ABSTRACT
Considering that it is difficult to completely segment the spider mite image on the leaves of field crops from the leaf background, a combination segmentation method combining K-means clustering algorithm and Canny edge detection algorithm is proposed. This method first uses the K-means clustering algorithm to filter out most of the leaf background, then extracts the edge closed contour of the spider mite based on Canny edge detection, and implements the binarization segmentation of the spider mite image by algorithms such as seed filling and morphological opening operations. Experiments show that this method can achieve complete segmentation of spider mites images on leaves, which provides a new technique and method for spider mite pest analysis and insect number counting.
- Y. J. Li, Z. Y. Wang, G. H. Zhang, 2014. The effect of temperature on the growth and reproduction of the experimental population of eotetranychus kankitus ehara, Acta Ecologica Sinica, vol. 34, no. 4, pp. 862-868.Google Scholar
- J. Y. Gao, J. Guo, Z. R. Wang, 2012. Research on Pest Species and Occurrence Regularity of Main Pests in Dehong Lemon Garden, Yunnan, Acta Agriculturae Jiangxi, vol. 24, no. 6, pp. 70-73.Google Scholar
- H. Y. Kuang, L. S. Cheng. 1990. Study on distinguishing two similar species of Tetranychus cinnabarinus and Tetranychus urticae, Acta Entomologica Sinica, vol. 33, no. 1, pp. 109-116.Google Scholar
- R. J. Li, K. Y. Wang, X. Y. Jiang, 2005. Research progress in drug resistance of Tetranychus urticae, Journal of Shandong Agricultural University (Natural Science Edition), vol. 36, no. 4, pp. 637-639.Google Scholar
- P. C. Chen, J. H. Zhang, M. M. Li, 2007. Physiological changes and spectral characteristics of cotton leaves damaged by Tetranychus turkestani, Chinese Bulletin of Entomology, vol. 44, no. 1, pp. 61-64.Google Scholar
- H. L. Xiong, C. L. Wu. 2013. Image recognition of Eotetranychus Kankitus Ehara based on BP neural network, Hubei Agricultural Sciences, vol. 52, no. 23, pp. 5863-5865.Google Scholar
- D. Qiu, J. X. Li, L. T. Yang. 2014. Research on Jujube Red Spider Recognition Based on Neural Network, Electronic Science and Technology, vol. 27, no. 3, pp. 48-51.Google Scholar
- C. H. Wu, H. L. Xiong, Q. Wu. 2010. Matlab-based Edge Detection of Eotetranychus Kankitus Ehara, Microcomputer Information, vol. 26, no. 9, pp. 198-199.Google Scholar
- H. Zhang, G. C. Liu. 2014. Two-dimensional LWT wavelet lifting separation and recognition of field spider mite images, Bulletin of Science and Technology, vol. 30, no. 8, pp. 209-211.Google Scholar
- J. Wang, Z. Li. 2015. Tiansheng Hong, , “In-leaf Affected Area Identification from Hyper-spectral Image of Citrus Red Mite Infected Leaf”, Journal of Agricultural Mechanization Research, vol. 36, no. 7, pp. 18-22.Google Scholar
- H. Lan, X. Wang. 2013. Insect image segmentation method based on multiple linear regression, Computer Applications and Software, vol. 30, no. 7, pp. 193-195, 208.Google Scholar
Recommendations
Image segmentation using rough set based k-means algorithm
CUBE '12: Proceedings of the CUBE International Information Technology ConferenceThis paper describes a rough set approach for gray scale image segmentation that can automatically segment an image to its constituents parts. The aim of the proposed method is to produce an efficient segmentation of images using intensity information ...
Ultrasound Pupil Image Segmentation Based on Edge Detection and Detection Operators
ICMLC '20: Proceedings of the 2020 12th International Conference on Machine Learning and ComputingUltrasound imaging technology is developing rapidly and ultrasound images can provide a lot of information for doctors to diagnose. However, the same tissues and organs show large differences in edge strength in ultrasound images which may cause ...
Detection of Brain Tumor in MRI Images, Using a Combination of Fuzzy C-Means and Thresholding
The identification, segmentation, and detection of the infected area in brain tumor is a tedious and a time-consuming task. The different structures of the human body can be visualized by an image processing concept, an MRI. It is very difficult to ...
Comments