Adaptive neuro fuzzy for image segmentation and edge detection

• Authors: B. R. Vikram;M. A. Bhanu;S. C. Venkateswarlu;M. R. Babu
• Venue: Proceedings of the International Conference and Workshop on Emerging Trends in Technology
• Year: 2010

Adaptive Neuro-Fuzzy system for automatic multilevel image segmentation and edge detection. This system consists of a multilayer perceptron (MLP)-like network that performs image segmentation using thresholds automatically pre selected by Fuzzy C-means clustering algorithm. The learning technique employed is self supervised allowing, therefore, automatic adaptation of the neural network. This system does not require a priori assumptions whatsoever are made about the image (type, features, contents, stochastic model, etc.). Such algorithms are most useful for applications that are supposed to work with different (and possibly initially unknown) types of images. This system is also useful for applications dealing with more complex scenes, where several objects have to be detected. This system produces much smoother results as compared to region growing and histogram thresholding techniques and it is (type, features, contents, stochastic model, etc.). Such algorithms are most useful for applications that are supposed to work with different (and possibly initially unknown) types of images. This system is also useful for applications dealing with more complex scenes, where several objects have to be detected. This system produces much smoother results as compared to region growing and histogram thresholding techniques and it is robust to noise and un illumination conditions.