Convolutional Neural Networks Based Pornographic Image Classification
Authors:
- 18 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 206-209
Abstract
Considering the fact that pornographic images are flooding on the web, we propose a pornographic image recognition method based on convolutional neural network. This method can be divided into two parts: coarse detection and fine detection. Because majority of images are normal, we use coarse detecting to quickly identify the normal images with no or fewer skin-color regions and facial images. For the images which contain much more skin-color regions, they need further identification through fine detecting. At first, we trained the CNN using the strategy of pre-training mid-level features non-fixed fine-tuning, then based on the trained model, we can classify whether the image is pornographic or not. Compared with exiting methods, performance of our method is better than the state-of-the-art.Keywords
This publication has 10 references indexed in Scilit:
- A comparative study of local feature extraction algorithms for Web pornographic image recognition2015
- Research on pornographic images recognition method based on visual words in a compressed domainIET Image Processing, 2012
- Big Skin Regions Detection for Adult Image Identification2011
- Adult Image Detection Using Bayesian Decision Rule Weighted by SVM Probability2009
- Pornographic Images Detection Based on CBIR and Skin Analysis2008
- An adult image identification system employing image retrieval techniquePattern Recognition Letters, 2007
- An algorithm of pornographic image detection2007
- A Pyramidal Neural Network For Visual Pattern RecognitionIEEE Transactions on Neural Networks, 2007
- Rapid object detection using a boosted cascade of simple features2005
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004