Classification of Fruits Using Computer Vision and a Multiclass Support Vector Machine

Yudong Zhang,Lenan Wu

doi:10.3390/s120912489

Abstract

Automatic classification of fruits via computer vision is still a complicated task due to the various properties of numerous types of fruits. We propose a novel classification method based on a multi-class kernel support vector machine (kSVM) with the desirable goal of accurate and fast classification of fruits. First, fruit images were acquired by a digital camera, and then the background of each image was removed by a split-and-merge algorithm; Second, the color histogram, texture and shape features of each fruit image were extracted to compose a feature space; Third, principal component analysis (PCA) was used to reduce the dimensions of feature space; Finally, three kinds of multi-class SVMs were constructed, i.e., Winner-Takes-All SVM, Max-Wins-Voting SVM, and Directed Acyclic Graph SVM. Meanwhile, three kinds of kernels were chosen, i.e., linear kernel, Homogeneous Polynomial kernel, and Gaussian Radial Basis kernel; finally, the SVMs were trained using 5-fold stratified cross validation with the reduced feature vectors as input. The experimental results demonstrated that the Max-Wins-Voting SVM with Gaussian Radial Basis kernel achieves the best classification accuracy of 88.2%. For computation time, the Directed Acyclic Graph SVMs performs swiftest.

Highlights

Recognizing different kinds of vegetables and fruits is a difficult task in supermarkets, since the cashier must point out the categories of a particular fruit to determine its price
Gaussian Radial Basis kernel achieves the best classification accuracy of 88.2%
This work proposed a novel classification method based on multi-class kernel support vector machine (kSVM)

Summary

Introduction

Recognizing different kinds of vegetables and fruits is a difficult task in supermarkets, since the cashier must point out the categories of a particular fruit to determine its price. The use of barcodes has mostly ended this problem for packaged products but given that most consumers want to pick their products, they cannot be prepackaged, and must be weighed. A solution is issuing codes for every fruit, but the memorization is problematic leading to pricing errors. Another solution is to issue the cashier an inventory with pictures and codes, flipping over the booklet is time consuming [1]. Baltazar et al [4] first applied data fusion to nondestructive image of fresh intact tomatoes, followed by a three-class Bayesian classifier. Pholpho et al [6] used visible spectroscopy for classification of non-bruised and bruised longan fruits, and combined this with principal component analysis (PCA), Partial Least Square Discriminant Analysis (PLS-DA) and Soft Independent Modeling of Class Analogy (SIMCA) to develop classification models

Methods

Results

Conclusion