No abstract

No abstract

One emerging subject in medical image processing is to quantitatively assess the health and the properties of cranial hairs, including density, diameter, length, level of oiliness, and others. This information helps hair specialists with making a more accurate diagnosis and the therapy required. Unfortunately, present hair care and scalp diagnosis systems lack both robustness and efficiency. Hair counting is usually done manually, producing results that are often unreliable. To solve this problem, we developed a practical hair counting algorithm. This analytic system calculates the number of hairs on a scalp using an unsupervised mechanism, providing accurate information for both the hair specialist and the patient. Our proposed hair counting algorithm is substantially more accurate than the Hough-based one, and is robust to curls, oily scalp, noisecorruption, and overlapping hairs, under various levels of illumination.

When human beings enjoy the prosperity of the city, it is difficult to escape the ubiquitous light pollution. In order to develop a widely applicable metric to determine the level of light pollution risk, the article establishes a light pollution risk level identification model. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is adopted for comprehensive evaluation of 4 types of light pollution. In order to improve the weight assignment process of TOPSIS, the entropy weight method (EWM) is used. Finally, the article conducts K-Means clustering algorithm to grade the risk level of different locations. The proportion of regions of high risk, medium risk and low risk are 28.57%, 42.86% and 28.57% respectively.