Smart Content Recognition from Images Using a Mixture of Convolutional Neural Networks

TL;DR

This paper introduces a novel approach for adult content recognition in images using a mixture of convolutional neural networks, which improves accuracy over single models by combining multiple CNNs with learned weights.

Contribution

The paper presents a new method that combines multiple CNNs with a linear regression-based weighting scheme for enhanced content recognition accuracy.

Findings

The mixture model outperforms single CNN models.

The weighted sum approach improves recognition accuracy.

Experimental results validate the effectiveness of the proposed method.

Abstract

With rapid development of the Internet, web contents become huge. Most of the websites are publicly available, and anyone can access the contents from anywhere such as workplace, home and even schools. Nevertheless, not all the web contents are appropriate for all users, especially children. An example of these contents is pornography images which should be restricted to certain age group. Besides, these images are not safe for work (NSFW) in which employees should not be seen accessing such contents during work. Recently, convolutional neural networks have been successfully applied to many computer vision problems. Inspired by these successes, we propose a mixture of convolutional neural networks for adult content recognition. Unlike other works, our method is formulated on a weighted sum of multiple deep neural network models. The weights of each CNN models are expressed as a linear regression problem learned using Ordinary Least Squares (OLS). Experimental results demonstrate that the proposed model outperforms both single CNN model and the average sum of CNN models in adult content recognition.