Sugarcane node recognition technology based on wavelet analysis

Abstract In order to realize automatic production of sugarcane seed, a sugarcane node recognition analysis based on multi-threshold and multi-scale wavelet transform is proposed. The laser displacement sensor is used to obtain the surface contour signal of sugarcane. After analyzing the signal characteristics, the 5th order of Daubechies wavelet base db5, is chosen as the wavelet mother function, and the signal is decomposed to eight layers by discrete wavelet. The fifth, sixth, and seventh layer coefficients are extracted to perform threshold processing, and the reconstructed signals processed by each threshold value are superimposed to characterize the characteristics of the sugarcane nodes. A multisensory redundancy algorithm based on Gauss membership function is proposed to improve the accuracy of recognition. Experiments show that the recognition rate of the algorithm is 100%, the maximum positioning error is less than 2.5 mm, and the maximum delay is 0.25 s. Compared with other four algorithms based on image processing, the proposed algorithm has higher effectiveness and recognition rate.

[1]  Salah Bouhouche,et al.  Application of Wavelet Transform for Fault Diagnosis in Rotating Machinery , 2012 .

[2]  Yajing Shen,et al.  Surface defect detection of magnetic microwires by miniature rotatable robot inside SEM , 2016 .

[3]  Anand Kumar Pothula,et al.  Profile based image analysis for identification of chopped biomass stem nodes and internodes. , 2015 .

[4]  Takashi Kataoka,et al.  An image processing algorithm for detecting in-line potato tubers without singulation , 2010 .

[5]  C. Igathinathane,et al.  Digital image processing based identification of nodes and internodes of chopped biomass stems. , 2014 .

[6]  Claudio Caprara,et al.  Image Analysis Implementation for Evaluation of External Potato Damage , 2015 .

[7]  Saeid Minaei,et al.  Identification of Sugarcane Nodes Using Image Processing and Machine Vision Technology , 2008 .

[8]  Andreas Uhl,et al.  Directional wavelet based features for colonic polyp classification , 2016, Medical Image Anal..

[9]  José Blasco,et al.  Machine Vision System for Automatic Quality Grading of Fruit , 2003 .

[10]  Jui Jen Chou,et al.  Crop identification with wavelet packet analysis and weighted Bayesian distance , 2007 .

[11]  Jong Wan Hu,et al.  Structural Performance Assessment Based on Statistical and Wavelet Analysis of Acceleration Measurements of a Building during an Earthquake , 2016 .

[12]  S. Loutridis,et al.  CRACK IDENTIFICATION IN BEAMS USING WAVELET ANALYSIS , 2003 .

[13]  Hong Chen,et al.  Eggshell crack detection using a wavelet-based support vector machine , 2010 .

[14]  Gonzalo Pajares,et al.  Discrete wavelets transform for improving greenness image segmentation in agricultural images , 2015, Comput. Electron. Agric..

[15]  Vadim Shapiro,et al.  Effective contact measures , 2016, Comput. Aided Des..

[16]  Peng Hui,et al.  Recognition and features extraction of sugarcane nodes based on machine vision. , 2010 .

[17]  Yan-Fang Sang,et al.  A review on the applications of wavelet transform in hydrology time series analysis , 2013 .