Additive Noise Removal and Human-like Face Detection

Image noise is the random variation of brightness or color information in images. Noise is the result of errors in the image acquisition, transmission and processing. Noise corrupted image do not reflect the true intensities of the real scene. Noise maybe additive and can be removed by using a fuzzy based filter. Ultimate aim of image restoration is to improve an image to a pre-defined sense. Face detection is a computer technology being used in a variety of applications that identifies human faces in digital images. Face detectors perform well when an image is in a perfect condition and that without any random noise. The goal of this research is to find out the impact of providing more training data to a convolutional neural network (CNN) based face detector. The face detector is constructed by the deep learning framework Caffe, and the AlexNet is the model used. The performance gain is increased when more training data is presented.