Mango Classification System Based on Machine Vision and Artificial Intelligence Nguyen Truong Thinh Faculty of mechanical engineering Ho Chi Minh City University of Technology and Education Ho Chi Minh City, Viet Nam thinhnt@hcmute.edu.vn Huynh Thanh Cong Faculty of Engineering Mechanics Engineering Ho Chi Minh City University of Technology, VNU- HCMC Ho Chi Minh City, Viet Nam htcong@hcmut.edu.vn Nguyen Duc Thong Faculty of Education Physics - Chemistry - Biology Dong Thap University Cao Lanh City, Dong Thap, Viet Nam ndthong@dthu.edu.vn Nguyen Tran Thanh Phong 4th year student, Ho Chi Minh City University of Technology and Education. Ho Chi Minh City, Viet Nam nttphong2412@gmail.com Abstract—Sorting and Classification of mango, there are different colors, weights, sizes, shapes and densities. Currently, classification based on the above features is being carried out mainly by manuals due to farmers' awareness of low accuracy, high costs, health effects and high costs, costly economically inferior. The internal quality of the mango such as sweetness, hardness, age, brittleness... is very important but is only estimated by external or human-perceived evaluation. Therefore, it is necessary to use artificial neural networks to solve this problem. This study was conducted on three main commercial mango species of Vietnam to find out the method of classification of mango with the best quality and accuracy. World studies of mango classification according to color, size, volume and almost done in the laboratory but not yet applied in practice. The quality assessment of mango fruit has not been resolved. Application of image processing technology, computer vision combined with artificial intelligence in the problem of mango classification or poor quality. The goal of the study is to create a system that can classify mangoes in terms of color, volume, size, shape and fruit density. The classification system using image processing incorporates artificial intelligence including the use of CCD cameras, C language programming, computer vision and artificial neural networks. The system uses the captured mango image, processing the split layer to determine the mass, volume and defect on the mango fruit surface. Especially, determine the density of mangoes related to its maturity and sweetness and determine the percentage of mango defects to determine the quality of mangoes for export and domestic or recycled mangoes. Keywords-the classification of mango; sorting of mangoes; image processing technology; artificial intelligence; computer vision; artificial neural networks. I. INTRODUCTION The process of grading mango in Vietnam and the world is being carried out mainly by the direct labor of farmers. In the process of surveying and accessing some agricultural classification systems, the mango classification system on the market is not available in Vietnam. So achieving low productivity, increasing costs. Surveying some of the currently used automatic or semi-automatic agricultural classification systems can be designed and made into a mango classification system. Research and application of high-tech machinery in the process of producing agricultural products on the one hand reduce human labor, reduce costs, and otherwise meet high standards of food safety and hygiene in Processing in fastidious markets requires high quality. The proportion of fruit is considered as a mature indicator of mango fruit. The ripe fruit is submerged in the water while the fruit is alive. Fruit with density greater than 1.00 are submerged in water due to high content of dry matter in the fruit, while fruits with density less than 1.00 are floating in the water. The fruit size index = (wide * thick) / long) on Cat Hoa Loc mango (Vietnam) is strongly correlated with fruit density. Similarly, fruit density, dry matter weight and sugar content are correlated but not correlated with neutralizing acid. Analysis of quality criteria: Brix, dry weight, sugar content, starch content of live fruit, hardness measurement, density, color, fruit weight, sugar content, pH of fruit flesh to determine determine the best quality of mango. Mango is a very sensitive agricultural product and can easily appear brown spots after being crushed during post- harvest handling, transportation and marketing. Testing of the fruit of this fruit used today cannot detect lesions at an early stage of adulthood and so far no automated tools are able to detect; studying the approaches and techniques to assess the quality of mango fruit, checking the surface of mango fruit with deep, wilting, spongy, deformed mangoes, ripening on mango fruit; application of image processing technology, computer vision combined with artificial 475 2019 IEEE 7th International Conference on Control, Mechatronics and Automation 978-1-7281-3787-2/19/$31.00 ©2019 IEEE Authorized licensed use limited to: University College London. Downloaded on May 25,2020 at 07:26:03 UTC from IEEE Xplore. Restrictions apply.