Quantifying the unimportance of prior probabilities in a computer vision problem

作者: David B. Sher , Jonathan J. Hull

DOI: 10.1016/0167-8655(90)90107-D

关键词:

摘要: Abstract We present an empirical investigation of the importance accurate assessment prior probabilities in a typical visual classification problem, handwritten ZIP Code recognition. found that little accuracy was gained by distribution over individual digits.

参考文章(21)
Jonathan J. Hull, A computational theory of visual word recognition State University of New York at Buffalo. ,(1988)
David B. Sher, Christopher M. Brown, A probabilistic approach to low-level vision The University of Rochester, Eastman School of Music. ,(1987)
R. Chellappa, Fitting Markov Random Field Models to Images. Defense Technical Information Center. ,(1981) , 10.21236/ADA095857
George Nagy, 29 Optical character recognition—Theory and practice Handbook of Statistics. ,vol. 2, pp. 621- 649 ,(1982) , 10.1016/S0169-7161(82)02032-X
Harry C. Andrews, B. R. Hunt, Digital image restoration dir. ,(1977)
John D. Lowrance, Thomas D. Garvey, Evidential Reasoning: An Implementation for Multisensor Integration Technical Note. ,vol. 307, ,(1983)
Radian Shinghal, Godfried T. Toussaint, A bottom-up and top-down approach to using context in text recognition International Journal of Human-computer Studies \/ International Journal of Man-machine Studies. ,vol. 11, pp. 201- 212 ,(1979) , 10.1016/S0020-7373(79)80017-6
Jonathan J. Hull, Sargur N. Srihari, Ramesh Choudhari, An Integrated Algorithm for Text Recognition: Comparison with a Cascaded Algorithm IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-5, pp. 384- 395 ,(1983) , 10.1109/TPAMI.1983.4767408
D. Neuhoff, The Viterbi algorithm as an aid in text recognition (Corresp.) IEEE Transactions on Information Theory. ,vol. 21, pp. 222- 226 ,(1975) , 10.1109/TIT.1975.1055355