Design of an Optimum Computer Vision‐Based Automatic Abalone (Haliotis discus hannai) Grading Algorithm

Abstract

An automatic abalone grading algorithm that estimates abalone weights on the basis of computer vision using 2D images is developed and tested. The algorithm overcomes the problems experienced by conventional abalone grading methods that utilize manual sorting and mechanical automatic grading. To design an optimal algorithm, a regression formula and R(2) value were investigated by performing a regression analysis for each of total length, body width, thickness, view area, and actual volume against abalone weights. The R(2) value between the actual volume and abalone weight was 0.999, showing a relatively high correlation. As a result, to easily estimate the actual volumes of abalones based on computer vision, the volumes were calculated under the assumption that abalone shapes are half-oblate ellipsoids, and a regression formula was derived to estimate the volumes of abalones through linear regression analysis between the calculated and actual volumes. The final automatic abalone grading algorithm is designed using the abalone volume estimation regression formula derived from test results, and the actual volumes and abalone weights regression formula. In the range of abalones weighting from 16.51 to 128.01 g, the results of evaluation of the performance of algorithm via cross-validation indicate root mean square and worst-case prediction errors of are 2.8 and ±8 g, respectively.

Current applications and future trends of artificial senses in fish freshness determination: A review

“…The main tasks of computer vision can be classified as image acquisition, obtaining properties of the acquired images, such as corners, edges, regions of interest points, ridges, and color properties, and final decision‐making using different image processing techniques and algorithms as the recognition phase (Mery et al., 2010). Recently, the applications of computer vision in the food industry have grown because of its ability to localize raw materials and better characterize them before handling and further processing (Gonzalez Viejo et al., 2018; Lee et al., 2015; Zhu et al., 2021). Computer vision has great potential to perform such tasks by evaluating physical changes and image properties of both raw food materials and finished food products.…”

Automatic surface area and volume prediction on ellipsoidal ham using deep learning

“…From the computer vision perspective, aside from benefiting the industrial automation performance, it is popularly utilized to tackle various real‐world problems, such as biomedical image analysis (Ronneberger, Fischer, & Brox, ), facial expression recognition (Liong, See, Wong, & Phan, ), gait tracking (Pfister, West, Bronner, & Noah, ), phishing attack detection (Rao & Ali, ), and many other applications. Previous works applied computer vision to measure the volume of the food or agricultural products such as apples (Ziaratban, Azadbakht, & Ghasemnezhad, ), eggs (Soltani, Omid, & Alimardani, ), beans (Anders, Kaliniewicz, & Markowski, ), abalone (Lee, Lee, Kim, & Yang, ) and ham (Du & Sun, ). Note that many of the objects of interest have an ellipsoidal shape.…”

“…Lee et al () designed a laboratory‐scale system to automatically measure several geometric parameters (i.e., total length, body length, and thickness) of an abalone. The sample size in the experiment is 500 and their weights range around 15–130 g. The two‐dimensional (2D) images are obtained from two CCD cameras which are installed at the base and the side of the abalone.…”

Automatic Surface Area and Volume Prediction on Ellipsoidal Ham using Deep Learning

“…From the computer vision perspective, aside from benefiting the industrial automation performance, it is popularly utilized to tackle various real-world problems, such as biomedical image analysis [5], facial expression recognition [6], gait tracking [7], phishing attack detection [8], and many other applications. Previous works applied computer vision to measure the volume of the food or agricultural product such as apple [9], egg [10], beans [11], abalone [12] and ham [13]. Note that many of the objects of interest are in ellipsoidal shape.…”

“…Lee et al [12] design a laboratory-scale system to automatic measure several geometric parameters (i.e., total length, body length and thickness) of an abalone. The sample size in the experiment is 500 and they are ranged around 15g to 130g.…”