Pornographic image region detection based on visual attention model in compressed domain

• Published in: IET image processing Vol. 7; no. 4; pp. 384 - 391
• Main Authors: Zhang, Jing, Sui, Lei, Zhuo, Li, Li, Zhenwei
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.06.2013; Institution of Engineering and Technology; The Institution of Engineering & Technology
• Subjects: Applied sciences; biological attention mechanism; Color; Colour; Compressed; compressed domain; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; human visual system; image coding; image colour analysis; Image detection; image intensity; image representation; image segmentation; image texture; Information, signal and communications theory; object detection; Pattern recognition; pornographic image region detection; pornographic regions representation; Pornography; region of interest detection; ROI detection; Signal and communications theory; Signal processing; Signal, noise; skin colour regions; Surface layer; Telecommunications and information theory; Texture; threshold segmentation method; torso information; Visual; visual attention model; visual saliency map; human visual system; ROI detection; biological attention mechanism; skin colour regions; object detection; image texture; threshold segmentation method; pornographic image region detection; visual attention model; image segmentation; torso information; image intensity; pornographic regions representation; image representation; region of interest detection; visual saliency map; image colour analysis; image coding; compressed domain; Interest region; Accuracy; Segmentation; Pattern recognition; Visual saliency; Image sensor; Visual attention; Texture; Signal detection; Image method
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/iet-ipr.2012.0381

According to biological attention mechanism, a region of interest (ROI) detection based on visual attention model is closer to human visual system. Taken into account the characteristics of pornographic image during regions detection, a pornographic image region detection method based on visual attention model in compressed domain is proposed in this study, which includes the following four steps: (i) the skin colour regions of pornographic images are detected in compressed domain; (ii) visual saliency map in compressed domain is computed to construct visual attention model; (iii) threshold segmentation method is used for visual saliency map, and then the torso information is retained as pornographic regions; and (iv) four features of colour, texture, intensity and skin are extracted to represent pornographic region. The experimental results show that the proposed method can perform well on the speed/accuracy of pornographic regions detection and representation.