文章基本信息

标题：RECOGNITION OF CUNEIFORM SYMBOLS USING NEURAL NETWORK
本地全文：下载
作者：NADA A. RASHEED ; WESSAM LAHMOD NADOS
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：17
出版社：Journal of Theoretical and Applied
摘要：Recognition is regarded as a basic human attribute. In pattern recognition, there are many practical applications such as: handwriting, fingerprints, face recognition and many others. The purpose of the current work is to propose a method is able to recognize cuneiform symbols through the use of neural network. In order to achieve this objective, the image is loaded into the memory and the preprocessing can be done with introduce some modifications. Then, the attributes are extracted by finding the frequency of the on-pixels in the (50� 50) image matrix on the horizontal lines, vertical lines, the upper triangle of the main diagonal, and the lower triangle of the main diagonal. Finally, Backpropagation Algorithm was used in recognition with (20) hidden nodes and at the learning rate (0.05), within a short training time.
关键词：Cuneiform; Symbols; Numerals; Recognition; Backpropagation