The nude image identification with adaptive skin chromatic distribution matching scheme

Yung Ming Kuo, Jiann Shu Lee, Pau-Choo Chung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents a new nude image identification system. We propose an adaptive chroma-distribution matching scheme based on face detection to on-line determine the image's skin chromatic distribution such that it can tolerate the color deviation coming from special lighting without increasing false alarm. The object detection based on machine learning approach is used to locate the face region in the test image. According to the color information of face, the matched skin chromatic distribution is selected to detect the skin objects in the test image. The texture feature, namely coarseness, is used to acquire accurate skin segmentation. The low-level but reliable geometrical constraints and the mug shot exclusion procedure are employed to further examine the skin regions. Experimental results that the overall detection rate is 86.3% show our method can achieve satisfactory performance for detecting nude images under special lighting conditions.

Original languageEnglish
Title of host publicationICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings
DOIs
Publication statusPublished - 2010 Oct 25
Event2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010 - Chengdu, China
Duration: 2010 Apr 162010 Apr 18

Publication series

NameICCET 2010 - 2010 International Conference on Computer Engineering and Technology, Proceedings
Volume7

Other

Other2010 2nd International Conference on Computer Engineering and Technology, ICCET 2010
CountryChina
CityChengdu
Period10-04-1610-04-18

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'The nude image identification with adaptive skin chromatic distribution matching scheme'. Together they form a unique fingerprint.

Cite this