APPLYING HUMAN KNOWLEDGE TO IMPROVE MACHINE RECOGNITION OF CONFUSING HANDWRITTEN NUMERALS

被引：5

作者：

NADAL, C ^{[1
]}

SUEN, CY ^{[1
]}

机构：

[1] CONCORDIA UNIV,DEPT COMP SCI,CTR PATTERN RECOGNIT & MACHINE INTELLIGENCE,1455 MAISONNEUVE BLVD,MONTREAL H3G 1M8,QUEBEC,CANADA

来源：

PATTERN RECOGNITION | 1993年 / 26卷 / 03期

关键词：

HANDWRITTEN NUMERAL; RELIABILITY; KNOWLEDGE BASE; HUMAN EXPERTS; AMBIGUITY;

D O I：

10.1016/0031-3203(93)90166-T

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

It is believed that the decision making process of existing algorithms can be refined by gaining more human knowledge, especially when trying to recognize confusing characters. Therefore, to help improve machine performance on confusing samples, comments collected from an experiment conducted with a group of human experts specialized in unconstrained handwritten numeral recognition are analyzed. Based on this knowledge, a tool is being built which will manage the information and give results of analyses to help distinguish the different confusing styles of writing. These analyses will facilitate the design of new specialized modules aimed at differentiating numerals belonging to the same confusing pair.

引用

页码：381 / 389

页数：9

共 50 条

[31] A HIGH-ACCURACY ALGORITHM FOR RECOGNITION OF HANDWRITTEN NUMERALS
BAPTISTA, G
KULKARNI, KM
PATTERN RECOGNITION, 1988, 21 (04) : 287 - 291
[32] Graph Based Features for Recognition of Handwritten Devanagiri Numerals
Bhat, Mohammad Idrees
Sharada, B.
Nagabhushan, P.
2016 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), VOL. 1, 2016, : 1710 - 1715
[33] Recognition of handwritten Hindi numerals using structural descriptors
Elnagar, A
AlKharousi, F
Harous, S
SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 983 - 988
[34] RECOGNITION OF HANDWRITTEN NUMERALS WITH MULTIPLE FEATURE AND MULTISTAGE CLASSIFIER
CAO, J
AHMADI, M
SHRIDHAR, M
PATTERN RECOGNITION, 1995, 28 (02) : 153 - 160
[35] An HMM based recognition scheme for handwritten Oriya numerals
Bhowmik, Tapan K.
Parui, Swapan K.
Bhattacharya, Ujjwal
Shaw, Bikash
ICIT 2006: 9TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY, PROCEEDINGS, 2006, : 105 - 110
[36] Recognition of handwritten Bangla numerals based on structural approach
Chen, Hong-Liang
Yang, Zhong-Gen
PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, : 3345 - 3350
[37] A NEW HIERARCHICAL APPROACH FOR RECOGNITION OF UNCONSTRAINED HANDWRITTEN NUMERALS
WANG, GE
WANG, JF
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 1994, 40 (03) : 428 - 436
[38] Recognition of Assamese Handwritten Numerals Using Mathematical Morphology
Medhi, Kalyanbrat
Kalita, Sanjib Kr
SOUVENIR OF THE 2014 IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE (IACC), 2014, : 1076 - 1080
[39] An efficient fuzzy method for Bangla handwritten numerals recognition
Hoque, Mohammed Moshiul
Islam, Md. Mainul
Ali, Muhammad Masroor
ICECE 2006: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, 2006, : 197 - +
[40] Recognition of Handwritten Devanagari Numerals by Graph Representation and Lipschitz Embedding
Bhat, Mohammad Idrees
Sharada, B.
RECENT TRENDS IN IMAGE PROCESSING AND PATTERN RECOGNITION (RTIP2R 2016), 2017, 709 : 102 - 110

← 1 2 3 4 5 →