Assessing facial wrinkles: automatic detection and quantification.

BACKGROUND: As people mature, their skin gradually presents lines, wrinkles, and folds that become more pronounced with time. Skin wrinkles are perceived as important cues in communicating information about the age of the person. Nowadays, documenting the facial appearance through imaging is prevalent in skin research, therefore detection and quantitative assessment of the degree of facial wrinkling can be a useful tool for establishing an objective baseline and for assessing benefits to facial appearance due to various dermatological treatments. However, few image-based algorithms for computationally assessing facial wrinkles are present in the literature, and those that exist have limited reliability. METHODS: In this work, an algorithm for automatic detection of facial wrinkles is developed, based on estimating the orientation and the frequency of elongated spatial features, captured via digital image filtering. RESULTS: The algorithm is tested against one set of clinically validated 11-point wrinkle scales present on the face. The algorithm is employed for assessing the presence of forehead furrows on a set of 100 clinically graded facial images. The proposed computational assessment correlates well with the corresponding clinical scores. CONCLUSION: We find that the results are in better agreement with clinical scoring when the wrinkle depth information, approximated via filter responses, is combined with the wrinkle length information as opposed to the case when the two measures are considered separately.

Measurement of skin texture through polarization imaging.

BACKGROUND: Determination of skin surface texture is of particular importance in the field of dermatology as such measurements can be used for skin diagnostics and evaluation of therapeutic or cosmetic treatments. Profilometry of skin replicas, three-dimensional imaging and computer vision have been successfully used to measure and document skin texture. Nevertheless, the development of a simpler and faster technique may prove to be advantageous in a clinical setting. OBJECTIVES: We propose the use of polarization imaging with high angles of incidence as a simple alternative to measure/document skin texture/roughness. METHODS: A system based on digital photography and polarization optics was developed to acquire and compute texture images. Optimization of the system configuration was conducted to enhance the contrast for measuring skin roughness. The method was validated against roughness standards and tested in clinical studies. Measurements were made in subjects aged from 9 to 70 years and image analysis was used to evaluate texture. RESULTS: The developed texture scale was shown to correlate closely to the results from clinical assessment and from roughness standards. Frequency domain analysis showed a significantly different power spectrum for the texture images of young subjects when compared with older subjects. The evaluation of texture as a function of age showed that facial skin roughness increased linearly from teenage to 40 years followed by a plateau thereafter. CONCLUSIONS: The system proved to be a useful clinical tool for assessing skin texture. The age-related results may indicate that some skin texture features are formed before the age of 40 years.

In vivo determination of optical properties of normal and tumor tissue with white light reflectance and an empirical light transport model during endoscopy.

Determination of tissue optical properties is fundamental for application of light in either therapeutical or diagnostics procedures. In the present work we implemented a spatially resolved steady-state diffuse reflectance method where only two fibers (one source and one detector) spaced 2.5 mm apart are used for the determination of the optical properties. The method relies on the spectral characteristics of the tissue chromophores (water, dry tissue, and blood) and the assumption of a simple wavelength dependent expression for the determination of the reduced scattering coefficient. Because of the probe dimensions the method is suited for endoscopic measurements. The method was validated against more traditional models, such as the diffusion theory combined with adding doubling for in vitro measurements of bovine muscle. Mean and standard deviation of the absorption coefficient and the reduced scattering coefficient at 630 nm for normal mucosa were 0.87+/-0.22 cm(-1) and 7.8+/-2.3 cm(-1), respectively. Cancerous mucosa had values 1.87+/-1.10 cm(-1) and 8.4+/-2.3 cm(-1), respectively. These values are similar to data presented by other authors. Blood perfusion was the main variable accounting for differences in the absorption coefficient between the studied tissues.