Using texture feature in fruit classification

Abstract EN

Recent advances in computer vision have allowed wide-rangingapplications in every area of life.

One such area of application is theclassification of fresh products, but the classification of fruits andvegetables has proven to be a complex problem and needs furtherdevelopment.

In recent years, various machine learning techniques havebeen exploited with many methods of describing the different features offruit and vegetable classification in many real-life applications.

Classification of fruits and vegetables presents significant challenges dueto similarities between layers and irregular characteristics within theclass.

Hence, in this work, three feature extractor/ descriptor which arelocal binary pattern (LBP), gray level co-occurrence matrix (GLCM) and, histogram of oriented gradient(HoG) has been proposed to extract fruitefeatures, the extracted features have been saved in three feature vectors, then desicion tree classifier has been proposed to classify the fruit types.

fruits 360 datasets is used in this work, where 70% of the dataset wereused in the training phase while 30% of it used in the testing phase.

Thethree proposed feature extruction methods plus the tree classifier havebeen used to classifying fruits 360 images, results show that the the threefeature extraction methods give a promising results, while the HoGmethod yielded a poerfull results in which the accuracy obtained is 96%