Volume 43 Issue 12
Jan.  2015
Turn off MathJax
Article Contents

Chen Yu, Huo Furong, Liu Hongzhi, Zheng Liqin. Target recognition with scale distortion based on improved MACH filter[J]. Infrared and Laser Engineering, 2014, 43(12): 4186-4191.
Citation: Chen Yu, Huo Furong, Liu Hongzhi, Zheng Liqin. Target recognition with scale distortion based on improved MACH filter[J]. Infrared and Laser Engineering, 2014, 43(12): 4186-4191.

Target recognition with scale distortion based on improved MACH filter

  • Received Date: 2014-04-09
  • Rev Recd Date: 2014-05-11
  • Publish Date: 2014-12-25
  • When observation distance and angle change, angular distortion and scale distortion of target image relative to the template will appear, which limits the development of pattern recognition with correlation recognition technology. The Maximum Average Correlation Height (MACH) filter was applied to recognize distorted targets in this paper. According to multiple computer simulation experiments and optical experiments, the filter has the characteristcs of high distortion tolerance and bright correlation peaks by optimizing the control parameters of the synthesized filter. Distorted targets were filtered in frequency domain by the improved MACH filter, correlation peaks could be sharpened effectively and recognition scope was expanded succesfully. As a practical example, computer simulation experiments and optical experiments for warship in cluttered scene were carried out. The experimental results prove the feasibility of the algorithm.
  • [1]
    [2] Ma Beihe, Chen Li, Lei Liang, et al. The identification of the vehicle licensing alphabet with the real-time joint Fourier transformation correlation recognition [J]. Journal of Guangdong University of Technology, 2009, 26 (3): 68-71. (in Chinese) 马北河, 陈丽, 雷亮, 等. 实时联合变换相关识别在车牌字 符识别中的应用[J]. 广州工业大学学报, 2009, 26(3): 68-71.
    [3] Zhan Xue, Shang Jiyang, Wang Wensheng. Recognition of distorted target in cluttered background based on maximum average correlation height algorithm [J]. Chinese Jounal of Scientific Instrument, 2010, 31(9): 2042-2048. (in Chinese) 战雪, 尚吉扬, 王文生. 最大平均相关高度法实现复杂背 景畸变目标识别[J]. 仪器仪表学报, 2010, 31(9): 2042-2048.
    [4]
    [5] Shang Jiyang, Chen Chi, Zhang Yu, et al. Application of maximum average correlation height filter algorithm in distotted target recognition [J]. Acta Photonic Sinica, 2011, 40(8): 1231-1236. (in Chinese) 尚吉杨, 陈驰, 张宇, 等. 最大平均相关高度滤波算法在畸 变目标识别中的应用[J]. 光子学报, 2011, 40(8): 1231-1236.
    [6]
    [7]
    [8] Shang Jiyang, Zhang Yu, Chen Chi, et al. Distorted target recognition based on wavelet-modified maximum average correlation height (MACH) algorithm[J]. Chinese Jounal of Scientific Instrument, 2011, 32(9): 2057-2065. (in Chinese) 尚吉扬, 张宇, 陈驰, 等. 小波改进最大平均相关高度法实现 畸变目标识别[J]. 仪器仪表学报, 2011, 32(9): 2057-2065.
    [9] Zhang Su, Xu Chunyun, Wang Wensheng. Tracking technology of moving target in foggy weather based on multi-wavelet enhancement [J]. Infrared and Laser Engineering, 2014, 43(2): 625-632. (in Chinese) 张肃, 徐春云, 王文生. 基于多小波增强的雾天运动目标 跟踪技术[J]. 红外与激光工程, 2014, 43(2): 625-632.
    [10]
    [11]
    [12] Miao Hua, Chen Yu, Wang Wensheng. Research on the application of reversing phase technology in joint transform correlator[J]. Infrared and Laser Engineering, 2007, 36(S): 190-192. (in Chinese) 苗华, 陈宇, 王文生. 提高复杂背景目标探测与识别能力 的研究[J]. 红外与激光工程, 2007, 36(S): 190-192.
    [13]
    [14] Ph. Refregier. Optimal trade-off filters for noise robustness sharpness of the correlation and Horner efficiency [J]. Opt Lett, 1991, 16: 829-831.
    [15] Peter Bone, Rupert Young, Chris Chatwin. Position rotation scale and orientation invariant multiple object recognition from cluttered scenes [C]//SPIE, 2005, 5816: 66-77.
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(266) PDF downloads(132) Cited by()

Related
Proportional views

Target recognition with scale distortion based on improved MACH filter

  • 1. School of Optoelectronic Engineering,Changchun University of Science and Technology,Changchun 130022,China;
  • 2. Changchun New Industries Optoelectronics Tech. Co.,Ltd.,Changchun 130022,China

Abstract: When observation distance and angle change, angular distortion and scale distortion of target image relative to the template will appear, which limits the development of pattern recognition with correlation recognition technology. The Maximum Average Correlation Height (MACH) filter was applied to recognize distorted targets in this paper. According to multiple computer simulation experiments and optical experiments, the filter has the characteristcs of high distortion tolerance and bright correlation peaks by optimizing the control parameters of the synthesized filter. Distorted targets were filtered in frequency domain by the improved MACH filter, correlation peaks could be sharpened effectively and recognition scope was expanded succesfully. As a practical example, computer simulation experiments and optical experiments for warship in cluttered scene were carried out. The experimental results prove the feasibility of the algorithm.

Reference (15)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return