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.
HUANG Shu-ling* (黄蜀玲), PANG Yong-jie (庞永杰), WANG Bo (王 博), WAN Lei (万 磊)
. Wavelet Moment Invariants Extraction of Underwater Laser Vision Image[J]. Journal of Shanghai Jiaotong University(Science), 2013
, 18(6)
: 712
-718
.
DOI: 10.1007/s12204-013-1454-6
[1] Chua K, Arshad M R. Robotics vision-based heuristic reasoning for underwater target tracking and navigation[J]. International Journal of Advanced Robotic Systems, 2005, 2(3): 245-250.
[2] Cufi X, Garcia R, Ridao P. An approach to visionbased station keeping for an unmanned underwater vehicle[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. EPFL,Lausanne, Switzerland: IEEE, 2002: 799-804.
[3] Kinsey J C, Eustice R M, Whitcomb L L. A survey of underwater vehicle navigation: Recent advances and new chanllenges [C]//Proceedings of the 7th IFAC Conference on Maneuvering and Control of Marine Craft. Lisbon, Portugal: IFAC, 2006: 1-12.
[4] Hu M-K. Visual pattern recognition by moment invariants [J]. IRE Transactions on Information Theory,1962, 8(1): 179-187.
[5] Li Y J. Reforming the theory of invariant moments for pattern recognition [J]. Pattern Recognition, 1992,25(7): 723-730.
[6] Teague M R. Image analysis via the general theory of moments [J]. Journal of Optical Society American,1980, 70(8): 920-930.
[7] Belkasim S O, Shridhar M, Ahmadi M. Pattern recognition with moment invariants: A comparative study and new results [J]. Pattern Recognition, 1991,24(12): 1117-1138.
[8] Tang Xu-dong, Zhu Wei, Pang Yong-jie, et al. Target recognition system based on optical vision for AUV [J].Robot, 2009, 31(2): 171-178 (in Chinese).
[9] Shen D, Ip H H S. Discriminative wavelet shape descriptors for recognition of 2-D patterns [J]. Pattern Recognition, 1999, 32(2): 151-165.
[10] Wang Xiang-yang, Yang Yi-ping, Yang Hong-ying. A new robust digital image watermarking based on wavelet moments [J]. Journal of Image and Graphics,2010, 15(1): 15-19 (in Chinese).
[11] Zhang Tie-zhu, Jiang Hong. Intelligent target recognition based on the data fusion of radar and infrared imaging sensor [J]. Infrared and Laser Engineering,2010, 39(4): 756-760 (in Chinese).
[12] Zhu Guang-tao, Li Ying. License plate character recognition method based on wavelet moment and principal component analysis [J]. Computer Systems Application, 2012, 21(7): 168-171 (in Chinese).
[13] Zhang He, Xu Yu-ru, Wan Lei, et al. Processing method for underwater degenerative Image [J]. Journal of Tianjin University, 2010, 43(9): 827-833 (in Chinese).
[14] Wang Yi-feng, Liu Zhi-shen. A denoising method for underwater laser image based on mathematical morphology [J]. Electro-Optic Technology Application,2006, 21(3): 51-53 (in Chinese).
[15] Erkmen B, Yildirim T. Improving classification performance of sonar targets by applying general regression neural network with PCA [J]. Expert Systems with Applications, 2008, 35(1-2): 472-475.
[16] Paroj?ci′c J, Ibri′c S,Djuri′c Z, et al. An investigation into the usefulness of generalized regression neural network analysis in the development of level A in vitro-in vivo correlation [J]. European Journal of Pharmaceutical Sciences, 2007, 30(3-4): 264-272.
