Document image quality: making fine discriminations

We estimate, using synthetically generated images, the smallest changes in document image quality that can be distinguished reliably and fully automatically by T. Kanungo's (1996) bootstrapping test. Six parameters of a physics based document image degradation model (H.S. Baird, 1992), are varied, one at time: for each, over a range of parameter value differences, two sets of synthetic images are generated pseudorandomly and the two sets tested for statistical equivalence using Kanungo's method. The rate at which Kanungo's method rejects the hypothesis that the two sets are drawn from the same distribution is analyzed as a function of parameter difference (a specialized "power function"). The finest discriminations afforded by the method are given by the width of the power function at a low fixed reject threshold. The data show that remarkably fine discriminations are possible-often subtler than are evident to visual inspection-for all six parameters. As few as 25 reference images are sufficient. These results suggest that Kanungo's method is sufficiently sensitive to a wide range of physics based image degradations to serve as an engineering foundation for many image quality estimation and OCR engineering purposes.

[1]  Jianying Hu,et al.  Next-generation multimedia messaging , 1997, Proceedings of First Signal Processing Society Workshop on Multimedia Signal Processing.

[2]  Henry S. Baird,et al.  Asymptotic accuracy of two-class discrimination , 1994 .

[3]  George Nagy,et al.  Self-correcting 100-font classifier , 1994, Electronic Imaging.

[4]  Henry S. Baird.  Fast algorithms for LSI artwork analysis , 1977, DAC '77.

[5]  Kazuhiko Yamamoto,et al.  Structured Document Image Analysis , 1992, Springer Berlin Heidelberg.

[6]  Tin Kam Ho,et al.  Evaluation of OCR Accuracy Using Synthetic Data , 1995 .

[7]  Henry S. Baird,et al.  A FAX Reader for the Blind , 1990, 1990 Conference Record Twenty-Fourth Asilomar Conference on Signals, Systems and Computers, 1990..

[8]  Robert M. Haralick,et al.  Document Degradation Models: Parameter Estimation and Model Validation , 1994, MVA.

[9]  Lawrence D. Jackel,et al.  Constrained neural network for unconstrained handwritten digit recognition , 1990 .

[10]  Tin Kam Ho,et al.  Large-Scale Simulation Studies in Image Pattern Recognition , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Tapas Kanungo,et al.  Document degradation models and a methodology for degradation model validation , 1996 .

[12]  Henry S. Baird,et al.  Feature identification for hybrid structural/statistical pattern classification , 1988, Comput. Vis. Graph. Image Process..

[13]  Robert M. Haralick,et al.  Power functions and their use in selecting distance functions for document degradation model validation , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[14]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[15]  Henry S. Baird,et al.  Document image defect models and their uses , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[16]  Henry S. Baird,et al.  Coordination Software for Robotic Workcells , 1984, ICRA.

[17]  Y. Le Cun,et al.  Optical character recognition: a technology driver for neural networks , 1990, IEEE International Symposium on Circuits and Systems.

[18]  Henry S. Baird,et al.  A family of European page readers , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[19]  Henry S. Baird,et al.  Language-free layout analysis , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[20]  Henry S. Baird,et al.  An artwork design verification system , 1975, DAC '75.

[21]  Tin Kam Ho,et al.  Pattern Classification with Compact Distribution Maps , 1998, Comput. Vis. Image Underst..

[22]  K. S. Baird,et al.  Anatomy of a versatile page reader , 1992, Proc. IEEE.

[23]  H. Damasio,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence: Special Issue on Perceptual Organization in Computer Vision , 1998 .

[24]  Colin L. Mallows,et al.  High-performance OCR preclassification trees , 1995, Electronic Imaging.

[25]  Tin Kam Ho,et al.  Estimating the intrinsic difficulty of a recognition problem , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[26]  Lauren MacLennan,et al.  Annual research report , 1991 .

[27]  H. S. Baird,et al.  Applications of multidimensional search to structural feature identification , 1988 .

[28]  Henry S. Baird,et al.  Image segmentation by shape-directed covers , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[29]  Henry S. Baird,et al.  Language identification in Complex, Unoriented, and Degraded Document Images , 1996, DAS.

[30]  Y. Le Cun,et al.  VLSI implementations of electronic neural networks: an example in character recognition , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[31]  Yann LeCun,et al.  Handwritten zip code recognition with multilayer networks , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.