Abstract
This paper describes a computational framework for the extraction of low-level directional primitives in images. The system is divided in two stages. The first one consists of the low level directional primitive extraction, through the Gabor wavelet decomposition. The second one consists of the reduction of the high dimensionality of the Gabor decomposition results by means of auto-organised structures. The main advantages of the system introduced are two: it provides accurate and reliable information, and it produces good results on different image types without intervention of the final user. These advantages will be demonstrated by comparing our system with a classical edge detector.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- SOM:
-
Self-organising map
- GCS:
-
Growing cell structures
- GNG:
-
Growing neural gas
References
Carreira M, Mirmehdi M, Thomas B, Penas M (2002) Perceptual primitives from an extended 4D Hough transform. Image Vision Comput 20(13–14): 969–980
Chen J, Sato Y, Tamura S (2000) Orientation space filtering for multiple orientation line segmentation. IEEE Trans Pattern Anal Mach Intell 22(5): 417–429
Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am 2(7): 1160–1169
Deemter JHV, Buf JMHD (2000) Simultaneous detection of lines and edges using compound Gabor filters. Int J Pattern Recogn Artif Intell 14(4): 757–777
Foley JD (1990) Computer graphics. Principles and practice. Addison-Wesley
Fritzke B (1994) Growing cell structures – a self-organizing network for unsupervised and supervised learning. Neural Networks 7(9): 1441–1460
Fritzke B (1996) Growing self-organising networks – Why?. In: 4th European symposium on artificial neural networks. pp. 61–72
Gabor D (1946) Theory of communication. J Inst Electr Eng 36(93): 429–457
Kohonen T (1982) Self-organised formation of topologically correct feature maps. Biol Cybern 43: 267–273
Kohonen T, Hynninen J, Kangas J, Laaksonene J (1996) SOM-PAK: The Self-Organizing Map Program Package. Technical report, Laboratory of Computer and Information Science, Helsinky University of Technology
Lampinen J, Oja E (1995) Distortion tolerant pattern recognition based on self-organizing feature extraction. IEEE Trans Neural Networks 6(3): 539–547
Lowe DG (1985) Perceptual organization and visual recognition. Kluwer Academic Publishers
Lowe DG (1993) Perceptual organisation in computer vision: a review and a proposal for a classificatory structure. IEEE Trans Syst Man Cybern 23(2): 382–399
Martinetz T, Schulten K (1991) A Neural-Gas network learns topologies. In: Proceedings of the international conference on neural networks. pp. 397–402
Mehrotra R, Namuduri KR, Ranganathan N (1992) Gabor filter-based edge detection. Pattern Recogn 25(12): 479–1494
Nestares O, Navarro R, Portilla J, Tabernero A (1998) Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. J Electr Imaging 7: 166–173
Penas M, Carreira MJ, Penedo MG, Barreira N (2005) Comparison of alternative frameworks for directional primitive extraction. Pattern Recogn Image Anal 15(2): 279–282
Sarkar S, Boyer KL (1994) Computing perceptual organization in computer vision. World Scientific
Sarkar S, Soundararajan P (2000) Supervised learning of large perceptual organization: graph spectral partitioning and learning automata. IEEE Trans Pattern Anal Mach Intell 22(3): 504–517
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Penas, M., Penedo, M.G. & Carreira, M.J. A Neural Network Based Framework for Directional Primitive Extraction. Neural Process Lett 27, 67–83 (2008). https://doi.org/10.1007/s11063-007-9060-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-007-9060-y