基于改进熵率超像素和区域合并的岩屑图像分割
Rock Image Segmentation Based on Improved Entropyrate Superpixel and Region Merging

作者: 李 杰 , 吴小强 * , 熊淑华 , 王亚静 , 何小海 :四川大学电子信息学院,四川 成都;

关键词: 岩屑图像图像分割熵率超像素区域合并Rock Image Image Segmentation Entropy Rate Superpixel Region Merging

摘要:
岩屑颗粒的分割与提取在地质分析、矿物处理中起着关键的作用,是岩性识别和分析的基础。针对岩屑颗粒图像纹理、阴影、形状、边缘特征复杂的特点,本文提出一种改进熵率超像素分割和区域合并后续处理方法。熵率超像素算法提出具有紧凑性、区域一致性约束的目标函数,考虑岩屑颗粒的形状,对此目标函数加入基于镜面对称系数的几何对称性约束条件,用此目标函数对岩屑颗粒聚类超像素分割,使岩屑颗粒图像分割边缘定位更加准确。针对超像素过分割严重的特征,提出基于和差直方图的最大相似度合并算法,降低岩屑图像过分割率。实验结果表明,此算法用于岩屑的分割,比其他算法取得较好的分割结果。

Abstract: Detection and segmentation of rocks plays an important role in many applications such as geological analysis and mining processes, and it is the foundation of the analysis and recognition. Rocks are usually segmented using a variety of features such as texture, shading, shape and edges. In this paper, an improved algorithm based on entropy rate superpixel and region merging is provided. The entropy rate superpixel segmentation algorithm proposes an objective function, which favors formation of compact and homogeneous clusters. Considering the shape of Rocks, the mirror sym- metry coefficient is integrated into the objective function. If rock images were then segmented by superpixel algorithms with this objective function, the results would adhere more accurately to rock boundaries. Furthermore, we propose an improved maximal similar region merging algorithm based on the sum and difference histograms for function reducing the over-segmentation. The experiment results show that applying this algorithm to rock images performs very well.

文章引用: 李 杰 , 吴小强 , 熊淑华 , 王亚静 , 何小海 (2016) 基于改进熵率超像素和区域合并的岩屑图像分割。 图像与信号处理, 5, 16-24. doi: 10.12677/JISP.2016.51003

参考文献

[1] Mori, G., Ren, X., Efros, A.A. and Malik, J. (2004) Recovering Human Body Configurations: Combining Segmentation and Recognition. In CVPR.

[2] Ren, X. and Malik, J. (2003) Learning a Classification Model for Segmentation. In ICCV.
http://dx.doi.org /10.1109/iccv.2003.1238308

[3] Kohli, P., Ladicky, L. and Torr, P. (2009) Robust Higher Order Potentials for Enforcing Label Consistency. IJCV, 82, 302-324.
http://dx.doi.org /10.1007/s11263-008-0202-0

[4] Hoiem, D., Stein, A.N., Efros, A.A. and Hebert, M. (2007) Recovering Occlusion Boundaries from a Single Image. In ICCV.
http://dx.doi.org /10.1109/iccv.2007.4408985

[5] Ramalingam, S., Kohli, P., Alahari, K. and Torr, P.H.S. (2008) Exactinference in Multi-Label Crfs with Higher Order Cliques. In CVPR.

[6] 王春瑶, 陈俊周, 李炜. 超像素分割算法研究综述[J]. 计算机应用研究, 2014, 31(1): 6-12.

[7] Felzenszwalb, P.F. (2004) Efficient Graph-Based Image Segmentation. International Journal of Computer Vision, 59, 167-181.
http://dx.doi.org /10.1023/B:VISI.0000022288.19776.77

[8] Vincent, L. and Soille, P. (1991) Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13, 583-598.
http://dx.doi.org /10.1109/34.87344

[9] 王亚静, 王正勇, 等. 基于熵率超像素和区域合并的岩屑颗粒图像分割[J]. 计算机工程与设计, 2014, 35(12): 4223-4227.

[10] Liu, M.Y., Tuzel, O., Ramalingam, S. and Chellappa, R. (2014) Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 99-112.

[11] Cicconet, M., Geiger, D., Gunsalus, K.C., et al. (2014) Mirror Symmetry Histograms for Capturing Geometric Properties in Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2981-2986.

[12] Cover, T.M. and Thomas, J.A. (1991) Elements of Information Theory. 2nd Edition, John Wiley & Sons.
http://dx.doi.org /10.1002/0471200611

[13] Ning, J.F., Zhang, L., Zhang, D. and Wu, C.K. (2010) Interactive Image Segmentation by Maximal Similarity Based Region Merging. Pattern Recognition, 43, 445-456.

[14] 杨振威. 岩屑图像分析及边缘检测技术的研究与实现[D]. 成都: 四川大学, 2012.

[15] Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J. and Dickinson, S.J. (2009) Fast Superpixels Using Geometric Flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31, 2290-2297.

[16] 何艳. 岩屑图像分割算法研究[D]. 成都: 四川大学, 2013.

[17] 王倩. 岩屑图像分割相关技术研究及应用[D]. 成都: 四川大学, 2014.

分享
Top