Digital Measurement of Maturity Indices of Mangoes using Selected Image Features

Abstract

Maturity is the most important factor to determine the storage-life and quality of fruits like mangoes. Fruit maturity can be recognized by different attributes and among them skin color is the most significant criteria for judging maturity. Typically, human experts visually detect the fruit color to identify the maturity stages which is very prone to error. In this paper, a method of digital image processing has been proposed to classify mangoes into six maturity stages according to the United States department of agriculture (USDA) standard classification. The experimentation considers sample images of more than 100 mangoes of different stages. A total of 24 image features are extracted and then correlation based and information gain based evaluation has been performed in order to select the most informative feature sets. Categorization is done using the decision tree which provides up to 96% classification accuracy. Several computer vision based methods have been developed to determine the state of the maturity of different fruits. A spectral analysis of bananas obtained under white and ultra-violet has been performed [3]. A Computer Vision System to estimate the antioxidant and phenol content on carrots based on the fruit's surface color was accomplished [4]. An index of the tomatoes ripeness is proposed, which allows classifying the fresh fruit into 6 classes, according to the USDA international standard [5]. A Computer Vision System to discriminate varieties of French olives is developed where Pit images (frontal and profile) were used and characteristics such as the histograms of the RGB model and form descriptors (area, perimeter, length, width, etc.) were computed [6]. Liming and Yanchao [7] developed an automated strawberry grading system using image processing technique and graded the strawberry adopting one or two or three indices among shape, color and size. Digital Measurement of Maturity Indices of Mangoes Using Selected Image FeaturesA method to classify mango fruits into their maturity stages was developed using the fuzzy logic and RGB color sensor model. The advantage of fuzzy approaches is, approximate inference can be performed by fuzzy IF-THEN [8]. Another method to categorize mangoes according to their maturity indices was proposed using their color and size features and histogram analysis. The advantage of histogram analysis is low computational complexity [9].As it was seen, a large number of works to estimate the maturity

Flutter-Based Real-Time Mobile App for Fruit Shelf-Life Prediction (FSP) Using Multi-Modality Imaging

“…An ordinary work in image processing is recognizing the same kinds of items using machine learning techniques for classifying and clustering the fruits (Bhole et al, 2020b). Previously, a thermal imaging idea in Naik and Patel (2017), machine learning with a color feature extraction model (Bhole et al, 2020a) and deep neural network (Bhole et al, 2020c) have been suggested and manifested for evaluation of quality and categorizing maturity of the mango (Behera et al, 2020;Sahu and Potdar, 2017;Sultana et al, 2017;Bhole and Kumar, 2020d). Numerous techniques have been employed for identifying the quality of fruits with maturity levels through RGB imaging, either under-controlled or real situations (Behera et al, 2020;Sahu and Potdar, 2017;Sultana et al, 2017;Intaravanne et al, 2012).…”

“…Previously, a thermal imaging idea in Naik and Patel (2017), machine learning with a color feature extraction model (Bhole et al, 2020a) and deep neural network (Bhole et al, 2020c) have been suggested and manifested for evaluation of quality and categorizing maturity of the mango (Behera et al, 2020;Sahu and Potdar, 2017;Sultana et al, 2017;Bhole and Kumar, 2020d). Numerous techniques have been employed for identifying the quality of fruits with maturity levels through RGB imaging, either under-controlled or real situations (Behera et al, 2020;Sahu and Potdar, 2017;Sultana et al, 2017;Intaravanne et al, 2012). Particularly, these non-destructive methods have been dependent on the examination of visible and spectral imaging using pattern analysis.…”