Automatic surface defects classification of Kinnow mandarins using combination of multi‐feature fusion techniques

Abstract

AbstractAnalyzing the quality of biological products is a difficult task, as their physicochemical properties such as size, shape, color, and texture change over time. Among many quality attributes, automatic classification of defects is a challenging work due to similarity or diversity of defects in terms of shape, color, and texture within intra and inter cultivars. In this work, an image analysis and machine learning‐based method to identify and classify four defects of Kinnow mandarins is proposed. A simple and fast adaptive thresholding technique was used to segment the defects. Defects discriminatory abilities of three prevalent texture descriptors namely local binary patterns, gray level co‐occurrence matrix (GLCM), and gray level run length matrix (GLRLM) were explored. In order to measure the effectiveness of color models in food analysis techniques, texture features were extracted on individual and combined color channels of three popular color models, that is, RGB, HSV, and CIELAB. Two machine‐learning techniques: random forest (RF) and artificial neural networks (ANNs) classifiers were trained with extracted features to predict the defects. The highest accuracies of 93.5 and 89.3% and average accuracies of 88.95 and 80.67% were achieved by ANN and RF classifiers, respectively, for the feature set {GLCM, GLRLM} on {H,S,V} color set.Practical applicationsKinnow mandarins' cultivation area occupies around 50% of the total citrus farming regions in India. Currently, the expert laborers manually carry out the grading of Kinnow fruits based on the existence of external defects. This process is labor‐intensive, inefficient, and time‐consuming. However, now this labor‐intensive task can be replaced with automatic fruit classification machines based on computer vision (CV) and machine learning (ML) technologies. Presently, there is a scarcity of studies as well as algorithms to automate the process of Kinnow fruit defects classification. The developed CV‐ and ML‐based algorithm is capable to identify and discriminate four types of external defects pertaining to Kinnow mandarins. The classification accuracy and other performance measures achieved on the developed algorithm make it ideal for real‐time online Kinnow defects classification systems.