1. Overview
The WebTattoo dataset was built based on Images from Internet, which contains about 300K tattoo images which are supposed to be the distracter background images in large-scale tattoo retrieval tasks. We additionally provided the tattoo bounding boxes for the tattoo images from the public-domain flickr [6] and demsi [7] datasets. We also provided 300 tattoo sketches with their mated tattoo photos for sketch-based tattoo retrieval task. The figure below gives a few examples of the tattoos and tattoo sketches.
2. Evaluation Protocol For tattoo localization task, we recommend using FPPI-Recall and mAP to evaluate the performance. For tattoo retrieval and sketch-based tattoo retrieval tasks, we recommend using the PR curve to evaluate the performance.
3. Contact
Hu Han (hanhu@ict.ac.cn), Jie Li (jie.li@vipl.ict.ac.cn), Institute of Computing Technology, Chinese Academy of Sciences
4. Download
The WebTattoo dataset is released to universities and research institutes for research purpose only. To request a copy of the WebTattoo database (including the URLs of the Internet tattoo images, the sketches and annotations), please follow the instructions below:
•Download
the WebTattoo Database License Agreement, read it carefully, and complete it appropriately. Note that the agreement should be signed by a full-time staff member (that is, student is not acceptable). Then, please scan the signed agreement and send it to Dr. Han (hanhu@ict.ac.cn) using an official email address (that is, university or institute email address, and non-official email addresses such as Gmail and 163 may not be accepted). When we receive your reply, we would provide a download link to you.
• By using the WebTattoo database, you are recommended to cite the following paper:
H. Han, J. Li, A. K. Jain, S. Shan and X. Chen, "Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning, " in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 10, pp. 2333-2348, Oct. 2019.
References
1. Mei Ngan and Patrick Grother. Tattoo Recognition Technology - Challenge (Tatt-C): An Open Tattoo Database for Developing Tattoo Recognition Research. In International Conference on Identity, Security and Behavior Analysis (ISBA), pp.1-6, 2015.
2.Tatt-E-https://www.nist.gov/programs-projects/tattoo-recognition-technology-evaluation-tatt-e
3. X. Di and V. M. Patel, “Deep tattoo recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop, Jun. 2016, 1100 pp. 119–126.
4. X. Xu and A. Kong, “A geometric-based tattoo retrieval system,” in Proc. 23rd Int. Conf. Pattern Recognit., Dec. 2016, pp. 3019–3024.
5. H. Han and A. K. Jain. Tattoo Based Identification: Sketch to Image Matching. in Proc.6th IAPR International Conference on Biometrics (ICB), pp. 1-8, Madrid, Spain, Jun. 4-7, 2013.
6. Ghosh S . Tattoo Detection based on CNN and Remarks on the NIST Database. in Proc.6th IAPR International Conference on Biometrics (ICB)
7. Tomislav Hrkać, Karla Brkić, Zoran Kalafatić. Tattoo Detection for Soft Biometric De-identification Based on Convolutional Neural Networks. Oagm-arw Joint Workshop-vision Meets Robotics. 2016.