Open AccessLearning Vector Quantization 3 (LVQ3) and Spatial Fuzzy C-Means (SFCM) for Beef and Pork Image Classification
Author(s) -
Jasril Jasril,
Suwanto Sanjaya
Publication year - 2018
Publication title -
indonesian journal of artificial intelligence and data mining
Language(s) - English
Resource type - Journals
eISSN - 2614-6150
pISSN - 2614-3372
DOI - 10.24014/ijaidm.v1i2.5024
Subject(s) - pattern recognition (psychology) , artificial intelligence , segmentation , vector quantization , image segmentation , mathematics , computer science
Base on some cases in Indonesia, meat sellers often mix beef and pork. Indonesia is a predominantly Muslim country. Pork is forbidden in Islam. In this research, the classification of beef and pork image was performed. Spatial Fuzzy C-Means is used for image segmentation. GLCM and HSV are used as a feature of segmentation results. LVQ3 is used as a method of classification. LVQ3 parameters tested were the variety of learning rate values and window values. The learning rate values used is 0.0001; 0.01; 0.1; 0.4; 0.7; 0.9 and the window values used is 0.0001; 0.4; 0.7. The training data used is 90% of the total data, and the testing data used is 10%. Maximum epoch used is 1000 iterations. Based on the test results, the highest accuracy was 91.67%.