Can Convolution Neural Network (CNN) Triumph in Ear Recognition of Uniform Illumination Invariant?

http://iaescore.com/journals/index.php/IJEECS/article/view/12811
Abstract:

Current deep convolution neural network (CNN) has shown to achieve superior 

performance on a number of computer vision tasks such as image recognition, classification 

and object detection. The deep network was also tested for view-invariance, robustness and 

illumination invariance. However, the CNN architecture has thus far only been tested on non-

uniform illumination invariant. Can CNN perform equally well for very underexposed or 

overexposed images or known as uniform illumination invariant? This is the gap that we are 

addressing in this paper. In our work, we collected ear images under different uniform 

illumination conditions with lumens or lux values ranging from 2 lux to 10,700 lux. A total of 

1,100 left and right ear images from 55 subjects are captured under natural illumination 

conditions. As CNN requires considerably large amount of data, the ear images are …