Cartoonify Realistic Images and Videos Using OPENCV

Abstract— Nowadays we keep Online Status consistently, share photographs and remarks. To have a pleasant profile we can utilize our own photograph in a profile picture, make an entertaining symbol or transform your photograph into an animation. Therefore this paper representing the technique of converting realistic images and videos into cartoon. The objective of this study is to explore possibility of applying the application of a Generative Adversarial Network (GAN) with using two loss functions, content loss and adversarial loss for getting a sharp and clear image and converting realistic images and videos into cartoonized version with the help of K- means clustering. This article has conducted a comparative study on the performance of models created using deep learning based generative model architecture and K-means clustering. This system also evaluates those parameters on both algorithms. The histogram functionality are processed in python programming language using Convolution block and clustering.