Study on Plant Pest Images Identification Based on Lifting Wavelet Transform

Abstract:

Aiming at the weak noise signals the existence of plant diseases and insect pest images, pathological activity regulation of identification of the plant, so that between the signal molecules exist in plants can regulate mutually, collaborative work. Therefore, identification of weak signal molecules in plants is significant to the study of plant life activities. Taking corn pest images as the research object, using the identification method of lifting wavelet transform, combined with image identification technology, calculated the original plant diseases and insect pest images by not detect the break point of signal. Simulation results show that, the analysis of lifting wavelet of plant disease image identification technology reliability is about 71.65%; the accuracy of edge detection is about 76.21%. The operation speed of this algorithm is fast, easy for hardware implementation, provides an effective method for plant disease images identification.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 3640-3643
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.3640
• Online since: November 2014
• Authors: Chang Cheng Li, Lai Wu Yin, Dong Chen*
• Keywords: Identification, Lifting Wavelet Transform, Plant Pests Image

References

[1] Z. Sun, B. Zhang and K. Fan. Damage identification research of frame structures based on lifting wavelet [J]. World Earthquake Engineering, 2010 26(4) 25-30.

[2] H. S. Li, H. Q. Wang, Y. N. Wang and Z. H. Wang. Distinguish of Fire Image Based on Lifting Wavelet Transform [J]. Computing Technology and Automation, 2008 27(2) 81-84.

[3] X. Zhou, Q. W. Lin. A Fingerprint Identification System Based on Lifting Wavelet and its DSP Realization [J]. Computer Engineering & Science, 2009 31(2) 46-49.

[4] H. K. Jiang, Z. S. Wang and Z. J. He. Early Identification of Weak-Signal Fault Features under Very Unfavorable Environment Using Adaptive Lifting Scheme Packet [J]. J. of Northwestern Polytechnical University, 2008 26(1) 99-103.

[5] Z. J. Yang, L. G. Cai and L. X. Gao. Adaptive redundant lifting wavelet denoising analysis and its application in bearing fault identification [J]. J. of Vibration and Shock, 2013 32(7) 54-57.

[6] Y. L. Dong and W. Jiang. Facial expression recognition based on lifting wavelet and FLD [J]. Optical Technique, 2012 38(5) 579-582.

[7] C. C. Li, C. J. Xie and S. Li et al: Lossless Hyper-Spectral Image Compression Based on XCJRCT, Discrete Wavelet Transform and Set Partitioning In Hierarchical Trees Coding, 2011 International Conference on Mechatronic Science, Electric Engineering and Computer[C]. 2011 11(A) 1010-1014.

DOI: 10.1109/mec.2011.6025636

[8] C. C. Li, L. W. Yin, D. Chen and X. H. Tang. Threshold of Denoising Weak Electrical Signals in Plants from Daubechies Wavelet Transform, 2013 International Conference on Computer Sciences and Applications[C], 2013 8(13) 600-603.

DOI: 10.1109/csa.2013.145