|Type of Publication:||Article||Keywords:||Object recognition; Degraded images; Transformation invariance; Sensor array imaging; Sparsity; Image reconstruction; Preprocessing; Neural networks|
|Authors:||A. Ravichandran, B. Yegnanarayana|
The objective of this paper is to study the performance of artificial neural network models for recognition of objects from poorly resolved, noisy, and transformed (scaled, rotated, translated) images, such as images reconstructed from sparse and noisy data in a sensor array imaging context. Noise and sparsity of data in the imaging context result in degradation of quality of the reconstructed image as a whole, instead of affecting it in the form of local corruption of the image pixel information as in many image processing situations. Hence, (i) neighbourhood processing methods for noise cleaning may not be suitable, (ii) feature extraction cannot be reliably performed, and (iii) model-based methods for classification cannot easily be applied. In this paper, we show that neural network models can be used to overcome some of the difficulties in dealing with degraded images as obtained in an imaging context.