ABSTRACT
We present a novel algorithm for discriminating pornographic and assorted benign images, each categorized into semantic subclasses. The algorithm exploits connectedness and coherence properties in skin image regions in order to capture alarming Regions of Interest (ROIs). The technique to identify ROIs in an image employs a region-splitting scheme, in which the image plane is recursively partitioned into quadrants. Splitting is achieved by considering both the accumulation of skin pixels and texture coherence. This processing step is proven to significantly boost the accuracy and reduction of running time demands, even in the presence of sparse noise due to errors attributed to skin segmentation. For detected ROIs, we extract 15 rough color and spatial features computed from the pixels residing in the ROI. A novel classification scheme based on a tree-structured ensemble of strong Random Forest classifiers is also proposed. The method achieves competitive performance both in terms of response time and accuracy when compared to the state-of-the-art.
- L. Breiman. Random forests. Machine learning, 45(1):5--32, 2001. Google ScholarDigital Library
- M. Fleck, D. Forsyth, and C. Bregler. Finding naked people. In Proc. ECCV, pages 593--602, 1996. Google ScholarDigital Library
- M. Hu. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, 8(2):179--187, 1962.Google ScholarCross Ref
- S. Karavarsamis, N. Ntarmos, and K. Blekas. InFeRno-an intelligent framework for recognizing pornographic web pages. In Proc. ECML PKDD, pages 638--641, 2011. Google ScholarDigital Library
- A. Materka and M. Strzelecki. Texture analysis methods-a review. Technical report, Tech. Univ. of Lodz, Inst. of Electronics, 1998.Google Scholar
- POESIA project. http://www.poesia-filter.org/.Google Scholar
- J. Quinlan. C4.5: Programs for machine learning. Morgan kaufmann, 1993. Google ScholarDigital Library
- Y. Shi, J. Yang, and R. Wu. Reducing illumination based on nonlinear gamma correction. In Proc. IEEE ICIP, volume 1, pages 529--532, 2007.Google ScholarCross Ref
- V. Vezhnevets, V. Sazonov, and A. Andreeva. A survey on pixel-based skin color detection techniques. In Proc. Graphicon, volume 3, 2003.Google Scholar
- J. Wang, J. Li, G. Wiederhold, and O. Firschein. Classifying objectionable websites based on image content. In Proc. IDMS, pages 113--124, 1998. Google ScholarDigital Library
- J. Wang, G. Wiederhold, and O. Firschein. System for screening objectionable images using Daubechies' wavelets and color histograms. In Proc. IDMS, pages 20--30, 1997. Google ScholarDigital Library
- J. Yang, Y. Shi, and M. Xiao. Geometric feature-based skin image classification. In Proc. ICIC, pages 1158--1169, 2007. Google ScholarDigital Library
Index Terms
- Recognizing pornographic images
Recommendations
Fast and Effectively Identify Pornographic Images
CIS '11: Proceedings of the 2011 Seventh International Conference on Computational Intelligence and SecurityIn this paper, we present a practical solution to identifying pornographic images based on multiple low-level image features and support vector machine (SVM). First, the region of interest (ROI) is obtained from an original image based on the detection ...
Automatic region of interest generation for kidney ultrasound images
ACS'11: Proceedings of the 11th WSEAS international conference on Applied computer scienceUltrasound scanning of the kidney is performed to assess kidney size, shape and location as well as to detect any abnormalities in kidney like cysts and stones. Since ultrasound image contains speckle noise, performing the segmentation methods for the ...
Scale- and rotation-invariant texture description with improved local binary pattern features
Local Binary Pattern (LBP) is an effective image descriptor based on joint distribution of signed gray level differences. Simplicity, discriminative power, computational efficiency and robustness to illumination changes are main properties of LBP. ...
Comments