The obfuscation algorithm covers a minimum explicitly nude area of 0.68 on average.Ĭontent-based image retrieval (CBIR) retrieves visually similar images from aĭataset based on a specified query. The classification network achieves a top-1 accuracy of 0.903 and a top-2 accuracy of 0.986. This obfuscation algorithm presents a novel-use case of class-specific activation mappings for censoring regional explicit nudity in images.

Our automatic obfuscation algorithm uses the information obtained from the classification network and does not require additional annotation or supplementary training. Our classification network is trained with automatically labelled data using noise-robust techniques. Our proposed solution is a cost-efficient in terms of human labour and practical for deploying the real-time systems. Our solution consists of two main parts: the first part classifies a given image into granular content classes and a second part obfuscates the part of a given image that might be inappropriate for the target audience. In this research work, we propose an automatic content moderation pipeline based on deep neural networks. Automating content moderation is a scalable solution for social media platforms. Therefore, human-reviewed content moderation is not achievable in such volume. Millions of users produce and consume billions of content on social media.