Research on Threshold Segmentation and Hough Circle Detection Based on Grape Image
Main Article Content
Abstract
To solve the problem that the shape of the fruit is round and overlapping, the segmentation and circle detection of the image of the fruit are studied, which provides a feasible method for the recognition and positioning of the fruit by mechanical picking. In this paper, the image is first enhanced, Tsallis entropy algorithm and Ostu method are selected to find the best threshold for image segmentation, and Hough transform is combined to detect the target region automatically. By comparing the segmentation and detection effects of Tsallis entropy algorithm and Ostu method on grape images, the experimental results show that under the condition of the same radius and sensitivity of 0.96, the segmentation effects of the two algorithms are comparable, and the Ostu method correctly detects relatively more grape numbers. The proposed algorithm can effectively improve the detection and operation efficiency and reduce the calculation amount.
Article Details
![Creative Commons License](http://i.creativecommons.org/l/by-nc-nd/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Pan F, Guodong L, Pengju G, et al. Multi-Feature Patch-Based Segmentation Technique in the Gray-Centered RGB Color Space for Improved Apple Target Recognition[J]. Agriculture, 2021, 11(3): 273-273.
Yu C, Dashi L, Chaowen H. ASE-UNet: An Orange Fruit Segmentation Model in an Agricultural Environment Based on Deep Learning[J]. Optical Memory and Neural Networks, 2023, 32(4): 247-257.
Zhang Li, Li Xiao, Wu Haotian, et al. Research on image segmentation algorithm based on maximum inter-class variance [J]. Science & Technology Innovation and Application, 2021, (08): 39-41+46.
Lei Xiqian, Xu Qin, Luo Dian, et al. Improved Tsallis entropy image threshold segmentation based on image complexity [J]. Internet of Things Technology, 2019,11(12):65-66+70. (in Chinese)
Zhifen W , Zhonghua Z, Yuqi L, et al. SE-COTR: A Novel Fruit Segmentation Model for Green Apples Application in Complex Orchard. [J]. Plant phenomics (Washington, D.C.), 2022, 20220005-0005.
Junxiong Liang et al. Occlusion-aware fruit segmentation in complex natural environments under shape prior[J]. Computers and Electronics in Agriculture, 2024, 217: 108620-.
Wang X. Research on multi-variety fruit flower image segmentation based on deep learning [D]. Wuhan University of Light Industry,2021.
Lin G, Tang Y, Zou X, et al. Fruit detection in natural environment using partial shape matching and probabilistic Hough transform[J]. Precision Agriculture: An International Journal on Advances in Precision Agriculture, 2020, 21(1): 160-177.