Comparative Analysis of Efficient Image Segmentation Technique for Text Recognition and Human Skin Recognition

Abstract

Computer Vision and Pattern Recognition is one of the most interesting research subject on computer science, especially in case of reading or recognition of objects in real-time from the camera device. Object detection has wide range of segments, in this study we will try to find where the better methodologies for detecting a text and human skin. This study aims to develop a computer vision technology that will be used to help people with disabilities, especially illiterate (tuna aksara) and deaf (penyandang tuli) to recognize and learn the letters of the alphabet (A-Z). Based on our research, it is found that the best method and technique used for text recognition is Convolutional Neural Network with achievement accuracy reaches 93%, the next best achievement obtained OCR method, which reached 98% on the reading plate number. And also OCR method are 88% with stable image reading and good lighting conditions as well as the standard font type of a book. Mean while, best method and technique to detect human skin is by using Skin Color Segmentation: CIELab color space with accuracy of 96.87%. While the algorithm for classification using Convolutional Neural Network (CNN), the accuracy rate of 98%.