The design and implementation of a Chinese financial invoice recognition system
International Symposium on VIPromCom Video/Image Processing and Multimedia Communications - Trang 79-82
Tóm tắt
This paper designs and implements a financial invoice recognition system based on the features of the Chinese financial invoice. By using the linear whole block moving method in each vertical segment, a new fast algorithm is put forward to detect and rectify slanted images. To distinguish the different form types (the foundation necessary for locating the form fields, filtering the form lines, etc), several representative form features are discussed and an invoice-type features library is built by using a semi-automatic machine study method. On the basis of the recognized invoice type, a real invoice form is re-oriented against the corresponding blank form according to the invoice type feature, solving the problem of adhesion of characters and form lines, as well as the problem of character segmentation and recognition. Based on the financial Chinese invoice image feature, a mutual rectification mechanism founded on the recognition results of financial Chinese characters and Arabic numerals is put forward to raise the recognition rate. Finally, experimental results and conclusions are presented.
Từ khóa
#Character recognition #Optical character recognition software #Image recognition #Image segmentation #Image processing #Pattern recognition #High speed optical techniques #Optical filters #System testing #LaboratoriesTài liệu tham khảo
xiaoping, 1998, The Segmentation and Recognition of Unconstrained Handwritten Numerals, The Latest Development of Computer Intelligent Interface and Intelligent Applications, 86
10.1109/ICDAR.1995.598979
fletcher, 1987, Segmentation of Binary Images into Text Strings and Graphics, SPIE, 786, 533
mori, 1984, Line Filtering and its Application to Stroke Segmentation of Hand-printed Chinese Characters, Proc Int Conf Pattern Recognition, 366
shih, 1988, Generation of a Line Description File for Graphics Recognition, SPIE, 937, 568
jiazhong, 1996, Handwritten Chinese Character Recognition System, Journal of Software, 15
bunke, 1982, Automatic Interpretation of Text and Graphics in Circuit Diagrams, Pattern Recognition Theory and Applications", 297, 10.1007/978-94-009-7772-3_18
10.1016/0734-189X(86)90128-3
delie, 2000, The Slanting Image Detecting and Rectifying Technology in OCR System, Journal of Huazhong University of Science and Technology, 28, 66
10.1109/MCG.1985.276400
delie, 2000, An Improved Algorithm for Handwritten Chinese Text Segmentation, Journal of Huazhong University of Science and Technology, 28, 87