Greedy partitioning based tree structured multiclass SVM for Odia OCR

Abstract

There have been many proposals to extend the basic two-class SVM classifier for multiclass classification and it is established that among these extensions binary-structured hierarchical SVMs is the most efficient computationally. However, determining an effective binary structure by recursively dividing the classes is a major research issue. We describe a new classifier, GP-SVM, based on greedy partitioning of classes and demonstrate that GP-SVM gives better classification accuracy than all major combinational techniques besides having the computational advantages. The advantages of GP-SVM is better realized when the number of classes is large. We demonstrate this advantage in recognition of printed Odia character. We built a corpus of 10025 tagged Odia aksharas collected over multiple printed documents of different fonts. We used a very modest number of features. GP-SVM with 133 classes yielded 95% accuracy of recognition. During the learning process of GP-SVM, the proposed system could learn the taxonomy of character-shapes of Odia script.

Hidden Markov Model Based Odia Numeral Recognition Using Moment and Structural Features

“…The author purposed a method to recognize Odia script using SVM and KNN classifier by taking nearby paired example, focus symmetric neighborhood parallel example, directional neighborhood outrageous example and using LBP feature with SVM classifier the performance of Odia script identification was found to be 84% [10]. Author developed a model for Odia script by using support vector machine and greedy partitioning by taking the directional feature such as meshing, horizontal, vertical, right, left and found the accuracy up to 95% [11]. Offline Odia character can be recognized using segmentation, neural network and back propagation by taking the statistical and geometrical, Structural features, hybrid feature and found the result up to 97.87% [12].…”