Segmentation of Cotton Leaves Based on Improved Watershed Algorithm
Crop leaf segmentation was one important research content in agricultural machine vision applications. In order to study and solve the segmentation problem of occlusive leaves, an improved watershed algorithm was proposed in this paper. Firstly, the color
- PDF / 1,000,821 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 83 Downloads / 205 Views
4
College of Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China [email protected], [email protected] 2 Beijing Research Center for Information Technology in Agriculture, Beijing 100097, China {lih,zhengwg}@nercita.org.cn 3 National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China Beijing Kingpeng International Hi-Tech Corporation, Beijing 100094, China [email protected], [email protected]
Abstract. Crop leaf segmentation was one important research content in agricultural machine vision applications. In order to study and solve the segmentation problem of occlusive leaves, an improved watershed algorithm was proposed in this paper. Firstly, the color threshold component (G−R)/(G+R) was used to extract the green component of the cotton leaf image and remove the shadow and invalid background. Then the lifting wavelet algorithm and Canny operator were applied to extract the edge of the pre-processed image to extract cotton leaf region and enhance the leaf edge. Finally, the image of the leaf was labeled with morphological methods to improve the traditional watershed algorithm. By comparing the cotton leaf area segmented using the proposed algorithm with the manually extracted cotton leaf area, successful rates for all the images were higher than 97 %. The results not only demonstrated the effectiveness of the algorithm, but also laid the foundation for the construction of cotton growth monitoring system. Keywords: Machine vision Watershed algorithm
Image segmentation
Lifting wavelet
1 Introduction Crop growth information is the basis of precise management of crop production, which plays a decisive role in the management of growth, quality and yield of crops. Leaf information is a direct reflection of crop growth status, and it is a research focus to extract leaf region effectively from crop image in the present research [1, 2]. Cotton is strategic materials relating to the national economy and people’s livelihood, and leaf is also an important organ for photosynthesis of cotton. The size of leaf area has a direct effect on the yield of cotton in a certain extent. Therefore, establishing a convenient and © IFIP International Federation for Information Processing 2016 Published by Springer International Publishing AG 2016. All Rights Reserved D. Li and Z. Li (Eds.): CCTA 2015, Part I, IFIP AICT 478, pp. 425–436, 2016. DOI: 10.1007/978-3-319-48357-3_41
426
C. Niu et al.
accurate method for obtaining leaf area is of positive significance to guide cotton production time activity and develop high yield, high quality and high efficiency cultivation technique measures [3, 4]. In the process of agricultural automation, machine vision technology has become an indispensable part. This technology has been used in many fields of agricultural automation to mine the data from crop images, such as crop water stress [5, 6] and detection of crop diseases [7], etc. In recent years, many resear
Data Loading...
