Pest Image Recognition of Multi-feature Fusion Based on Sparse Representation
HU Yong-Qiang1, SONG Liang-Tu2, ZHANG Jie2, XIE Cheng-Jun2, LI Rui2
1Institute of Science and Technology Information of Qinghai Province, Xining 810001) 2Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031
Abstract Aiming at the characteristics of different pest images with different colors, shapes and textures, a pest recognition method based on sparse representation and multi-feature fusion is proposed, which uses a matrix of labeled training samples to construct different dictionaries. The recognition result is achieved by solving optimal sparse coefficients with the corresponding feature dictionary. Furthermore, a novel learning method, which can be improved efficiently by jointly optimizing classifier weights, is presented to effectively fuse multiple features for pest categorization. The experimental results on real datasets show that the proposed method performs well on pest species recognition either in laboratory or in farmland.
[1] Yang H Z, Zhang J W, Li X T, et al. Remote Automatic Identification System Based on Insect Image. Transactions of the Chinese Society of Agricultural Engineering, 2008, 24(1): 188-192 (in Chinese) (杨红珍,张建伟,李湘涛,等.基于图像的昆虫远程自动识别系统的研究.农业工程学报, 2008, 24(1): 188-192) [2] Mao W H, Zheng Y J, Zhang Y Q, et al. Grasshopper Detection Method Based on Machine Vision. Transactions of the Chinese Society of Agricultural Engineering, 2008, 24(11): 155-158 (in Chinese) (毛文华,郑永军,张银桥,等.基于机器视觉的草地蝗虫识别方法.农业工程学报, 2008, 24(11): 155-158) [3] Han A T, Guo X H, Liao Z, et al. Classification of Agricultural Pests Based on Compressed Sensing Theory. Transactions of the Chinese Society of Agricultural Engineering, 2011, 37(6): 203-207 (in Chinese) (韩安太,郭小华,廖 忠,等.基于压缩感知理论的农业害虫分类方法.农业工程学报, 2011, 27(6): 203-207) [4] Neethirajan S, Karunakaran C, Jayas D S, et al. Detection Techniques for Stored-Product Insects in Grain. Food Control, 2007, 18(2): 157－162 [5] Shen Z R, Zhao H Q, Yu X W. Use of Math-Morphological Features in Insect Taxonomy. III. At the Family Level. Acta Entomologica Sinica, 2003, 46(3): 339-344 (in Chinese) (沈佐锐,赵汗青,于新文.数学形态学在昆虫分类学上的应用研究.III.在科阶元上的应用研究.昆虫学报, 2003, 46(3): 339-344) [6] Zhu L Q, Zhang Z. Insect Recognition Based on Integrated Region Matching and Dual Tree Complex Wavelet Transform. Journal of Zhejiang University-Science C(Computers & Electronics), 2011, 12(1): 44-53 [7] Zhao H Q, Shen Z R, Yu X W. Use of Math-Morphological Features in Insect Taxonomy. I. At the Order Level. Acta Entomologica Sinica, 2003, 46(1): 45-50 (in Chinese) (赵汗青,沈佐锐,于新文.数学形态学在昆虫分类学上的应用研究.Ⅰ.在目级阶元上的应用研究.昆虫学报, 2003, 46(1): 45-50) [8] Zhao H Q, Shen Z R, Yu X W. Use of Math-Morphological Features in Insect Taxonomy. II. At Superfamily Level. Acta Entomologica Sinica, 2003, 46(2): 201-208 (in Chinese) (赵汗青,沈佐锐,于新文.数学形态学在昆虫分类学上的应用研究.II.在总科阶元上的应用研究.昆虫学报, 2003, 46(2): 201-208) [9] Hu Y X, Zhang H T. Recognition of the Stored-Grain Pests Based on Simulated Annealing Algorithm and Support Vector Machine. Transactions of the Chinese Society for Agricultural Machinery, 2008, 39(9): 108-111 (in Chinese) (胡玉霞,张红涛.基于模拟退火算法——支持向量机的储粮害虫识别分类.农业机械学报, 2008, 39(9): 108-111) [10] Chen Y H, Hu X G, Zhang C L. Algorithm for Segmentation of Insect Pest Images from Wheat Leaves Based on Machine Vision. Transactions of the Chinese Society of Agricultural Engineering, 2007, 23(12): 187-192 (in Chinese) (陈月华,胡晓光,张长利.基于机器视觉的小麦害虫分割算法研究.农业工程学报, 2007, 23(12): 187-192) [11] Qiu B J, Cheng Q W, Chen G P, et al. Multiple Areas and Multiple Structures Method of Image Edge Detection for the Long Wing Laodelphax Striatellus (Fallen). Transactions of the Chinese Society for Agricultural Machinery, 2008, 39(7): 119-123 (in Chinese) (邱白晶,程麒文,陈国平,等.长翅灰飞虱图像边缘的多区域多结构检测方法.农业机械学报, 2008, 39(7): 119-123) [12] Zhu L Q, Zhang Z, Zhang P Y. Image Identification of Insects Based on Color Histogram and Dual Tree Complex Wavelet Transform (DTCWT). Acta Entomologica Sinica, 2010, 53(1): 91-97 (in Chinese) (竺乐庆,张 真,张培毅.基于颜色直方图及双树复小波变换(DTCWT)的昆虫图像识别.昆虫学报, 2010, 53(1): 91-97) [13] Zhang H T, Mao H P, Qiu D Y. Feature Extraction for the Stored-Grain Insect Detection System Based on Image Recognition Technology. Transactions of the Chinese Society of Agricultural Engineering, 2009, 25(2): 126-130 (in Chinese) (张红涛,毛罕平,邱道尹.储粮害虫图像识别中的特征提取.农业工程学报, 2009, 25(2): 126-130) [14] Zhang H T, Mao H P. Rough Sets Weights Application in the Extension Classification of the Stored-Grain Pests Based on Fuzzy C-means Discretization. Transactions of the Chinese Society of Agricultural Machinery, 2008, 39(7): 124-128 (in Chinese) (张红涛,毛罕平.基于FCM 离散化的粗集权重在粮虫可拓分类中的应用.农业机械学报, 2008, 39(7): 124-128) [15] Cai Q, He D J. Identification of Vegetable Leaf-Eating Pests Based on Image Analysis. Journal of Computer Application, 2010, 30(7): 1870-1872 (in Chinese) (蔡 清,何东健.基于图像分析的蔬菜食叶害虫识别技术.计算机应用, 2010, 30(7): 1870-1872) [16] Wang J N, Lin C T, Ji L Q, et al. A New Automatic Identification System of Insect Images at the Order Level. Knowledge-Based Systems, 2012, 33: 102-110 [17] Wen C L, Guyer D. Image-Based Orchard Insect Automated Identification and Classification Method. Computers and Electronics in Agriculture, 2012, 89: 110－115 [18] Wright J,Yang A Y,Ganesh A, et al. Robust Face Recognition via Sparse Representation. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227 [19] Han A T, Peng H, Li J F, et al. Recognition of Pests Based on Compressive Sensing Theory // Proc of the 3rd IEEE International Conference on Communication Software and Networks. Xi′an, China, 2011: 263-266 [20] Elhamifar E, Vidal R. Robust Classification Using Structured Sparse Representation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 1873-1879 [21] Qiao L S, Chen S C, Tan X Y, et al. Sparsity Preserving Projections with Applications to Face Recognition. Pattern Recognition, 2010, 43(1): 331-341 [22] Zhang T Z, Ghanem B, Liu S, et al. Low-Rank Sparse Coding for Image Classification // Proc of the IEEE International Conference on Computer Vision. Sydney, Australia, 2013: 281-288 [23] Qi L Y. A Study of Automated Insect Identification Based on Multi-Features Synthesis. Journal of Anhui Agricultural Science, 2009, 37(3): 1380-1381 (in Chinese) (齐丽英.基于多特征综合的昆虫识别研究.安徽农业科学,2009, 37(3): 1380-1381) [24] Wu J, Qiu Z D. An Overview: Low-level Feature Fusion in Content-Based Image Retrieval. Journal of Image and Graphics, 2008, 13(2): 189-197 (in Chinese ) (吴 介,裘正定.底层内容特征的融合在图像检索中的研究进展.中国图象图形学报, 2008, 13(2): 189-197) [25] Swain M J, Ballard D H. Color Indexing. International Journal of Computer Vision, 1991, 7(1): 11-32 [26] Ojala T, Pietikinen M, Harwood D. A Comparative Study of Texture Measures with Classification Based on Feature Distributions. Pattern Recognition, 1996, 29(1): 51-59 [27] Ojala T, Pietikinen M, Maenpaa T. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987 [28] Wu H, Pan Y H, Zhuang Y T, et al. Query Image by Object Shape. Journal of Software, 1988, 9(5): 343-349 (in Chinese) (邬 浩,潘云鹤,庄越挺,等.基于对象形状的图象查询技术.软件学报, 1998, 9(5): 343-349) [29] Chan Y M. Shape-Based Image Retrieval in Iconic Image Databases. Master Dissertation. Hong Kong, China: The Chinese University of Hong Kong, 1999 [30] Rosset S, Zhu J, Hastie T. Boosting as a Regularized Path to a Maximum Margin Classifier. The Journal of Machine Learning Research, 2004, 5: 941-973 [31] Qiu D Y, Zhang C H, Zhang H T, et al. Application of Neural Networks in the Recognition of Stored-Grain Pests. Transactions of the Chinese Society of Agricultural Engineering, 2003, 19(1): 142-144 (in Chinese) (邱道尹,张成花,张红涛,等.神经网络在储粮害虫识别中的应用.农业工程学报, 2003, 19(1): 142-144)
2014, Vol. 27 
