The demands and application of face recognition are growing quickly in recent years due to the development of advances technology. One of the most challenging tasks of face recognition is to be recognized the facial image with limited training samples (a few or single image per person). This real-world problem can be seen in access control, physical security and international border control. In order to provide a new benchmark facial dataset for this issue, the FACEID-550 dataset is constructed (the full dataset is available from: http://dx.doi.org/10.17632/zs2vnf9692.2). Itcontains total 11,550 color images (256 × 256 pixels) of 550 subjects. Each person has one ID photo and twenty daily (or selfie) photos.