The Identification of Beef and Pork Using Neural Network Based on Texture Features

Abstract

The actual problem that frequently happens related to meat sales at conventional markets is the manipulation of pork and beef. It can happen as both visual textures bear resemblances. Texture is a crucial part of an object. In image processing, textures can be used for classification, recognition or prediction of an image. The author offers the method Minimum Overlap Probability - Neural Network (MOP-NN) for the identification of pork and beef based digital image features. Minimum Overlap Probability was employed to select features of the strongest characteristics, whilst Neural Network is used for training and classification. Based on the test results, the strongest features are maximum probability, contrast, sum average, autocorrelation, and energy and entropy sum. Based on MOP-NN Model test result, the digital image identification of beef and pork has performance with an accuracy of 96% on 400 images of sample data.