Age Group Estimation from Face Images

• Main Author: Tiong, Pei Kee
• Format: Final Year Project / Dissertation / Thesis
• Published: 2015
• Subjects: TA Engineering (General). Civil engineering (General); TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utar.edu.my/1809/1/Age_Group_Estimation_from_Face_Images.pdf; http://eprints.utar.edu.my/1809/

Age group estimation is useful in real-world applications such as security access control and human computer interaction. We have proposed an age group estimation algorithm based on the wrinkle features on the face image. During pre-processing stage, geometric normalization is performed to correct the out-of-plane rotated images. Then, conversion of image to grayscale image is performed, if needed; followed by noise removal using median filtering method. Wrinkle features are extracted from the regions of interest of a normalized image using Canny edge detection for age group estimation. Finally, the images are classified into three age groups: babies/ children, young adults and old adults. The average accuracy of the algorithm is 72.66% for good quality images and 44.92% for poor quality images.