In-vivo differentiation of photo-aged epidermis skin by texture-based classification

Two sets of in vivo female cheek skin epidermis images were analyzed through gray level co-occurrence matrix (GLCM) and fast fourier transform (FFT). One set was derived from women in their 20s and the other from women more than 60 years of age. GLCM was used to evaluate the texture features of the regions of interest within the cheek epidermis, and texture classification was subsequently performed. During texture classification, 25 images (320×240 pixels) in each age set were randomly selected. Three texture features, i.e., energy, contrast, and correlation, were obtained from the skin images and analyzed at four orientations (0°, 45°,90°, and 135°), accompanied by different distances between two pixels. The textures of the different aging skins were characterized by FFT, which provides the dermatoglyph orientation index. The differences in the textures between the young and old skin samples can be well described by the FFT dermatoglyph orientation index. The texture features varied among the different aging skins, which provide a versatile platform for differentiating the statuses of aging skins.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  Paul P M van Zuijlen,et al.  Collagen morphology in human skin and scar tissue: no adaptations in response to mechanical loading at joints. , 2003, Burns : journal of the International Society for Burn Injuries.

[3]  Bhabatosh Chanda,et al.  CBIR using perception based texture and colour measures , 2004, ICPR 2004.

[4]  Kurt C. Lawrence,et al.  Discriminant analysis of dual-wavelength spectral images for classifying poultry carcasses , 2002 .

[5]  H. Murase,et al.  Effect of probability-distance based Markovian texture extraction on discrimination in biological imaging , 2008 .

[6]  Elio Ramos,et al.  Classification of leaf epidermis microphotographs using texture features , 2009, Ecol. Informatics.

[7]  Evangelos Kiossis,et al.  Examination of cyclic changes in bovine luteal echotexture using computer-assisted statistical pattern recognition techniques. , 2008, Animal reproduction science.

[8]  Riccardo Cicchi,et al.  Scoring of collagen organization in healthy and diseased human dermis by multiphoton microscopy , 2009, Journal of biophotonics.

[9]  Hui Li,et al.  Quantitative analysis on collagen morphology in aging skin based on multiphoton microscopy. , 2011, Journal of biomedical optics.

[10]  Guang-ming Xian,et al.  An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM , 2010, Expert Syst. Appl..

[11]  J. Bos,et al.  Dermal Organization in Scleroderma: The Fast Fourier Transform and the Laser Scatter Method Objectify Fibrosis in Nonlesional as well as Lesional Skin , 2000, Laboratory Investigation.

[12]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[13]  J. Macgregor,et al.  Image texture analysis: methods and comparisons , 2004 .

[14]  Ranjan Parekh,et al.  Skin Texture Recognition using Medical Diagnosis , 2010 .

[15]  Shuangmu Zhuo,et al.  Multiphoton laser scanning microscopy of localized scleroderma , 2009, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.