Classification Of Pistachio Images With The ResNet Deep Learning Model

Abstract

Pistachio, which is grown in many parts of the world today, has an important place in the agricultural economy. In order to maintain this economic value, the post-harvest industrial classification process is very important to obtain efficiency from this harvest. In the process of separating pistachios, an efficient classification process is needed in order for different pistachio species to appeal to different markets. For this reason, the classification process of pistachios is very important. In this study, Kirmizi and Siirt pistachio classification with 2148 images was made using ResNet architecture. After the statistical experimental studies, the highest classification accuracy was obtained from fold-1 as 88.5781% and the Accuracy value was 0.86168 after the classification process.