Document image decoding using Markov source models

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 16; no. 6; pp. 602 - 617
• Main Authors: Kopec, G.E., Chou, P.A.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.06.1994; IEEE Computer Society
• Subjects: Applied sciences; Artificial intelligence; Automata; Computer science; control theory; systems; Decoding; Dynamic programming; Exact sciences and technology; Heuristic algorithms; Image converters; Image generation; Image recognition; Noise generators; Pattern recognition. Digital image processing. Computational geometry; Stochastic processes; Transducers; Stochastic model; Image recognition; Decoding; Grammar; Markov model; Pattern recognition; Document; Automatic recognition
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/34.295905

Document image decoding (DID) is a communication theory approach to document image recognition. In DID, a document recognition problem is viewed as consisting of three elements: an image generator, a noisy channel and an image decoder. A document image generator is a Markov source (stochastic finite-state automaton) that combines a message source with an imager. The message source produces a string of symbols, or text, that contains the information to be transmitted. The imager is modeled as a finite-state transducer that converts the 1D message string into an ideal 2D bitmap. The channel transforms the ideal image into a noisy observed image. The decoder estimates the message, given the observed image, by finding the a posteriori most probable path through the combined source and channel models using a Viterbi-like dynamic programming algorithm. The proposed approach is illustrated on the problem of decoding scanned telephone yellow pages to extract names and numbers from the listings. A finite-state model for yellow page columns was constructed and used to decode a database of scanned column images containing about 1100 individual listings.< >