Extracting Contours of Hydrothermal Chimney Undersea Images Based on Machine Vision

Contour information is regarded as important characteristic in computer vision. It is difficult to extract contour information from the object of underwater images such as hydrothermal chimney due to its complicated structure. In this paper we discuss of the problem of the contour extraction of the hydrothermal chimney from underwater images. The variety of image quantity of information was denoted dynamically by Multi-Scale Entropy (MSE). And the Multi-Scale Entropy Difference (MSED) can present the break part of the image gray information and recognize the boundary between object and background effectively. The non-structured object contours underwater can be extracted with the advantages of the Maximal Multi-Scale Entropy Difference (MMSED). From the experimental results, the approach is effective. KeywordsMulti-Scale Entropy, Maximal Multi-Scale Entropy Difference, non-structural object, Contour Extraction, information amount

[1]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[2]  P. Rives,et al.  Extracting robust features and 3D reconstruction in underwater images , 2001, MTS/IEEE Oceans 2001. An Ocean Odyssey. Conference Proceedings (IEEE Cat. No.01CH37295).

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Horst Bischof,et al.  Natural, salient image patches for robot localization , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Tat-Jen Cham,et al.  Stereo coupled active contours , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Natan Peterfreund,et al.  Robust tracking with spatio-velocity snakes: Kalman filtering approach , 1997, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[8]  C. K. Leung,et al.  Image segmentation by edge pixel classification with maximum entropy , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).