The Indexing and Retrieval of Document Images

Lexicon-free handwritten word spotting using character HMMs

An algorithm for robust machine recognition of keywords embedded in a poorly printed document is presented For each keyword, two statistical models, called pseudo 2-D hidden Markov models, are created for representing the actual keyword and all the other extraneous words, respectively Dynamic programming is then used for matching an unknown input word with the two models and for making a maximum likelihood decision Although the models are pseudo 2-D in the sense that they are not fully connected 2-D networks, they are shown to be general enough in characterizing printed words efficiently These models facilitate a nice "elastic matching" property in both horizontal and vertical directions, which makes the recognizer not only independent of size and slant but also tolerant of highly deformed and noisy words The system is evaluated on a synthetically created database that contains about 26000 words Currently, the authors achieve a recognition accuracy of 99% when words in testing and training sets are of the same font size, and 96% when they are in different sizes In the latter case, the conventional 1-D HMM achieves only a 70% accuracy rate >

Keyword spotting in poorly printed documents using pseudo 2-D hidden Markov models

An integrated media image information storage and retrieval system processes information supplied by different types of media. A processor-based network server operates as a system interface between one or more user control terminals, a media image capture station through which media image input/output devices are coupled to the network server, and a memory for storing media image files to be retrieved for reproduction. A supervisory media image manipulation and control program is accessed through a supervisory graphical user interface at any user control terminal, and has embedded subordinate media image manipulation programs for different types of media and information formats. When using the interface to import information from an arbitrary medium, the user is able to generate a first, index storage file, and a supplemental text description-based file, so as to facilitate rapid retrieval of any type of data, regardless of its original format (e.g. text, picture, text-picture combination, video, audio) and regardless of the capture medium or source from which it is imported into the system.

System for storage and retrieval of diverse types of information obtained from different media sources which includes video, audio, and text transcriptions

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. >

Document image decoding using Markov source models

A hidden-Markov-model (HMM)-based system for font-independent spotting of user-specified keywords in a scanned image is described. Word bounding boxes of potential keywords are extracted from the image using a morphology-based preprocessor. Feature vectors based on the external shape and internal structure of the word are computed over vertical columns of pixels in a word bounding box. For each user-specified keyword, an HMM is created by concatenating appropriate context-dependent character HMMs. Nonkeywords are modeled using an HMM based on context-dependent subcharacter models. Keyword spotting is performed using a Viterbi search through the HMM network created by connecting the keyword and nonkeyword HMMs in parallel. Applications of word-image spotting include information filtering in images from facsimile and copy machines, and information retrieval from text image databases. >

D.S. Bloomberg

Papers

Word spotting in scanned images using hidden Markov models