Triangle Geometry Method Based Dominant Distribution Foreground for Digit Recognition

Abstract

Digit recognition has been studied for four decades ago. Many approaches and techniques such as Hidden Markov Model, Neural Network, back-propagation and k-nearest neighbor have been applied to recognize the digit images. Recently, the triangle geometry method has been applied to extract features from triangle properties such as ratio, angle and gradient. However, a problem in determining points of a triangle was triggered due to the points’ position in straight line. Thus, a method of extracting triangle features using triangle geometry based on the dominant of distribution foreground for digit recognition has been proposed. The dominant of distribution foreground is referred to the digit of ‘0’ which is represented as a foreground image during the binarization process. The process to determine the triangle points are based on the dominant of distribution foreground. The classifiers of Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) are used to measure the classification accuracies for four types of digit datasets which are HODA, IFCHDB, MNIST, and BANGLA. The comparison results classification of accuracies demonstrated the effectiveness of our proposed method.