Posts

Image
First week Progress In the first week of my Google Summer of code Project , I accomplished the following tasks : Added the class which would implement the face alignment algorithm as described in the research paper http://www.cvfoundation.org/ openaccess/content_cvpr_2014/ papers/Kazemi_One_Millisecond_ Face_2014_CVPR_paper.pdf to the face module of opencv_contrib. Added basic functionality by implementing functions for proper loading of data and initialisation of the shape. With this I achieved the following results : The above images are taken from HELEN dataset which contains 194 landmarks for each face. The above image face shows the initial shape assigned to the face while training. Major problems that occurred : The face detector detects only the inner face . So some modifications had to be made so that initial shape is correctly assigned .
Post a Comment
Read more
Image
Google Summer of code Project (Organisation : OpenCV) Face alignment is a computer vision technology for identifying the geometric structure of human faces in digital images. Given the location and size of a face, it automatically determines the shape of the face components such as eyes and nose. The main aim of the project is an implementation of an excellent paper from this year's Computer Vision and Pattern Recognition Conference: One Millisecond Face Alignment with an Ensemble of Regression Trees by Vahid Kazemi and Josephine Sullivan All discussion regarding the project can be found at OpenCV face alignment slack channel: https://open-cv.slack.com/messages/C5HGCM4PR/ The complete timeline of the project can be found at: https://calendar.google.com/calendar/embed?src=2j9ih3ela4ulmg96evon8rhq8c%40group.calendar.g The complete code along with the commit history can be found at pull request :  https://github.com/opencv/opencv_contrib/pull/1199 T...
Post a Comment
Read more