Automatic fruit classification using random forest algorithm

Abstract

The aim of this paper is to develop an effective classification approach based on Random Forest (RF) algorithm. Three fruits; i.e., apples, Strawberry, and oranges were analysed and several features were extracted based on the fruits' shape, colour characteristics as well as Scale Invariant Feature Transform (SIFT). A preprocessing stages using image processing to prepare the fruit images dataset to reduce their color index is presented. The fruit image features is then extracted. Finally, the fruit classification process is adopted using random forests (RF), which is a recently developed machine learning algorithm. A regular digital camera was used to acquire the images, and all manipulations were performed in a MATLAB environment. Experiments were tested and evaluated using a series of experiments with 178 fruit images. It shows that Random Forest (RF) based algorithm provides better accuracy compared to the other well know machine learning techniques such as K-Nearest Neighborhood (K-NN) and Support Vector Machine (SVM) algorithms. Moreover, the system is capable of automatically recognize the fruit name with a high degree of accuracy.

A study on classification of fruit type and fruit disease

“…Zawbaa [13] proposed random forests (RF) as classifier. Firstly, this paper used color, shape features and SIFT methods to extract a number of features from a 90x90 pixel fruit image.…”

Summary on fruit identification methods: A literature review

“…[26] applied SIFT to extract features according to the fruits' appearance and using Random Forest (RF) as the classifier to determine the classes of fruits. The author compares RF with the following classifiers: (i) KNN; (ii) SVM.…”

“…89.1% SESH + RF [25] The computational complexity is high. 99.36% SIFT + RF [26] The datasets are unbalanced in fruit category. 96.97% CH + Unser's texture measure + morophology + BBO-FNN [27] The performance of feature extraction is lower than other methods.…”

Fruit Disease Categorization based on Color, Texture and Shape Features

“…Therefore, the first feature extraction method uses color and shape characteristics to generate the feature vector for each fruit image in the dataset. The used color moments to describe the images are color variance, color mean, color kurtosis, and color skewness [20], [21]. The shape features is described using Eccentricity, Centroid, and Euler Number features [22].…”