Advertisement

Colorful Fruit Image Segmentation Based on Texture Feature

  • Chunyan YangEmail author
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 157)

Abstract

The recognition of colorful fruit is one of the important research contents of agricultural machinery vision system. At present, the popular image segmentation method of color model is generally suitable for the case of large difference between fruit and background color. For the image segmentation where the difference between fruit and background color is not obvious, the image segmentation method based on color model cannot meet the actual needs. Therefore, this paper introduces the use of gray-level co-occurrence matrix to analyze the texture features of fruit and background, find out the texture feature parameters to distinguish the fruit and background, and segment the image with similar color between fruit and background. The experimental results show that texture features can not only successfully separate the red apple from the background but also have a very good effect on the segmentation of blue apple image with complex background.

Keywords

Texture Gray-level co-occurrence matrix Segmentation 

References

  1. 1.
    Bo, H., Ma, J., Jiao, L.C.: Analysis of gray level co-occurrence matrix calculation of image texture. Acta Electron. Sin. (2006)Google Scholar
  2. 2.
    Yuan, L., Fu, L., Yang, Y., Miao, J.: Analysis of experimental results of texture feature extraction by gray co-occurrence matrix. Comput. Appl. (2009)Google Scholar
  3. 3.
    Xuesong,W., Mingquan,Z., Yachun, F.: The algorithm of graph cut using HSI weights in color image segmentation. J. Image Graph. 16(2), 221–226 (2012)Google Scholar
  4. 4.
    Mignotte, M.: A de-texturing and spatially constrained K-means approach for image segmentation. Pattern Recogn. Lett. 32(2), 359–367 (2013)CrossRefGoogle Scholar
  5. 5.
    Zhiguang, Z.: A new color space YCH with strong clustering power for face detection. Pattern Recogn. Artif. Intell. 24(4), 502–505 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Baicheng Normal UniversityBaichengChina

Personalised recommendations