An Approaching Machine Learning Model: Tile Inspection Case Study

Abstract

Clothing, food, and shelter are three basic types of needs in our lives. If one of the basic needs is not met then there can be an imbalance in our lives. One of the basic needs is to build a house. House needs a tile or roof to cover of a building that can protect all weather influences. One company in Majalengka only uses fleeting vision in inspection process. This can result in a decrease in work productivity. This paper proposed an approach machine learning model for classification of defects was carried out in the inspection process. Feature extraction was performed using the Local Binary Pattern (LBP) method to obtain training features. The next stage is training (training) to the characteristics of training that has been obtained. Furthermore, the database obtained from the training results will be used to classify tile image test data using the Support Vector Machine (SVM) method. From the test results, the system is made capable of classifying defects of a maximum accuracy value of 63.21%. The results obtained are the best accuracy value generated is 76.67% with LBP parameters used are 256 × 256 cell size and radius 2. While for SVM parameters use Polynomial kernel type or RBF with OAA multiclass