coupled multiprocessing architecture where successive input images are distributed to available address recognition processors. The functional architecture, software design, system architecture, and the hardware implementation are described. Performance evaluation on machine‐ and hand‐written addresses are presented.

Reading handwritten US census forms

Commercial forms-reading systems for extraction of data from forms do not meet acceptable accuracy requirements on forms filled out by hand. In December 1993, NIST called industry and research organizations working in the area of handwriting recognition to participate in a test to determine the state of the art in the area. A database of form images containing actual responses received by the US Census Bureau was provided. The handwritten responses are very loosely constrained in terms of writing style, format of response and choice of text. The sizes of the lexicons provided are very large (about 50000 entries) and yet the coverage is incomplete (about 70%). In this paper we discuss the approach taken by CEDAR to automate the task of reading the census forms. The subtasks of field extraction and phrase recognition are described.