Aiming at the difficulty of artificial fruit classification in traditional agriculture, a nondestructive intelligent sorting and grading system for tomatoes is proposed.Firstly, the system uses microcontroller device to collect digital images of samples to construct species vectors and carry out binary classification to distinguish tomatoes from other species.Secondly, according to the color attribute, tomatoes are divided into mature and immature categories, and Gabor wavelet transform is used to segment the damaged areas in the image and identify the defects in the fruits.Finally, three types of defects are identified according to the defect vectors constructed by additional color and geometric features.The experiment results show that compared with other classifier models, the proposed system has the best performance in all performance indexes.
Key words
intelligent classification /
ARM7 /
Gabor wavelet transform /
support vector machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] Ht A, Tw A, Yl A, et al. Computer vision technology in agricultural automationA reviewScienceDirect[J].Information Processing in Agriculture, 2020, 7(1):119.
[2] Zhao W, Wang X, Qi B, et al.GroundLevel Mapping and Navigating for Agriculture Based on IoT and Computer Vision[J].IEEE Access, 2020(8):221975221985.
[3] Terekhin E A.Recognition of abandoned agricultural lands using seasonal NDVI values[J].Computer Optics, 2017, 41(5):719725.
[4] Qizi A.Methods of Teaching Exact and Natural Sciences Using Computer Technologies to Agricultural Students[J].International Journal of Psychosocial Rehabilitation, 2020, 24(5):74537460.
[5] Hashim N, Ad Ebayo S E, Abdan K, et al.Comparative study of transformbased image texture analysis for the evaluation of banana quality using an optical backscattering system[J].Postharvest Biology and Technology, 2018(135):3850.
[6] Jhawar, Jyoti.Orange Sorting by Applying Pattern Recognition on Colour Image[J].Procedia Computer Science, 2016(78):691697.
[7] Ramos P J, Prieto F A, Montoya E C.Automatic fruit count on coffee branches using computer vision[J].Computers and Electronics in Agriculture, 2017(137):922.
[8] Sofu M M, Er O, Kayacan M C, et al.Design of an automatic apple sorting system using machine vision[J].Computers and Electronics in Agriculture, 2016(127):395405.
[9] 王拥军, 马维华.支持向量机与微波传感器在手势识别中的应用[J].单片机与嵌入式系统应用, 2020, 20(2):5760.
[10] 潘青松, 张怡, 曹永鹏, 等.基于HOG+SVM的智能家居入侵检测系统设计[J].单片机与嵌入式系统应用, 2018, 18(4):7882.
[11] Zhu H, Liu S, Deng L, et al.Infrared Small Target Detection via LowRank Tensor Completion With TopHat Regularization[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 2(58):10041016.
[12] 周威, 刘辉, 曾伟高.基于顶帽变换的指节纹和掌纹识别改进算法[J].传感器与微系统, 2019, 38(3):133136.
[13] Radivojevi D S, Mirkov N S, Maleti S.Human Activity Recognition based on Machine Learning Classification of Smartwatch Accelerometer Dataset[J].FME Transactions, 2021, 49(1):225232.
[14] 余梦媛.基于小波支持向量机的图书馆借阅量预测[J].微型电脑应用, 2020, 36(4):150152.
[15] 陶筱娇, 王鑫.基于深度学习算法的图像分类方法[J].微型电脑应用, 2019, 35(3):4043.
PDF(2092 KB)
