Theory and application of connectivity maskbased reconstruction
opening operator
CAI Jinhui1,2, ZHANG Guangxin1, CAI Hui1,3, HOU Dibo1, ZHOU Zekui1
pening operatorCAI Jinhui1,2, ZHANG Guangxin1, CAI Hui1,3, HOU Dibo1, ZHOU Zekui1
(1. Department of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China;
2. College of Metrological Technology and Engineering, China Jiliang University, Hangzhou 310018, China;
3. National Electronic Information Products Quality Supervision and Inspection Center, Fujian Provincial Central
Inspection Institute, Fuzhou 350002, China
A new reconstruction operator based on secondgeneration connectivity mask was proposed to efficiently utilize the multichannel information and improve the filtering performance of reconstruction operator. The connectivity mask image, reconstruction mask image and reconstruction marker image are firstly obtained based on different channel information and constrictions. According to the maskbased secondgeneration connectivity, the proposed operator relabels the connected components in the reconstruction mask image. By partition and clustering, a new connectivity space is formed from the reconstruction mask image. In the new connectivity space, some connected components are selectively reconstructed according to the corresponding regions in the marker image. By flexibly selecting the connectivity mask and the mark image, and effectively utilizing the grads information, color information and multichannel information, the maskbased reconstruction operator can solve the problem of information restriction of the traditional reconstruction operator.
［1］ IVAN R, TEROL V. Openings and closings with reconstruction criteria: a study of a class of lower and upper levelings ［J］. Journal of Electronic Imaging, 2005, 14(1): 111.
［2］ SALEMBIER P, SERRA J. Flat zones filtering, connected operators, and filters by reconstruction ［J］. IEEE Transactions on Image Processing, 1995, 3(8): 11531160.
［3］ SERRA J. A lattice approach to image segmentation ［J］. Journal of Mathematical Imaging and Vision, 2006 24(1): 83130.
［4］ BRAGANETO U, GOUTSIAS J. Grayscale level connectivity: theory and applications ［J］. IEEE Transactions on Image Progressing, 2004, 13(12): 15671580.
［5］ BRAGANETO U, GOUTSIAS J. Connectivity on complete lattices: new results ［J］. Computer Vision and Image Understanding, 2002, 85(1): 2253.
［6］ GEORGIOS K, MICHAEL H F. Countering oversegmentation in partitioningbased connectivities ［C］∥ International Conference of Image Processing. Genova: IEEE, 2005, 3: 844847.
［7］ MICHAEL H F. Attributespace connectivity and connected filters ［J］. Image and Vision Computing, 2007, 25(4): 426435.
［8］ GEORGIOS K, MICHAEL H F. Maskbased secondgeneration connectivity and attribute filters ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 9901004.
［9］ SALEMBIER P, RUIZ J. Connected operators based on reconstruction process for size and motion simplification ［C］∥ Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Orlando: IEEE, 2002, 4: 32893292.
［10］ 张光新,蔡晋辉,周泽魁. 面积重构算子理论及应用［J］. 浙江大学学报：工学版, 2005, 39(9): 13581362.
ZHANG Guangxin, CAI Jinhui, ZHOU Zekui. Theory and application of areareconstruction operator ［J］. Journal of Zhejiang University: Engineering Science, 2005, 39(9): 13581362.
