Smart phone-based fuzzy modeling to examine facial skin quality

Grooming made a good impression on the people. To accompany the demand of applying right cosmetics on face, multitudes of skin detectors emerged. Though small-scale skin detectors are easy to carry due to their lightweight and easy to use they need to contact the face by the metal part of the detector while examining. As photographic enhancements of the smart phones, taking and acquiring digital images become easier. Thus, this study uses smart phones to take facial skin images. Then, we can calculate the texture features, including contrast, entropy and inverse difference moment through gray level co-occurrence matrix. Finally, vertical, horizontal and diagonal texture features on the original gray image are found by Haar wavelet transform. After defining the six texture features of input and output membership functions of the skin types, the skin quality characteristics are inferred by the proposed fuzzy models. In order to reduce the computing time, we use principal component analysis method to discriminate texture features. The purpose is to examine the skin types with fewer features. With the six texture features from fuzzy inference results as a reference value, both the results from the principal component analysis and gray level co-occurrence matrix methods achieve the accuracy rates of 96.29% and 93.21%, respectively. These results verify that the proposed smart phone-based fuzzy models are effective for facial skin quality examination.