Color based skin classification

Abstract

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection, (2) the role of the illuminance component of a color space, (3) the appropriate pixel based skin color modeling technique and finally, (4) the effect of color constancy algorithms on color based skin classification. The comprehensive color space and skin color modeling evaluation will help in the selection of the best combinations for skin detection. Nine skin modeling approaches (AdaBoost, Bayesian network, J48, Multilayer Perceptron, Naive Bayesian, Random Forest, RBF network, SVM and the histogram approach of Jones and Rehg [15]) in six color spaces (IHLS, HSI, RGB, normalized RGB, YCbCr and CIELAB) with the presence or absence of the illuminance component are compared and evaluated. Moreover, the impact of five color constancy algorithms on skin detection is reported. Results on a database of 8991 images with manually annotated pixel-level ground truth show that (1) the cylindrical color spaces outperform other color spaces, (2) the absence of the illuminance component decreases performance, (3) the selection of an appropriate skin color modeling approach is important and that the tree based classifiers (Random forest, J48) are well suited to pixel based skin detection. As a best combination, the Random Forest combined with the cylindrical color spaces, while keeping the illumi- nance component outperforms other combinations, and (4) the usage of color constancy algorithms can improve skin detection performance.

Model Warna HSCbCrAB untuk Deteksi Kulit Menggunakan PCA-kNN

“…[8] dan [9] menggunakan RGB dan YCbCr, sedangkan [10] hanya menggunakan YCbCr karena ruang warna ini memberikan hasil yang terbaik untuk warna kulit manusia. Berbeda dengan yang dilakukan oleh [11] yang menggunakan IHLS, HSI, RGB, nRGB, YCbCr, dan CIELAB yang kemudian mengeleminasi komponen luminan: L pada IHLS, I pada HSI, G pada RGB, nG pada nRGB, Y pada YCbCr, dan L pada CIELAB. Dengan melakukan perbandingan untuk setiap ruang warna terhadap RGB diperoleh bahwa CIELAB merupakan yang terbaik, yang diikuti oleh IHLS, HSI, YCbCr, dan nRGB.…”

“…Metode ini dipilih karena k-Means sangat sederhana. HSV, YCbCr, dan CIELAB dipilih karena memberikan hasil yang terbaik berdasarkan [11], dan dalam paper ini kami mengajukan model warna baru dengan menghilangkan komponen luminannya (HSCbCrAB).…”

Self-adaptive algorithm for segmenting skin regions

“…There have been a handful of methods proposed [10,11] that combine model adaptivity with spatial analysis. These techniques require a skin sample for the adaptation, delivered by a face detector, and they do not exploit textural features.…”

A Parametric Discriminative Approach for Skin color Detection by Training Weak Learners on Normalized Chrominance and Luminance

“…This paper deals with the first two of these problems. Skin color distribution can be modeled primarily by many ways such as histogram models [2], single/Gaussian mixture models [3], and table look-up methods [4]. Many of these techniques are not effective when the illumination conditions vary rapidly and for the whole range of skin tones from fair to deep color tone.…”