REAL-TIME EXPLICIT IMAGE FILTERING USING CONVOLUTIONAL NEURAL NETWORKS

Abstract

Image classification is a critical and significant research problem in computer vision applications such as facial expression classification, satellite image classification, and plant classification based on images. This project proposes the image classification model applied for identifying the display of daunting pictures on the internet. The proposed model uses Convolutional Neural Network (CNN) to identify these images and filter them through different blocks of the network so that they can be classified accurately. The model works on Tensor Flow a userfriendly platform, which provides different high leveled APIs (in Keras) which are used to build any basic model. It also permits us to add our libraries. The input data for the model are images we collected online through various resources. Our model will work as an extension to the web browser and will work on all websites when activated. The output of the proposed model is blurring the images and deactivating the links. This means that it will scan the entire web page and find all the daunting images present on that page. Then we will blur those images before they are loaded and the children could see them. Apart from it, we will also disable any clickable links present. This ensures protection from disturbing images and links to the children.