TY - GEN
T1 - Type-2 fuzzy Markov random fields to handwritten character recognition
AU - Zeng, Jia
AU - Liu, Zhi-Qiang
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2006
Y1 - 2006
N2 - This paper integrate s Markov random fields (MRFs) with type-2 fuzzy sets (T2 FSs) referred to as T2 FMRFs, which can handle the fuzziness of the labeling space as well as the randomness of observations within the unified framework. Because fuzzy and random uncertainties exist in many computer vision problems, we extend the maximum a posteriori (MAP) criterion for the best labeling configuration by T2 FSs operations. We apply T2 FMRFs as character models to similar handwritten Chinese character recognition on ETL-9B and KAIST databases. Experimental results show that T2 FMRFs have a better classification and generalization ability for similar patterns than classical MRFs. © 2006 IEEE.
AB - This paper integrate s Markov random fields (MRFs) with type-2 fuzzy sets (T2 FSs) referred to as T2 FMRFs, which can handle the fuzziness of the labeling space as well as the randomness of observations within the unified framework. Because fuzzy and random uncertainties exist in many computer vision problems, we extend the maximum a posteriori (MAP) criterion for the best labeling configuration by T2 FSs operations. We apply T2 FMRFs as character models to similar handwritten Chinese character recognition on ETL-9B and KAIST databases. Experimental results show that T2 FMRFs have a better classification and generalization ability for similar patterns than classical MRFs. © 2006 IEEE.
UR - https://www.scopus.com/pages/publications/34047224657
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-34047224657&origin=recordpage
U2 - 10.1109/ICPR.2006.1139
DO - 10.1109/ICPR.2006.1139
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 0769525210
SN - 9780769525211
VL - 1
T3 - Proceedings - International Conference on Pattern Recognition
SP - 1162
EP - 1165
BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006
T2 - 18th International Conference on Pattern Recognition, ICPR 2006
Y2 - 20 August 2006 through 24 August 2006
ER -