论文信息 - Contextual Edge Detection Using a Recurrent Neural Network

Contextual Edge Detection Using a Recurrent Neural Network

If we consider edge detection as a classification problem, then it seems reasonable that context should play an important role in its study. In fact, it is frequent that neighboring pixels exhibit a strong inter-dependence. In this paper we propose a recurrent neural network for edge detection, which uses a special architecture intended to incorporate contextual information during operation. Some experimental results are presented, showing its effectiveness.

Armando J. Pinho | Luís B. Almeida

[1] Armando J. Pinho,et al. Edge Detection Filters Based on Artificial Neural Networks , 1995, ICIAP.

[2] Patrick A. Shoemaker,et al. A note on least-squares learning procedures and classification by neural network models , 1991, IEEE Trans. Neural Networks.

[3] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[4] Bruce W. Suter,et al. The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[5] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6] M. Bertero,et al. Ill-posed problems in early vision , 1988, Proc. IEEE.

[7] Eric A. Wan,et al. Neural network classification: a Bayesian interpretation , 1990, IEEE Trans. Neural Networks.

[8] Shigeki Miyake,et al. Bayes statistical behavior and valid generalization of pattern classifying neural networks , 1991, IEEE Trans. Neural Networks.

[9] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[10] Armando J. Pinho,et al. Some results on edge enhancement with neural networks , 1994, Proceedings of 1st International Conference on Image Processing.

[11] Richard Lippmann,et al. Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.