Tifinagh Character Recognition using Harris Corner Detector and Graph Representation

Abstract

In this article, a printed Tifinagh character recognition system is presented. It is composed of three main steps: preprocessing, features extraction and classification. In the preprocessing step, binarization, normalization and thinning are applied to enhance the quality of the image. In the feature extraction step, corners are extracted using Harris Corner Detection method then represented by graph. In the classification step, graphs are compared using a graph matching method. Experimental results are obtained using IRCAM database to test the effectiveness. The system shows good results in terms of accuracy.

Characters recognition using keys points and convolutional neural network

“…To improve the efficiency of our method, we use a CNN white two convolution layers and 2 pooling layers, the training process is performed on a personal computer (PC) equipped with Intel UHD Graphics 620 and a processor i7 8th generation, the accuracy obtained of training and testing is showed in the Table 1. The old method that uses feature extraction in tifinagh character recognition have several problems specially with character in Figure 7 that have a similarity of 80% or more, and to resolve the problem we need an additional treatment such as our previous work [25] or the recognition rate will be inferior to 95%. In this paper this kind of problem was solved by adding key points.…”