CLASSIFICATION OF DEFECTS ON PACKING CANS USING LACUNARITY AND NAÏVE BAYES METHODS

Abstract

Cans are steel sheets coated with tin (Sn) and used to package food and beverage products. The use of cans as packaging for food products because cans are difficult for microorganisms to pass and cannot be penetrated by ultraviolet light so that the quality of packaged food or beverage products is maintained. The cans selected as packaging must be in a non-defective condition so that an inspection process is needed on the cans. This research implements the Lacunarity and Naïve Bayes Classification methods to classify the types of cans which are grouped into 2 classes, namely Good and Reject. From the implementation of the Lacunarity method, it is able to produce 28 values of texture feature extraction that vary in each image. The results of the evaluation of the classification of the Naïve Bayes Classification method to classify the condition of packaged cans obtained an accuracy value of 0.87, a precision of 0.88, a recall of 0.86 and an f-measure of 0.87, so that the Naïve Bayes Classification method can classify the types of cans packaging in Good and Reject condition based on the value of texture extraction using the Lacunarity method.