Comparison of Machine Learning Approach for Waste Bottle Classification

The use of machine learning for the image classification process is growing all time. Many methods can be used to classify an with good accuracy. Convolutional Neural Network (CNN) and Support Vector Machine (SVM) are popular this case. two approaches have differences in data training achieve objectives. Although there some between these approaches, advantages both them. This research explores comparison CNN SVM by comparing carried out accuracy results classification. stages divided into pre-processing, training, testing. objects ten waste plastic bottles different brands medium size a total 1100 images. Based on observations, disadvantages process. However, from results, CNN's better than SVM. networks 99% 74% SVM, respectively. So, experiments that been study, it was found still Doi: 10.28991/ESJ-2022-06-05-011 Full Text: PDF