Hass avocado ripeness classification by mobile devices using digital image processing and ANN methods

Abstract

Proper farming, transportation, and storage processes of Hass avocado are important owing to its recent increase in production, export, and economic activity in Colombia. Since Hass avocado pricing and utility depend on its consumption ripeness, related to changes in skin color, sensory properties, texture, and nutritional value, developing an Android mobile application, namely iHass for smartphones and tablets, which estimates the number of days in which the Hass avocado reaches its optimal ripening level during post-harvest storage, contributes toward improving the fruit quality and decreasing the export costs and losses. This study aims to monitor the ripening processes of Hass avocados in complex backgrounds and indoor environments using various digital image processing techniques. The proposed study uses the red, green, and blue color model based on the physical and chemical changes that are observed during the ripening process. Herein, the color, shape, and texture characteristics of the fruits are obtained, and the fruits are classified using an artificial neural network, which features three layers, four input parameters, six hidden neurons, and four output parameters. Furthermore, ripeness was monitored in two crops, which provided 65 samples each. The results provided a ripeness estimate accuracy of 88% and a regression value of 0.819 during the post-harvest period.

Flexible Dual-Mechanism Pressure Sensor Based on Ag Nanowire Electrodes for Nondestructive Grading and Quality Monitoring of Fruits

“…The accuracies of avocado grading for the four ripening stages are 87.5%, 95%, 90%, and 92.5%, respectively, which may be due to the irregularity of the avocado shape and the instability of the manipulator control system. In addition, we have added in Figure S13b a comparison with other literature studies on fruit ripeness grading accuracy, and the performance of this flexible DMPS enabled intelligent manipulator system is comparable to machine learning and machine vision grading methods. − Optical technology has the advantages of non-destructiveness and in-depth research, but the variability of fruit surface characteristics and the influence of environmental factors pose reliability problems. Also, there is still a lack of quantitative analysis of the external characteristics of fruits .…”

Advancement in artificial intelligence for on-farm fruit sorting and transportation

“…Multiple sensors have been used for image acquisition in on-farm sorting and transportation, including a red-green-blue (RGB) camera, a charge-coupled device (CCD) camera, a hyperspectral camera, a near-infrared (NIR) sensor, visible and near-infrared spectroscopy, and a thermal camera. According to previous studies, the RGB camera is currently the most widely employed for on-farm sorting, especially for surface damage detection, color grading, mass and volume estimation of apples, and ripeness of avocados ( Jaramillo-Acevedo et al., 2020 ; Lu et al., 2022 ; Mansuri et al., 2022 ). A CCD camera was utilized for the size and color grading of apples and mass grading of mangoes ( Momin et al., 2017 ; Zhang et al., 2021 ).…”

“…Spectroscopy techniques such as hyperspectral spectroscopy and visible and near-infrared spectroscopy, which include large amounts of data, have been used for the chemical detection of various fruits due to their sensitivity to nutritional and constituent content that can be detected by external inspection ( Ben-Zvi et al., 2017 ; Jaramillo-Acevedo et al., 2020 ; Çetin et al., 2022 ). ANN models, which are robust for pattern recognition in a large amount of data, are used for hyperspectral imaging analysis in chemical detection, such as total soluble solids content, mineral nutrient content, and dry matter content for mangoes, bananas, blueberries, etc.…”

Application of Machine Learning Techniques for Okra Shelf Life Prediction

“…Jaramillo-Acevedo, Choque-Valderrama, Guerrero-Álvarez and Meneses-Escobar [21], leveraged on the RGB color model which is based on the physical and chemical changes during the ripening process. Hence, classified the consumption maturity for Hass avocado fruits using an artificial neural network.…”