Research on the Edge Detection Method of the Rice Leaves Image Based on Phase Consistency under the Complex Environment

Abstract:

In order to realize the effective segmentation of the rice leaf lesion, how to remove background interference and isolating single rice leaf from collected images is the basis of disease classification and recognition. The main body information of the images collected under the simple background of lighting box and field contains only single leaf, so we can use the normal way to detect the blade edge. However, because of the outside interference under the background of field, parameters can't be quantified and the treatment effect of using ordinary edge detection methods is bad. This paper takes advantage of the characteristics that phase consistency test methods that protect them from the image contrast and brightness change and have a strong ability to resist noise to realize complete extraction of the main blade edge in the rice leaf image under the complex background.

• Periodical: Advanced Materials Research (Volumes 605-607)
• Pages: 2145-2148
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.605-607.2145
• Online since: December 2012
• Authors: Li Bo Liu, Chun Jiang Zhao, Hua Rui Wu, Rong Hua Gao
• Keywords: Complex Environment, Edge Detection, Phase Consistency, Rice Leaves

References

[1] Gan Jinlai, Liu Zhao, the image feature detection algorithm based on phase[J]. Experimental Science and Technology, 2006 (2) : 16-19.

[2] MCMorrone & RAOwens. Feature detection from local Eenergy [J]. Pattern Recognition Letters, 1987, 6 (5): 303-313.

[3] Yuan Haidong. Research of low-level visual features detection technology based on the gradient and phase information[D]. Beijing: Beijing University of Posts and Telecommunications, (2008).

[4] Xiao Z T, HOU ZX. Phase based feature detector consistent with human visual system characteristics [J]. Pattern RecognitionLetters, 2004, 25 (10): 1 115-1 121.

DOI: 10.1016/j.patrec.2004.03.018

[5] XIAO Z T, HOU ZX, MIAOCY, etal. Using phase information for symmetry detection [J]. Pattern Recognition Letters, 2005, 26 (13): 1985-(1994).

DOI: 10.1016/j.patrec.2005.02.003

[6] Venkatesh S. & Owens RA. An energy feature detection seheme [C]. In The Intemational Conferenee on Image Proeessing, Singapore, 1989, 553-557.

[7] Weng Xiumei. Image segmentation study through Phase information [J]. Tianjin: Tianjin University of Technology, (2008).

[8] Luo Bin, Tu Zhengzheng, Guo Yutang. Moving target Extraction based on motion information and the phase coherence [J]. Journal of system simulation, 2008, 20 (1): 94-98.