Purpose: Wrinkles are the most visually obvious features of aging and are\nthe prime target of a vast number of products (both medical and cosmetic).\nIt is important for clinicians to be able to grade wrinkles objectively. Although\nwrinkles are easily recognisable for humans, it remains a very challenging\ntask for computer vision systems to detect them automatically. In\nour center, we developed a wrinkle detection algorithm based on a technique\ncalled ââ?¬Å?reversible jump Markov chain Monte Carlo framework with\ndelayed rejectionââ?¬Â. This system is able to accurately and rapidly detect wrinkles.\nMethods: 300 images were submitted to the analyser for reading. Each\nimage was analysed with a million iterations in ten minutes. The same 300\nimages were sent to a dermatologist for post-analyser evaluation. The system\nwas trained to detect major and minor wrinkles. The results were\nbenchmarked against the reviewing dermatologist. Results: Out of 300 patients,\nthe pickup rate for major wrinkles was 100%. However, on average it\nwould be able to trace out only approximately 56.5% of the entire length of\nthe wrinkle. The analyser was also able to detect minor wrinkles. However,\nthe detection rate was only 13.4%. Conclusion: Our system is able to accurately\ndetect all major wrinkles. This enables physicians to track progress of\nantiwrinkling techniques such as Botox or surgical facelifts. Our system is\nalso low cost as the wrinkle detection can be simply based off simple photographs.
Loading....