The object recognition algorithm based on local gradient ratio feature measurement

被引：0
作者：
Chen, Yuantao [1 ]
Zuo, Jingwen [2 ]
She, Kang [2 ]
Xiang, Zhiwu [2 ]
Wang, Zhongyuan [2 ]
机构：
[1] School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha
[2] College of Chengnan, Changsha University of Science & Technology, Changsha
来源：
Journal of Information and Computational Science | 2015年 / 12卷 / 12期
基金：
中国国家自然科学基金;
关键词：
Local gradient ratio feature measurement; Object recognition; SAR image; Similarity calculation;
D O I：
10.12733/jics20106421
中图分类号：
学科分类号：
摘要：
For the speckle noise and local image gradient characteristics in SAR image coherent, the paper has proposed a local gradient ratio feature similarity criterion based on the gradient ratio. Firstly, it extracts features of each image pixel of SAR image, then constructs the Local Gradient Ratio Feature Measurement (LGRFM), and further analyzes multi-scale LGRFM and the K-L distance definition of similarity calculation of multi-scale LGRFM. The SAR image simulation and real image simulation are based on the experimental results. The similarity to SAR image with speckle noise and local gradient ratio feature is not sensitive to change. It can be applied in SAR image for object recognition. Copyright © 2015 Binary Information Press.
引用
收藏
页码：4689 / 4695
页数：6
相关论文
共 11 条
  • [1] Inglada J., Mercier G., A new statistical similarity measure for change detection in multitemporal SAR images and its extension to multitemporal SAR images and its extension to multiscale change analysis, IEEE Transactions on Geoscience and Remote Sensing, 45, 5, pp. 1432-1445, (2007)
  • [2] Dong Y., Ma J., Wavelet-based image texture classification using local energy histograms, IEEE Transactions on Signal Processing Letters, 18, 4, pp. 247-250, (2011)
  • [3] Dai D., Yang W., Sun H., Multi-level local pattern histogram for SAR image classification, IEEE Transactions on Geoscience and Remote Sensing Letters, 8, 2, pp. 225-229, (2011)
  • [4] Ojala T., Pietikainen M., Et al., A comparative study of texture measures with classification based on feature distributions, Pattern Recognition, 29, 1, pp. 51-59, (1996)
  • [5] Jun B.J., Kim D.J., Robust face detection using local gradient patterns and evidence accumulation, Pattern Recognition, 45, 2, pp. 3304-3315, (2012)
  • [6] Ojala T., Pietikainen M., Et al., Multiresolution grayscale and rotation invariant texture classification with local binary patterns, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 7, pp. 971-977, (2002)
  • [7] Guo Z.H., Zhang L., Et al., Hierarchical multiscale LBP for face and palmprint recognition, Proceedings of the IEEE International Conference on Image Processing, pp. 4521-4524, (2010)
  • [8] Li L., Tong C.S., Et al., Texture classification using refined histogram, IEEE Transactions on Image Processing, 19, 5, pp. 1371-1378, (2010)
  • [9] He Z.G., Lu J., Kuang G.Y., A fast SAR target recognition approach using PCA features, Proceedings of the Fourth International Conference on Image and Graphics, pp. 580-585, (2007)
  • [10] Liu H., Zhang Y., Zhang C., Medical image segmentation based on contextual label tree for retrieval, Journal of Computational Information Systems, 7, 5, pp. 1472-1478, (2011)
12