Design And Implementation Of Gabor Filter Based Offline YorÙbÁ Handwritten Recognition System.

Arabic Handwritten Script Recognition System Based on HOG and Gabor Features
The  proposed system is working better than any other current approaches as it produces superior outcomes. RBF kernel SVM exploiting HOG method is totally a promising classification method in the handwriting recognition area. As perspective, we have to combine HOG and gabor features with a further feature vectors in order to increase the recognition rate.
Jumoke F. Ajao, Stephen O.Olabiyisi, Elijah O.Omidiora and Odetunji O. Odejobi (2015)
Yoruba Handwriting Word Recognition Quality Evaluation of Preprocessing Attributes using Information Theory.
In the present work, a novel method is devised to adapt the information theory and related techniques in the development of a robust and accurate Yoruba word recognition system.
From experiment, it was observed that, the entropy measure of the handwritten decreases at each level of pre-processing which is tending towards the entropy measure of typewritten word.  
The result implies that preprocessing stage to be deployed should be able to achieve an entropy measure closer to the entropy measure of the original Information.
J.Pradeep, E.Srinivasan and S.Himavathi (2011)
DIAGONAL BASED FEATURE EXTRACTION FOR HANDWRITTEN ALPHABETS RECOGNITION SYSTEM USING NEURAL NETWORK
A simple off-line handwritten English alphabet characters recognition system using a new type of feature extraction, namely, diagonal feature extraction is proposed. Two approaches using 54 features and 69 features are chosen to build the Neural Network recognition system. Experimental results reveals that 69 features gives better recognition accuracy than 54 features for all the types of feature extraction. From the test results it is identified that the diagonal method of feature extraction yields the highest recognition accuracy of 97.8 % for 54 features and 98.5% for 69 features
Jin Chen, Huaigu Cao, Rohit Prasad, Anurag Bhardwaj and Prem Natarajan (2010)
Gabor Features for Offline Arabic Handwriting Recognition
Observed that many features prevalent in the field of Arabic handwriting recognition are extracted from binary images, we constructed a set of Gabor filters that operate directly on gray-level images and then extract features from the filtering response. Using an SVM classifier with the RBF kernel, we found that the proposed Gabor features outperformed the GSC features and graph-based features. More interestingly, the combination of Gabor and GSC features resulted in a significant performance improvement over using any of these feature sets along.