The effects of training algorithms in MLP network on image classification

This paper presents the use of multilayer perceptrons (MLP) trained with various training algorithms for image analysis and pattern recognition. Given a data set of images with known classifications, a system can predict the classification of new images. However, the accuracy of the networks, having the same size and same learning parameters, changes according to training algorithm used in MLP. The effects of the different algorithms are investigated and the best learning methods were proposed for image segmentation.

[1]  M. Avci,et al.  Classification of escherichia coli bacteria by artificial neural networks , 2002, Proceedings First International IEEE Symposium Intelligent Systems.

[2]  Edward Tolson,et al.  Machine Learning in the Area of Image Analysis and Pattern Recognition , 2001 .

[3]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[4]  James T. Kwok.  Moderating the outputs of support vector machine classifiers , 1999, IEEE Trans. Neural Networks.

[5]  Kannan,et al.  ON IMAGE SEGMENTATION TECHNIQUES , 2022 .

[6]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.