Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2013, Vol. 14 Issue (7): 495-504    DOI: 10.1631/jzus.CIDE1303
    
A review of object representation based on local features
Jian Cao, Dian-hui Mao, Qiang Cai, Hai-sheng Li, Jun-ping Du
College of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  Object representation based on local features is a topical subject in the domain of image understanding and computer vision. We discuss the defects of global features in present methods and the advantages of local features in object recognition, and briefly explore state-of-the-art recognition methods using local features, especially the main approaches of local feature extraction and object representation. To clearly explain these methods, the problem of local feature extraction is divided into feature region detection, feature region description, and feature space optimization. The main components and merits of these steps are presented. Technologies for object presentation are classified into three types: vector space, sliding window, and structure relationship models. Future development trends are discussed briefly.

Key wordsObject presentation      Local feature      Image understanding      Object recognition      Visual words     
Received: 29 December 2012      Published: 05 July 2013
CLC:  TP391.41  
Cite this article:

Jian Cao, Dian-hui Mao, Qiang Cai, Hai-sheng Li, Jun-ping Du. A review of object representation based on local features. Front. Inform. Technol. Electron. Eng., 2013, 14(7): 495-504.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.CIDE1303     OR     http://www.zjujournals.com/xueshu/fitee/Y2013/V14/I7/495


A review of object representation based on local features

Object representation based on local features is a topical subject in the domain of image understanding and computer vision. We discuss the defects of global features in present methods and the advantages of local features in object recognition, and briefly explore state-of-the-art recognition methods using local features, especially the main approaches of local feature extraction and object representation. To clearly explain these methods, the problem of local feature extraction is divided into feature region detection, feature region description, and feature space optimization. The main components and merits of these steps are presented. Technologies for object presentation are classified into three types: vector space, sliding window, and structure relationship models. Future development trends are discussed briefly.

关键词: Object presentation,  Local feature,  Image understanding,  Object recognition,  Visual words 
[1] Rong-Feng Zhang , Ting Deng , Gui-Hong Wang , Jing-Lun Shi , Quan-Sheng Guan . A robust object tracking framework based on a reliable point assignment algorithm[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 545-558.
[2] M. F. Kazemi, M. A. Pourmina, A. H. Mazinan. Level-direction decomposition analysis with a focus on image watermarking framework[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1199-1217.
[3] Xun Liu, Yin Zhang, San-yuan Zhang, Ying Wang, Zhong-yan Liang, Xiu-zi Ye. Detection of engineering vehicles in high-resolution monitoring images[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 346-357.
[4] Gui-jie Wang, Yun-long Cai, Min-jian Zhao, Jie Zhong. Joint adaptive power allocation and interference suppression algorithms based on the MSER criterion for wireless sensor networks[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(10): 917-928.
[5] Zheng Liu, Wei-ming Wang, Xiu-ping Liu, Li-gang Liu. Scale-aware shape manipulation[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(9): 764-775.
[6] Xu-dong Jiang, Bin Sheng, Wei-yao Lin, Wei Lu, Li-zhuang Ma. Image anti-aliasing techniques for Internet visual media processing: a review[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(9): 717-728.
[7] Yong-zhao Zhan, Yan-ting Li, Xin-yu Wang, Yi Qian. A blind watermarking algorithm for 3D mesh models based on vertex curvature[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(5): 351-362.
[8] Xin Hao, Ye Shen, Shun-ren Xia. Automatic mass segmentation on mammograms combining random walks and active contour[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(9): 635-648.
[9] Chang-Il Son, Shun-ren Xia. Diffusion tensor interpolation profile control using non-uniform motion on a Riemannian geodesic[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(2): 90-98.
[10] Le-qing Zhu, Zhen Zhang. Insect recognition based on integrated region matching and dual tree complex wavelet transform[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(1): 44-53.
[11] Rui Wang, Wei-feng Chen, Ming-hao Pan, Hu-jun Bao. Harmonic coordinates for real-time image cloning[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(9): 690-698.
[12] Lei Zhang, Peng Liu, Yu-ling Liu, Fei-hong Yu. High quality multi-focus polychromatic composite image fusion algorithm based on filtering in frequency domain and synthesis in space domain[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(5): 365-374.
[13] Abbas Koochari, Mohsen Soryani. Exemplar-based video inpainting with large patches[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(4): 270-277.
[14] Hong ZHOU, Hai-er XU, Pei-qi HE, Zhi-bai SONG, Chen-ge GENG. Automatic inspection of LED indicators on automobile meters based on a seeded region growing algorithm[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(3): 199-205.
[15] Jun-jie CAO, Zhi-xun SU, Xiu-ping LIU, Hai-chuan BI. Measured boundary parameterization based on Poisson’s equation[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(3): 187-198.