Detection of Facial Wrinkle based on Improved Maximum Curvature Points in Image Profiles
Die Zhou, Shuo Zhao
Available Online April 2019.
- https://doi.org/10.2991/icmeit-19.2019.135How to use a DOI?
- wrinkle detection; Gabor filter bank; Frangi filter; maximum curvature.
- Face wrinkles, as an important sign of aging and the focus of anti-aging, have great research significance in detecting them. However, rough skin result in more noises, and the intensity difference between the fine wrinkles and the skin background is too small, which ultimately leads to low detection rate of wrinkles. An improved maximum curvature method is proposed for wrinkle detection. Firstly, the intensity gradient caused by wrinkles is highlighted by combining the image features of Gabor filter bank and Frangi filter. Then, the filtered result image is binarized, and the connected component eccentricity distribution is counted to judge the wrinkle feature extraction effect. According to the effect of wrinkle feature extraction, the image is selected, and the local maximum curvature of the cross-sectional contour is calculated to detect wrinkles. At the same time, combined with the complex geometric features of wrinkles, the connection method in the algorithm is improved. Compared with the existing wrinkle detection methods, the proposed method greatly improves the detection rate of wrinkles, especially in rough skin images.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Die Zhou AU - Shuo Zhao PY - 2019/04 DA - 2019/04 TI - Detection of Facial Wrinkle based on Improved Maximum Curvature Points in Image Profiles PB - Atlantis Press SP - 843 EP - 848 SN - 2352-538X UR - https://doi.org/10.2991/icmeit-19.2019.135 DO - https://doi.org/10.2991/icmeit-19.2019.135 ID - Zhou2019/04 ER -