Exploring hierarchy simplification for non-significant region removal
Image segmentation is a classic subject in the field of digital image processing, and it can be used to solve a large variety of problems or serve as preprocessing for other methods of image analysis. The use of hierarchical image segmentation methods, which provide a multiscale representation that can be seen as a series of image segmentations, is a very common approach. The main idea of these methods is to produce a nested set of image segmentations in which a result at a given level can be produced by merging regions of the segmentation at its previous level. However, a hierarchy representation may produce small components at its higher levels, leading to oversegmentations on such scales. To solve this problem, we explore strategies to simplify hierarchies in order to remove non-significant regions, in terms of area, while trying to preserve the hierarchical structure. We evaluate the proposed simplification strategies with different hierarchical segmentation methods on the Pascal Context dataset by using precision-recall measures and fragmentation curve, along with a qualitative assessment showing that the simplification of hierarchies can lead to visually better image segmentations.
M. F. Alcântara, T. P. Moreira, H. Pedrini, "Real-time action recognition based on cumulative motion shapes", 2014 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 2917-29May 2014.
I. Mingireanov Filho, T. V. Spina, A. X. Falcao, A. C. Vidal, "Segmentation of sandstone thin section images with separation of touching grains using optimum path forest operators", Computers & geosciences, vol. pp. 146-12013.
J. Cousty, L. Najman, M. Couprie, S. Clément-Guinaudeau, T. Goissen, J. Garot, "Segmentation of 4d cardiac mri: Automated method based on spatio-temporal watershed cuts", Image and Vision Computing, vol. no. 8, pp. 1229-122010.
F. Milletari, N. Navab, S.-A. Ahmadi, "V-net: Fully convolutional neural networks for volumetric medical image segmentation", 2016 Fourth International Conference on 3D Vision (3DV), pp. 565-52016.
K. Bacchuwar, J. Cousty, R. Vaillant, L. Najman, "Scale-space for empty catheter segmentation in pci fluoroscopic images", International journal of computer assisted radiology and surgery, vol. no. 7, pp. 1179-1188, 2017.
M. Drozdzal, G. Chartrand, E. Vorontsov, M. Shakeri, L. di Jorio, A. Tang, A. Romero, Y. Bengio, C. Pal, S. Kadoury, "Learning normalized inputs for iterative estimation in medical image segmentation", Medical image analysis, vol. pp. 1-2018.
J. Cousty, L. Najman, Y. Kenmochi, S. Guimarães, "Hierarchical segmentations with graphs: Quasi-flat zones minimum spanning trees and saliency maps", Journal of Mathematical Imaging and Vision, vol. no. 4, pp. 479-502, 2018.
L. Najman, M. Schmitt, "Geodesic saliency of watershed contours and hierarchical segmentation", Transactions on Pattern Analysis and Machine Intelligence, pp. 1163-111996.
P. Arbelaez, M. Maire, C. Fowlkes, J. Malik, "Contour detection and hierarchical image segmentation", Transactions on Pattern Analysis and Machine Intelligence, vol. no. 5, pp. 898-92011.
S. Guimaraes, Y. Kenmochi, J. Cousty, Z. Patrocinio, L. Najman, "Hierarchizing graph-based image segmentation algorithms relying on region dissimilarity - the case of the Felzenszwalb-Huttenlocher method", Mathematical Morphology - Theory and Applications, vol. 2, no. 1, pp. 55-2017.
S. J. F. Guimaraes, J. Patrocínio, K.G. Zenilton, A. Petrosino, "A graph-based hierarchical image segmentation method based on a statistical merging predicate" in Image Analysis and Processing - ICIAP 2013 ser. Lecture Notes in Computer Science, Springer Berlin Heidelberg, vol. 81pp. 11-2013.
S. J. F. Guimarães, Z. K. G. do Patrocínio, Y. Kenmochi, J. Cousty, L. Najman, V. Murino, E. Puppo, "Hierarchical image segmentation relying on a likelihood ratio test" in Image Analysis and Processing - ICIAP 20Cham:Springer International Publishing, pp. 25-2015.
L. Vincent, "Grayscale area opening and closing their efficient implementation and applications", Proc. Eurasip Workshop on Mathematical Morphology and its Applications to Signal Processing, 1993.
Y. Xu, T. Gćraud, L. Najman, "Hierarchical image simplification and segmentation based on mumford-shah-salient level line selection", Pattern Recognition Letters, vol. pp. 278-22016.
B. Perret, J. Cousty, J. C. R. Ura, S. J. F. Guimaraes, J. A. Benediktsson, J. Chanussot, L. Najman, H. Talbot, "Eval-uation of morphological hierarchies for supervised segmentation" in Mathematical Morphology and Its Applications to Signal and Image Processing, Springer International Publishing, pp. 39-2015.
B. Perret, J. Cousty, S. J. GuimarA£es, D. S. Maia, "Evaluation of hierarchical watersheds", IEEE Transactions on Image Processing, vol. no. 4, pp. 1676-1688, 2018.
P. Salembier, L. Garrido, "Binary partition tree as an efficient representation for image processing segmentation and information retrieval", IEEE Trans. Image Processing, vol. 9, no. 4, pp. 561-52000.
P. F. Felzenszwalb, D. P. Huttenlocher, "Efficient graph-based image segmentation", International Journal of Computer Vision, vol. no. 2, pp. 167-12004.
E. Cayllahua-Cahuina, J. Cousty, S. Guimaraes, Y. Kenmochi, G. Camara-Chávez, A. de Albuquerque Araújo, "A study of observation scales based on felzenswalb-huttenlocher dissimilarity measure for hierarchical segmentation" in Discrete Geometry for Computer Imagery, Springer International Publishing, pp. 167-12019.
P. Dollár, Zitnick, "Fast edge detection using structured forests", Transactions on Pattern Analysis and Machine Intelligence, vol. no. 8, pp. 1558-152015.
R. Mottaghi, X. Chen, X. Liu, N.-G. Cho, S.-W. Lee, S. Fidler, R. Urtasun, A. Yuille, "The role of context for object detection and semantic segmentation in the wild", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
M. Everingham, L. van Gool, C. K. I. Williams, J. Winn, A. Zisserman, The PASCAL Visual Object Classes Challenge 2010 (VOC20Results, [online] Available: http://www.pascal-network.org/challenges/VOC/voc2010/workshop/index.html.