Open charliecaffe opened 4 years ago
@X-zhangyang
Self-built-masked-face-recognition-dataset, lfw_masked and CASIA-WebFace_masked datasets have labels, and the rest dataset needs manual labeling.
Excuse me, I still can't find the labels of Self-built-masked-face-recognition-dataset. I downloaded Real-world masked face recognition dataset from https://drive.google.com/open?id=1UlOk6EtiaXTHylRUx2mySgvJX9ycoeBp. It seems that the zipped package contains 2 file dir: AFDB_masked_face_dataset (525 objects)and AFDB_face_dataset(460 objects). I wonder whether I should download RFMD_part_1, RFMD_part_2 (4 compressed files) and RFMD_part_3 (3 compressed files) completely if I ONLY use the Self-built-masked-face-recognition-dataset. @X-zhangyang
Our suggestion is to download and use the corresponding datasets according to the needs.
I still can't find the face landmark labels of Self-built-masked-face-recognition-dataset, can you show them to me? @X-zhangyang
In our Self-built-masked-face-recognition-dataset, each file name is a label. Our task only needs this labels.
@Chanyou-Xu @X-zhangyang I have checked the python code in wear mask file. For the face detection model, two choices are available in your code including 'hog' and 'cnn'. Could you please tell me which reference paper is the hog detection model used here from?
@wencoast May I ask have you installed the code yet? I need help!
I downloaded Real-world masked face recognition dataset from https://drive.google.com/open?id=1UlOk6EtiaXTHylRUx2mySgvJX9ycoeBp. However, I can't find the annotation labels of the face dataset. So I tried some regular face detection method such as MTCNN, dlib to dectect face and align face. But there are many wrong or missed detection probably due to the mask. I wonder what kind of face detector you used to detect and align face with Real-world masked face recognition dataset. Thanks in advance.