Labelling logical structures of document images using a dynamic perceptive neural network

• Published in: International journal on document analysis and recognition Vol. 15; no. 1; pp. 45 - 55
• Main Authors: Rangoni, Yves, Belaïd, Abdel, Vajda, Szilárd
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer-Verlag 01-03-2012; Springer; Springer Verlag
• Subjects: Applied sciences; Artificial intelligence; Computer Science; Computer science; control theory; systems; Computer Vision and Pattern Recognition; Connectionism. Neural networks; Data processing. List processing. Character string processing; Document and Text Processing; Exact sciences and technology; Image Processing and Computer Vision; Memory organisation. Data processing; Original Paper; Pattern Recognition; Pattern recognition. Digital image processing. Computational geometry; Software; Logical labelling; Perceptive neural network; Time-delay neural network; Document image analysis and recognition; Layout analysis; Image recognition; Segmentation; Image processing; Error rate; Labelling; Dynamical system; Modeling; Document layout; Classification; Delay time; Dynamic model; Document analysis; Delay system; Text; Neural network; Character recognition; Image analysis; Optical character recognition; Document structure; Sensorial perception; Occupation time; logical labelling
• DOI: 10.1007/s10032-011-0151-y
• EISSN: 1433-2825
• ISSN: 1433-2833

This paper proposes a new method for labelling the logical structures of document images. The system starts with digitised images of paper documents, performs a physical layout analysis, runs an OCR and finally exploits the OCR’s outputs to find the meaning of each block of text (i.e. assigns labels like “Title”, “Author”, etc.). The method is an extension of our previous work where a classifier, the perceptive neural network, has been developed to be an analogy of the human perception. We introduce in this connectionist model a temporal dimension by the use of a time-delay neural network with local representation. During the recognition stage, the system performs several recognition cycles and corrections, while keeping track and reusing the previous outputs. This dynamic classifier allows then a better handling of noise and segmentation errors. The experiments have been carried out on two datasets: the public MARG containing more than 1,500 front pages of scientific papers with four zones of interest and another one composed of documents from the Siggraph 2003 conference, where 21 logical structures have been identified. The error rate on MARG is less than 2.5% and 7.3% on the Siggraph dataset.