Skin detection using spatial analysis with adaptive seed
- 1 September 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 3720-3724
Abstract
This paper introduces a new method for adaptive skin detection in color images combined with spatial analysis of skin pixels. It has been reported in many works that adaptation of a skin color model to a particular image may decrease the false positives, however the false negatives are considerably high unless a local model is combined with the global one. Another possibility for improvement is to analyze spatial properties of the pixels classified as skin, but this operation strongly depends on the seed extraction technique. Our contribution lies in using a local dynamic skin model learned from the detected faces to extract seeds for the spatial analysis. We present an extensive experimental study confirming that our method outperforms alternative skin detection techniques.Keywords
This publication has 24 references indexed in Scilit:
- Dynamic approach for real-time skin detectionJournal of Real-Time Image Processing, 2012
- Systematic skin segmentation: merging spatial and non-spatial dataMultimedia Tools and Applications, 2012
- A dynamic threshold approach for skin segmentation in color images2010
- Skin detection for single images using dynamic skin color modelingPattern Recognition, 2009
- Naked image detection based on adaptive and extensible skin color modelPattern Recognition, 2007
- A survey of skin-color modeling and detection methodsPattern Recognition, 2007
- An adaptive real-time skin detector based on Hue thresholding: A comparison on two motion tracking methodsPattern Recognition Letters, 2006
- Improving adaptive skin color segmentation by incorporating results from face detection2003
- Adaptive skin segmentation in color images2003
- Skin detection in video under changing illumination conditions2002