“…Although many efficient methods of character recognition are proposed but many problems still remain to be solved. From the study, we found that the previous recognition system [1] cannot support various styles of writing of Thai handwritten character. To improve the system, we propose neural network technique hybrid to the heuristic rules to handle various style of writing and to further improving the accuracy of our recognition system emphasize on some problematic feature such as zigzag feature.…”
Section: Introductionmentioning
confidence: 93%
“…Our research emphasizes on improving the efficiency of the existing system developed by Mitrpanont and Kiwprasopask [1]. Two fundamental concepts are used for developing the feature extraction and recognition process, i.e., Thai Character Feature Space and Thai Character Solution Space.…”
Section: A Overview Of the Previous Thw-cr System [1jmentioning
confidence: 99%
“…For example, normally character '11' as defined in Thai Solution Space of [1], there are only 2 legs at the lower part of the character. However, in some situations, the current extraction process returns 3 lower legs and an end-point (EP) feature is mapped to the [lower-right] position of the standard 5 x 3 matrix.…”
Section: B Conflict Oj Extracted Features Problemmentioning
confidence: 99%
“…The diagram in Figure 5 shows the overall proposed functions of our system. The left side shows existing functions of THW-CR system [1] consisting of four significant processes including preprocessing, feature extraction, recognition and post-processing. All new functions …”
Section: B Neural Network-based Recognition Enhan Cem En Tmentioning
confidence: 99%
“…To improve THW-CR System [1], we first investigated and found a problem of conflict features. For example, normally character '11' as defined in Thai Solution Space of [1], there are only 2 legs at the lower part of the character.…”
Section: B Conflict Oj Extracted Features Problemmentioning
This research enhanced two major processes of the previous work of the off-line Thai handwritten character recognition using hybrid techniques of heuristic rules and neural network system. The proposed functions are mainly in 1) Feature extraction enhancement to improve the feature conflict resolution rule and the specialized neural network-based zigzag feature extraction. These functions are used to refine the conflict features and zigzag patterns; 2) Neural network-based recognition. Specifically, a neural network technique improves the capabilities of the recognition process to handle various styles of writing. The result showed that the additional feature conflict resolution rule could achieve the feature extraction rate of 87.85% (increased 2.13%), the feature extraction rate of the specialized neural network-based zigzag extraction could achieve 90.48% (increased 47.9%) and the recognition rate of the neural network-based recognition which combine both of the two proposed feature extraction functions could achieve 92.78% (increased 9.77%).
“…Although many efficient methods of character recognition are proposed but many problems still remain to be solved. From the study, we found that the previous recognition system [1] cannot support various styles of writing of Thai handwritten character. To improve the system, we propose neural network technique hybrid to the heuristic rules to handle various style of writing and to further improving the accuracy of our recognition system emphasize on some problematic feature such as zigzag feature.…”
Section: Introductionmentioning
confidence: 93%
“…Our research emphasizes on improving the efficiency of the existing system developed by Mitrpanont and Kiwprasopask [1]. Two fundamental concepts are used for developing the feature extraction and recognition process, i.e., Thai Character Feature Space and Thai Character Solution Space.…”
Section: A Overview Of the Previous Thw-cr System [1jmentioning
confidence: 99%
“…For example, normally character '11' as defined in Thai Solution Space of [1], there are only 2 legs at the lower part of the character. However, in some situations, the current extraction process returns 3 lower legs and an end-point (EP) feature is mapped to the [lower-right] position of the standard 5 x 3 matrix.…”
Section: B Conflict Oj Extracted Features Problemmentioning
confidence: 99%
“…The diagram in Figure 5 shows the overall proposed functions of our system. The left side shows existing functions of THW-CR system [1] consisting of four significant processes including preprocessing, feature extraction, recognition and post-processing. All new functions …”
Section: B Neural Network-based Recognition Enhan Cem En Tmentioning
confidence: 99%
“…To improve THW-CR System [1], we first investigated and found a problem of conflict features. For example, normally character '11' as defined in Thai Solution Space of [1], there are only 2 legs at the lower part of the character.…”
Section: B Conflict Oj Extracted Features Problemmentioning
This research enhanced two major processes of the previous work of the off-line Thai handwritten character recognition using hybrid techniques of heuristic rules and neural network system. The proposed functions are mainly in 1) Feature extraction enhancement to improve the feature conflict resolution rule and the specialized neural network-based zigzag feature extraction. These functions are used to refine the conflict features and zigzag patterns; 2) Neural network-based recognition. Specifically, a neural network technique improves the capabilities of the recognition process to handle various styles of writing. The result showed that the additional feature conflict resolution rule could achieve the feature extraction rate of 87.85% (increased 2.13%), the feature extraction rate of the specialized neural network-based zigzag extraction could achieve 90.48% (increased 47.9%) and the recognition rate of the neural network-based recognition which combine both of the two proposed feature extraction functions could achieve 92.78% (increased 9.77%).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.