Visual Detection of Hexagonal Headed Bolts Using Method of Frames and Matching Pursuit
In this paper we focus on the problem of automatically detecting the absence of the fastening bolts that secure the rails to the sleepers. The proposed visual inspection system uses images acquired from a digital line scan camera installed under a train. The general performances of the system, in terms of speed and detection rate, are mainly influenced by the adopted features for representing images and by their number. In this paper we use overcomplete dictionaries of waveforms, called frames, which allow dense and sparse representations of images and analyze the performances of the system with respect to the sparsity of the representation. Sparse means a representation with only few no vanishing components. In particular we show that, in the case of Gabor dictionaries, dense representations provide the highest detection rate. Moreover, the number of no vanishing components of 1% of the total reduces of 10% the detection rate of the system, indicating that very sparse representations do not heavily influence the performances. We show the adopted techniques by using images acquired in real experimental conditions.
KeywordsIndependent Component Analysis Sparse Representation Independent Component Analysis Match Pursuit Overcomplete Dictionary
Unable to display preview. Download preview PDF.
- 3.Sung, K., Poggio, T.: Example-based Learning for View-based Human Face Detection. Artificial Intelligence Laboratory. Massachusetts Institute of Technology, Cambridge, MA (1994), A.I. Memo No. 1521Google Scholar
- 4.Papageorgiou, C., Evgeniou, T., Poggio, T.: A trainable pedestrian detection system. In: Proceedings of Intelligent Vehicles, Stuttgart, Germany (October 1998)Google Scholar
- 8.Mazzeo, P.L., Ancona, N., Stella, E., Distante, A.: Visual Recognition of hexagonal headed bolts by comparing ICA to Wavelets. In: Proceedings of the IEEE Inter. Symposium on Intelligent Control-Houston, pp. 636–641 (2003)Google Scholar
- 9.Mazzeo, P.L., Ancona, N., Stella, E., Distante, A.: Fastening Bolts recognition in Railway images by Independent Component Analysis. In: Proc. 3rd Visualization, Imaging and Image Processing-Benalmadena, pp. 668–673 (2003)Google Scholar
- 10.Andrade-Cetto, J., Kak Avinash, C.: Object Recognition. Wiley Encyclopedia of Electrical Engineering Sup. 1, 449–470 (2000)Google Scholar
- 13.Bergeaud, F., Mallat, S.: Matching Pursuit of images. In: Proceedings of the International Conference on Image Processing, pp. 53–56 (1995)Google Scholar
- 17.Ancona, N., Stella, E.: Image representations with overcomplete dictionaries for object detection. Technical Report R.I.- ISSIA/CNR-Nr. 02/2003. Istituto di studi sui sistemi intelligenti per l’Automazione - Consiglio Nazionale delle Ricerche, Bari, Italy (2003) Google Scholar
- 18.Chen, S., Donoho, D., Saunders, M.: Atomic Decomposition by basis pursuit. Technical Report 479, Dept of Statistics, Standford University (1995)Google Scholar