Industrial IoT Technologies and Applications. Second EAI International Conference, Industrial IoT 2017, Wuhu, China, March 25–26, 2017, Proceedings

Research Article

Edge Affine Invariant Moment for Texture Image Feature Extraction

  • @INPROCEEDINGS{10.1007/978-3-319-60753-5_9,
        author={Yiwen Dou and Jun Wang and Jun Qiang and Ganyi Tang},
        title={Edge Affine Invariant Moment for Texture Image Feature Extraction},
        proceedings={Industrial IoT Technologies and Applications. Second EAI International Conference, Industrial IoT 2017, Wuhu, China, March 25--26, 2017, Proceedings},
        proceedings_a={INDUSTRIALIOT},
        year={2017},
        month={9},
        keywords={EAIM (edge affine invariant moment) Feature extraction K-means SSAT (short step affine transformation Sobel)},
        doi={10.1007/978-3-319-60753-5_9}
    }
    
  • Yiwen Dou
    Jun Wang
    Jun Qiang
    Ganyi Tang
    Year: 2017
    Edge Affine Invariant Moment for Texture Image Feature Extraction
    INDUSTRIALIOT
    Springer
    DOI: 10.1007/978-3-319-60753-5_9
Yiwen Dou1,*, Jun Wang1, Jun Qiang1, Ganyi Tang1
  • 1: Anhui Polytechnic University
*Contact email: yiwend@sina.com

Abstract

Texture image feature extraction is one of hot topics of texture image recognition in recent years. As to this, a novel technique for texture image feature extraction based on edge affine invariant moment is presented in this paper. Firstly, each texture image is checked by a short step affine transformation Sobel algorithm initially. Then, the corresponding texture image feature named edge affine invariant moment will be calculated and added to feature vector set. Subsequently, cluster analysis will be loaded upon the set by K-means algorithm and the categorized texture image can be obtained. Three simulation experiments closed to real environment over the two well-known Brodatz and KTH-TIPS texture databases are performed in order to test the efficiency of our proposed algorithm.