Academic Journal of Nawroz University (AJNU), Vol.13, No.1, 2024 This is an open access article distributed under the Creative Commons Attribution License Copyright ©2017. e-ISSN: 2520-789X https://doi.org/10.25007/ajnu.v13n1a1514 92 A Recognition and Classification of Fruit Images Using Texture Feature Extraction and Machine Learning Algorithms Nohadra Behnam Israel 1 , Adnan Ismail Al-Sulaifanie 2 and Ahmed Khorsheed Al-Sulaifanie 2 1 Energy Engineering Department, Technical College of Engineering, Duhok Polytechnic University, Duhok, Kurdistan Region-Iraq. 2 Electrical & Computer Engineering Department, College of Engineering, University of Duhok, Duhok, Kurdistan Region-Iraq. ABSTRACT: Fruits classification is demanded in some fields, such as industrial agriculture. Automatic fruit classification from their digital image plays a vital role in those fields. The classification encounters several challenges due to capturing fruits’ images from different viewing angle, rotation, and illumination pose. In this paper a framework for recognition and classification of fruits from their images have been proposed depending on texture features, the proposed system rely on three phases; firstly, pre-processing, as images need to be resized, filtered, color convert, and threshold in order to create a fruit mask which is used for fruit’s region of interest segmentation; followed by two methods for texture features extraction, first method utilize Local Binary Pattern (LBP), while the second method uses Principal Component Analysis (PCA) to generate features vector for each fruit image. Classification is the last phase; two supervised machine learning algorithms; K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) are utilized to identity and recognize the fruits images classes. Both methods are tested using 1200 fruits images, from 12 classes acquired from Fruits-360 database. The results show that combining LBP with K-NN, and SVM yields the best accuracy up to 100% and 89.44% respectively, while the accuracy of applying PCA with K-NN and SVM reached to 86.38 % and 85.83% respectively. Keywords: Pattern Recognition, Fruits Classification, LBP, PCA, K-NN, SVM 1. Introduction In recent years, the improvement in the cameras and sensors fields had led to an increase in intelligent systems, an essential purpose of those systems is to understand and perceive an image as done by human brain (Bhargava & Bansal, 2021). The usage of image processing has been wide increasingly in agricultural field to automate its processes; automation system can be implemented in crop ripeness monitoring, crop disease detection, fruits and vegetables recognition (Al-falluji, 2016). The automatic fruit’s image classification has attract wide attention by researchers worldwide cause its offers numerous solutions such as reducing manual effort to a large extent as well as time evolvement (Gill & Khehra, 2021). Fruits recognition systems can be utilized in many real-life implementations, such in store checkout, where it may be utilize rather than manual scanner tags; moreover, for helping eye weakness people as a supportive appliances, an educational tool for small children and Down syndrome patients. Recognizing several fruits species is a repeated chore in supermarkets, where the cashier has to define each item type that will determine its cost, a fruit recognition system, which automates labeling and computing the price, is the right solution for this problem, furthermore, fruit recognition system could be utilized as a mobile application that can help the user to identify nutrition and dietary information (Behera, Rath, Mahapatra, & Sethy, 2020). Fruits image visual characteristics like color, shape, size and texture are usually used for assisting the identification process (Jana & Parekh, 2017; Nosseir & Ahmed, 2018; Saranya, Srinivasan, Pravin Kumar, Rukkumani, & Ramya, 2019; Shukla & Desai, 2016), yet there are major challenges for an accurate imagining system; such as viewpoint variation, illumination pose, inter-class similarities and intra-class diversities. Texture considers an effective characteristic that analysis image surface, every fruit image owns unique and different texture when it compares to others (Indriani, Kusuma, Sari, & Rachmawanto, 2017), additionally texture- based approach has translation, rotation, shape and color dependency. In this paper a framework for fruits recognition and classification system has been proposed, based on texture feature, machine learning algorithms are utilized to recognize and classify the extracted features. The aim of this study is to investigate the influence of two methods in texture feature extraction and compare their accuracies. As