This paper is a complete survey of different Convolutional neural network models and comparison among them in various real time image colorization challenges. Models discussed are ResNet50, InceptionV3, Xception, Inception-ResNet-V2 and NASNetLarge. We intend this paper to be useful to researchers and practitioners interested in real time image processing. We also implemented the Image colorization methodology by taking a pre-trained neural network model which is one among the above mentioned and this will convert the old black and white images into colored image by performing certain methodologies throughout the stages involved in it.