Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2011, Vol. 12 Issue (1): 44-53    DOI: 10.1631/jzus.C0910740
    
Insect recognition based on integrated region matching and dual tree complex wavelet transform
Le-qing Zhu1, Zhen Zhang2
1 College of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou 310018, China 2 Key Lab of Forest Protection of State Forestry Administration, Research Institute of Forest Ecology, Environment and Protection, Chinese Academy of Forestry, Beijing 100091, China
Download:   PDF(414KB)
Export: BibTeX | EndNote (RIS)      

Abstract  To provide pest technicians with a convenient way to recognize insects, a novel method is proposed to classify insect images by integrated region matching (IRM) and dual tree complex wavelet transform (DTCWT). The wing image of the lepidopteran insect is preprocessed to obtain the region of interest (ROI) whose position is then calibrated. The ROI is first segmented with the k-means algorithm into regions according to the color features, properties of all the segmented regions being used as a coarse level feature. The color image is then converted to a grayscale image, where DTCWT features are extracted as a fine level feature. The IRM scheme is undertaken to find K nearest neighbors (KNNs), out of which the nearest neighbor is searched by computing the Canberra distance of DTCWT features. The method was tested with a database including 100 lepidopteran insect species from 18 families and the recognition accuracy was 84.47%. For the forewing subset, a recognition accuracy of 92.38% was achieved. The results showed that the proposed method can effectively solve the problem of automatic species identification of lepidopteran specimens.

Key wordsLepidopteran insects      Auto-classification      k-means algorithm      Integrated region matching (IRM)      Dual tree complex wavelet transform (DTCWT)     
Received: 04 December 2009      Published: 10 January 2010
CLC:  TP391.41  
Fund:  Project (No. 2006AA10Z211) supported by the National High-Tech Research and Development Program (863) of China
Cite this article:

Le-qing Zhu, Zhen Zhang. Insect recognition based on integrated region matching and dual tree complex wavelet transform. Front. Inform. Technol. Electron. Eng., 2011, 12(1): 44-53.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C0910740     OR     http://www.zjujournals.com/xueshu/fitee/Y2011/V12/I1/44


Insect recognition based on integrated region matching and dual tree complex wavelet transform

To provide pest technicians with a convenient way to recognize insects, a novel method is proposed to classify insect images by integrated region matching (IRM) and dual tree complex wavelet transform (DTCWT). The wing image of the lepidopteran insect is preprocessed to obtain the region of interest (ROI) whose position is then calibrated. The ROI is first segmented with the k-means algorithm into regions according to the color features, properties of all the segmented regions being used as a coarse level feature. The color image is then converted to a grayscale image, where DTCWT features are extracted as a fine level feature. The IRM scheme is undertaken to find K nearest neighbors (KNNs), out of which the nearest neighbor is searched by computing the Canberra distance of DTCWT features. The method was tested with a database including 100 lepidopteran insect species from 18 families and the recognition accuracy was 84.47%. For the forewing subset, a recognition accuracy of 92.38% was achieved. The results showed that the proposed method can effectively solve the problem of automatic species identification of lepidopteran specimens.

关键词: Lepidopteran insects,  Auto-classification,  k-means algorithm,  Integrated region matching (IRM),  Dual tree complex wavelet transform (DTCWT) 
[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] 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.
[6] 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.
[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] Jian Cao, Dian-hui Mao, Qiang Cai, Hai-sheng Li, Jun-ping Du. A review of object representation based on local features[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(7): 495-504.
[9] 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.
[10] 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.
[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] 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.
[15] 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.