Product Based Classification of Bulk Food Grains using Bag of Visual Words and Deep Features

Ali, Abdelmgeid; Mohammed, Usama Sayed; Nour, Rehab Ragaa

doi:10.21608/kjis.2021.198376

Product Based Classification of Bulk Food Grains using Bag of Visual Words and Deep Features

Document Type : Original Article

Authors

¹ Computer Science Department, Faculty of Science, Minia University, Al Minia 61519, Egypt

² Electrical Engineering Department, Faculty of Engineering, Assiut University, Assiut 71516, Egypt

10.21608/kjis.2021.198376

Abstract

The goal of this research is to compare between the performance of the traditional machine learning classification algorithm using Bag of Visual Words (BoVW) method and off-the-shelf deep features extracted by VGG-19, and Inception-V3 models and trained SVMs using the extracted features. By comparing the AUC, sensitivity, and specificity of SVM with VGG-19 and Inception-V3, we can conclude that off-the-shelf deep features has an important impact on food grains image classification.

Keywords