Wavelet Moment Invariants Extraction of Underwater Laser Vision Image  

作　　者：黄蜀玲 庞永杰 王博 万磊 

机构地区：[1]Science and Technology on Underwater Vehicle Laboratory,Harbin Engineering University

出　　处：《Journal of Shanghai Jiaotong university(Science)》2013年第6期712-718,共7页上海交通大学学报（英文版）

基　　金：the Fundamental Research Funds for Central Universities(No.HEUCF110111);the National Natural Science Foundation of China(No.51009040);the China Postdoctoral Science Foundation(No.2012M510928);the Heilongjiang Post-doctoral Fund(No.LBH-Z11205);the National High Technology Research and Development Program(863)of China(No.2011AA09A106)

摘　　要：Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and in- variant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li's(or Zernike's) polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regres- sion neural network(GRNN) was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.Wavelet moment invariants are constructed for object recognition based on the global feature and local feature of target, which are brought for the simple background of the underwater objects, complex structure, similar form etc. These invariant features realize the multi-dimension feature extraction of local topology and invariant transform. Considering translation and scale invariant characteristics were ignored by conventional wavelet moments, some improvements were done in this paper. The cubic B-spline wavelets which are optimally localized in space-frequency and close to the forms of Li＇s （or Zernike＇s） polynomial moments were applied for calculating the wavelet moments. To testify superiority of the wavelet moments mentioned in this paper, generalized regression neural network （GRNN） was used to calculate the recognition rates based on wavelet invariant moments and conventional invariant moments respectively. Wavelet moments obtained 100% recognition rate for every object and the conventional moments obtained less classification rate. The result shows that wavelet moment has the ability to identify many types of objects and is suitable for laser image recognition.

关 键 词：WAVELET MOMENT INVARIANTS UNDERWATER optical VISION images UNDERWATER laser imaging feature EXTRACTION object recognition 

分 类 号：U674.941[交通运输工程—船舶及航道工程]