Dynamic approach for real-time skin detection

Abstract

Human face and hand detection, recognition and tracking are important research areas for many computer interaction applications. Face and hand are considered as human skin blobs, which fall in a compact region of colour spaces. Limitations arise from the fact that human skin has common properties and can be defined in various colour spaces after applying colour normalization. The model therefore, has to accept a wide range of colours, making it more susceptible to noise. We have addressed this problem and propose that the skin colour could be defined separately for every person. This is expected to reduce the errors. To detect human skin colour pixels and to decrease the number of false alarms, a prior face or hand detection model has been developed using Haar-like and AdaBoost technique. To decrease the cost of computational time, a fast search algorithm for skin detection is proposed. The level of performance reached in terms of detection accuracy and processing time allows this approach to be an adequate choice for real-time skin blob tracking.

An investigation into the variability of skin colour measurements

“…The colour of skin is probably one of the colours that we see most in our daily lives, and it plays an important role in many multidisciplinary applications. Apart from the reproduction of skin colour in general amateur and professional photography, cinematography and printing, these include the photography of skin for medical recording and diagnosis and the potential manufacture of prosthetics, skin colour based faced detection for computer vision applications, the identification of the skin colour preference for applications in, for example, the cosmetics industries and, more recently, skin colour reproduction in 3D printing . For all these applications, a reliable technique to quantify the colour of skin objectively, in all its many variations, is of vital importance.…”

Self-adaptive algorithm for segmenting skin regions

“…Skin models can also be effectively adapted given a skin sample, acquired based on tracking skin-like objects in video sequences [33], or relying on face [11,34] or hand [3] detection. For such a skin sample, a local model can be generated using the Bayesian classifier [35,36] or GMMs [37] as they do not require time-consuming training.…”

“…Alternatively, a skin sample may be used to optimize the value of the acceptance thresholds [3,39]. Recently, Yogarajah et al [40] proposed to use skin samples for adapting the acceptance thresholds in a singledimensional error signal space (ESS) [14].…”

“…In case of the positive answer, skin segmentation is applied to determine the exact boundaries of the detected skin regions. Applications of skin detection and segmentation are of a wide range and significance, and they include gesture recognition for human-computer interaction [3], objectionable content filtering [4], content-based image retrieval [5], medical imaging [6,7], and image coding [8].…”

Gloved Finger Recognition by Curve Matching

“…Obviously, this method is not only inconvenient in application, but also is easily interfered by ambient light. Similarly, much literature shows that skin colors are used to position palms and recognize fingers [4]. Because of drastic changes of skin colors among different races and the influence of luminous environment on camera imaging, the finger recognition method based on skin colors has a poor recognition effect in many situations.…”