AN IMPROVED SVM AND CONVOLUTIONAL NEURAL NETWORK-BASED GARBAGE CLASSIFICATION SYSTEM (GCLS) AUGMENTED WITH TRANSFER LEARNING AND OBJECT DETECTION API

Abstract

Garbage is a waste substance that is abandoned by people, generally owing to a perceived lack of utility. We are confronted with the massive amount of garbage generated by people every day that should be properly recycled, reused and repaired by the garbage management system. The first step after garbage collection is to separate or classify garbage into different categories such as glass, paper, plastic, etc. in order to reuse, recycle, repair and recover it. The existing classifiers can only classify garbage in three or six categories. We have designed and implemented a Garbage Classification and Labeling System (GCLS) using SVM and Convolutional Neural Network(CNN) that segregates garbage in eight classes and also label the objects in the image namely cardboard, leather, glass, metal, plastic, paper, rubber and trash. Using transfer learning we have achieved up to 90.4% accuracy that is higher than the existing classifiers.