Multiclass Apple Varieties Classification Using Machine Learning with Histogram of Oriented Gradient and Color Moments

It is critically necessary to maximize the efficiency of agricultural methods while concurrently reducing the cost of production. Varieties, types, and fruit classification grades are crucial to fruit production. High expenditure, inconsistent subjectivity, and tedious labor characterize traditional and manual varieties classification. This study developed machine learning (ML) models to classify ten apple varieties, extracting the histogram of oriented gradient (HOG) and color moments from RGB apple images. Support vector machine (SVM), random forest classifier (RFC), multilayer perceptron (MLP), and K-nearest neighbor (KNN) classification models were trained with 10-fold stratified cross-validation (Skfold) by using the textural and color features, and a GridSearch was implemented to fine-tune the hyperparameters. The trained models, SVM, RFC, MLP, and KNN were tested with separate test data and performed well, having an accuracy of 98.17%, 96.67%, 98.62%, and 91.28%, respectively. Having the top results, the MLP and SVM models demonstrated the potential of applying HOG and color moments to train ML models for classifying apple varieties. This study suggests conducting further research to thoroughly examine additional image features and determine the impact of combining features and utilizing different classifiers.

[1]  Ercan Karaköse,et al.  Classification of apple images using support vector machines and deep residual networks , 2023, Neural Computing and Applications.

[2]  Zilong Zhuang,et al.  Color Classification and Texture Recognition System of Solid Wood Panels , 2021 .

[3]  Francesco Girardi,et al.  Fruit Development and Primary Metabolism in Apple , 2021, Agronomy.

[4]  Gniewko Niedbała,et al.  Artificial Neural Networks in Agriculture , 2021, Agriculture.

[5]  A. Bansal,et al.  Classification and Grading of Multiple Varieties of Apple Fruit , 2021, Food Analytical Methods.

[6]  Yuping Huang,et al.  Identification of Apple Varieties Using a Multichannel Hyperspectral Imaging System , 2020, Sensors.

[7]  Shaker K. Ali,et al.  Feature Extraction Methods: A Review , 2020, Journal of Physics: Conference Series.

[8]  D. Chicco,et al.  The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation , 2020, BMC Genomics.

[9]  D. Bochtis,et al.  Agricultural Sustainability: A Review of Concepts and Methods , 2019, Sustainability.

[10]  D. Sharmila,et al.  Performance analysis of soft computing techniques for the automatic classification of fruits dataset , 2019, Soft Comput..

[11]  Ann Nosseir,et al.  Automatic Classification for Fruits' Types and Identification of Rotten Ones Using k-NN and SVM , 2019, Int. J. Online Biomed. Eng..

[12]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[13]  Zaliman Sauli,et al.  Fruit Recognition Using Surface and Geometric Information , 2018 .

[14]  Hong Liang,et al.  Text feature extraction based on deep learning: a review , 2017, EURASIP J. Wirel. Commun. Netw..

[15]  Kadir Sabanci,et al.  Different Apple Varieties Classification Using kNN and MLP Algorithms , 2016 .

[16]  Bayram Cetisli,et al.  Design of an automatic apple sorting system using machine vision , 2016, Comput. Electron. Agric..

[17]  Evans Miriti,et al.  Classification of selected apple fruit varieties using naive bayes , 2016 .

[18]  J. Wolf,et al.  Towards sustainable intensification of apple production in China—Yield gaps and nutrient use efficiency in apple farming systems , 2016 .

[19]  Ashutosh Kumar Bhatt,et al.  Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation , 2015, AI & SOCIETY.

[20]  Xuesen Chen,et al.  Genetic diversity of volatile components in Xinjiang Wild Apple (Malus sieversii). , 2007, Journal of genetics and genomics = Yi chuan xue bao.

[21]  Tony R. Martinez,et al.  Distribution-balanced stratified cross-validation for accuracy estimation , 2000, J. Exp. Theor. Artif. Intell..

[22]  Javaid Iqbal,et al.  Analysis of visual features and classifiers for Fruit classification problem , 2021, Comput. Electron. Agric..

[23]  Zhe Chen,et al.  A Shallow Convolutional Neural Network for Apple Classification , 2020, IEEE Access.

[24]  Martín Carpio,et al.  A Comparison of Image Texture Descriptors for Pattern Classification , 2018, Fuzzy Logic Augmentation of Neural and Optimization Algorithms.

[25]  Danilo Medeiros Eler,et al.  Handwritten feature descriptor methods applied to fruit classification , 2018 .

[26]  D. Veringă,et al.  Determination of the relaxation time at static compression of Idared apples variety. , 2015 .

[27]  D. Veringă,et al.  Determination of the relaxation period at static compression of Golden Delicious apples variety. , 2015 .

[28]  R. Ciuperca,et al.  Researches regarding apples sorting process by their size. , 2014 .

[29]  S. Kodituwakku Comparison of Color Features for Image Retrieval , 2010 .

[30]  L. Breiman Random Forests , 2001, Machine Learning.