Side effects of laser-assisted hair removal can be minimized by directing the laser beam only to the detected hair regions. We propose a feature based hair region localization method by using machine learning techniques. Features with low computational complexity have been defined in order to discriminate hair and skin regions. Hair and skin region classification performances of different machine learning techniques have been tested and compared. Test results obtained from the proposed technique showed success in the detection of hair and skin regions. It has been evaluated that the proposed method can be used in real-time laser hair removal devices with a low computational complexity.

• The general system of guided laser epilation is seen here.
  
  Small spot-sized computer-assisted laser hair removal system.
  
  
• A sample of the training dataset is as follows.
  
  
  Sample hair(red boxes) and skin(blue boxes) region selections.
  
  
• Finally localized hair with the proposed automated methods.
  
  
  
  (a) Input image, results obtained for (b) LDA linear, (c) LDA quadratic, (e) SVM,
  (d) Decision Trees, (e) Naive Bayes, (f) 10-NN classification.
  
  
• We also evaluate the automated localization methods using quantitative metrics.
  
  
  Performance results obtained from different pattern classification techniques.
  
  
• References:
  1. M. Avsar, I. S. Yetik, "Automated Feature Based Hair Region Localization for Laser Hair Removal with Optical Imaging", IEEE EMBC 2014.
  2. M. Avsar, I. S. Yetik, "Hair Region Localization with Optical Imaging for Guided Laser Hair Removal", IEEE ISBI 2015.