Fast GNM – The Fast Gradient Network Method
Color image segmentation using the Gradient Network Method in combination with a fast pre-segmentation
Most color image segmentations struggle to identify objects formed by slowly varying shades of color. However, such objects, usually found in outdoors scenes or scenes affected by environment luminance, are easily distinguished as unique by the human eye.
Here we present a generic segmentation technique robust to this type of problem called Fast Gradient Network Segmentation (Fast GNM). The Fast GNM segmentation achieves that by looking for a higher degree of organization in the structure of the scene of the images through the search and identification of continuous and smooth color gradients. Our method works from a starting point from a super-segmented image constructing a network of gradients that is solved to group gradient paths with logical/inductive connection.
Besides providing the image results obtained with Fast GNM, we aim to objectively compare its quality with other state-of-art algorithms. For this goal, we have selected two distance measures developed for image segmentation evaluation. These measures, Rand [Rand71] and Bipartite Graph Matching [Cheng et. al.01], result in float values are in the [0,1] interval, where the closest to 0 the better the segmentation is.
Both Rand and BGM are ground-truth based evaluation measures. So, every image set selected has to have a group of ground-truth images available for the evaluation of the experiments. For this reason, we selected our test sets from the Berkeley Segmentation Dataset and Benchmark [Martin et.al.01], a well-known natural images dataset that has at least 5 and up to 7 ground-truths for every image in its dataset.
We compare our results with those obtained with the following techniques:
- CSC [RehrmannPriese98]
- Mumford-Shah [MumfordShah89] functional-based segmentation method [Megawave06].
- EDISON [ComaniciuMeer02]
- JSEG [DengManjunath01]
Dataset
- By images: a list of the segmentation image results for all the tested images and algorithms. Also every image set displays graphs containing its obtained Rand and BGM scores.
Evaluation results
Algorithm
A more detailed description about GNM can be found in our paper that has been published on Pattern Recognition Letters. This paper can be accessed through this link.
An implementation of the algorithm is available as a Windows binary file. This tar file contains the GNM executable and how to use it.
Results
We provide our obtained results for each selected dataset to allow the comparison with other algorithms. They can be downloaded as image files or as segmentation files following the format described here. The tables containing all the evaluated data can also be downloaded, as a xls file.
If you test GNM and compare it with other algorithms not listed here, we would like to see these results, so, if possible, contact us.
[Cheng et. al.01] H.D. Cheng, X.H. Jiang, Y. Sun and J. Wang. Color image segmentation: advances and prospects. Pattern Recognition 34 (2001), pp. 2259-2281.
[Rand71] W. M. Rand. Objective criteria for the evaluation of clustering methods. Journal of the American Statistical Association. Vol. 66. pp 846/850, 1971.
[ComaniciuMeer02] D. Comaniciu, P. Meer. Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence; 2002; 24 (5); 603-619.
[DengManjunath01] Deng, Y., Manjunath B.S. Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence; 2001; 23(8):800-810.
[Martin et.al.01] Martin, D., Fowlkes, C., Tal, D., Malik, J. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. 8th Int’l Conf. Computer Vision. vol. 2; 2001. p. 416-423.
[MumfordShah89] Mumford, D. and Shah, J. Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math., vol. 42, 1989: 577-684.
[RehrmannPriese98] Rehrmann, V. and Priese, L. Fast and Robust Segmentation of Natural Color Scenes. ACCV (1), 1998: 598-606.
[Megawave06] http://www.cmla.ens-cachan.fr/Cmla/Megawave/. Access in: 14 September 2006.
