Our research areas include Computer Vision and Pattern Recognition/Machine Learning. Currently, we focus on three main research topics including intelligent imaging, object recognition (segmentation, detection, tracking, classification, and search), and person recognition (face, fingerprint, palmprint).

3D Reconstruction including structure-from-motion using multiple images, stereo vision on two PTZ camera system and slide tracking, feature descriptor design and feature matching.

3D Reconstruction

(1) Xianwei Xu, Lu Tian, Jianjiang Feng, and Jie Zhou. OSRI: A Robust Local Binary Descriptor. IEEE Trans. on Image Processing, Vol.23(7), pp. 2983-2995, 2014

(2) Tian L, Xu X, Zhou J. Image matching for repetitive patterns[C]//Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. IEEE, 2015: 1488-1492.

(3) Jie Zhou, Dingrui Wan and Ying Wu. The Chameleon-like Vision System. IEEE Signal Processing Magazine, Vol.27(5), pp.91-101, 2010

(4) Dingrui Wan and Jie Zhou. Multi-resolution and wide-scope depth estimation using a dual-PTZ-camera system. IEEE Trans. On Image Processing, Vol.18(3), pp.677-682, 2009.

(5) Dingrui Wan and Jie Zhou. Stereo vision using two PTZ cameras. Computer Vision and Image Understanding. Vol.112, pp.184–194, Nov. 2008

Visual analysis aims to automatically analyze and understand the contents of image and videos, which is usually considered as a high-level computer vision task. ' In our group, we mainly study six visual analysis tasks including visual object segmentation, detection, matching, tracking, recognition and search. Generally, some machine learning techniques such as feature learning, metric learning, hashing learning, deep learning and multi-view learning are employed to learn useful knowledge to better analyze and understand the visual contents from images and videos.

Object Recognition

(1) AnranWang, Jiwen Lu, Jianfei Cai, Gang Wang, and Tat Jen Cham, “Unsupervised joint feature learning and encoding for RGB-D scene labeling,” IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 4459-4473, 2015.

(2) Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, and Jie Zhou, “Multimanifold deep metric learning for image set classification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), Boston, Jun., 2015

Object Tracking

(1) Lin Ma, Jiwen Lu, Jianjiang Feng, and Jie Zhou, “Multiple feature fusion via weighted entropy for visual tracking,” IEEE International Conference on Computer Vision (ICCV'15), Santiago, Dec., 2015.

(2) Lin Ma, Xiaoqin Zhang, Weiming Hu, Junliang Xing, Jiwen Lu, and Jie Zhou, “Local subspace collaborated tracking,” IEEE International Conference on Computer Vision (ICCV'15), Santiago, Dec., 2015

(3) Xiuzhuang Zhou, Yao Lu, Jiwen Lu, and Jie Zhou, “Abrupt motion tracking via intensively adaptive markov-chain monte carlo sampling,” IEEE Transactions on Image Processing, vol. 21, no. 2, pp. 789-801, 2012

Object Search

(1) Kevin Lin, Jiwen Lu, Chu-Song Chen, and Jie Zhou, “Learning compact binary descriptors with unsupervised deep neural networks,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), Las Vegas, Jun., 2016.

(2) Xianglong Liu, Lei Huang, Cheng Deng, Jiwen Lu, and Bo Lang, “Multi-view complementary hash tables for nearest neighbor search,” IEEE International Conference on Computer Vision (ICCV'15), Santiago, Dec., 2015.

(3) Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, and Jie Zhou, “Deep hashing for compact binary codes learning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), Boston, Jun., 2015.

Person recognition automatically recognizes human identities and/or attributes information via their physiological or behavioral characteristics. In our group, we mainly investigate person recognition techniques with four different biometrics modalities: face, body, fingerprint and palmprint. Generally, some image processing and statistical learning techniques such as feature learning, metric learning, hashing learning, deep learning and multi-view learning are utilized to help better recognize people from images and videos.

Face Recognition

(1) Jiwen Lu, Venice Erin Liong, Xiuzhuang Zhou, and Jie Zhou, “Learning compact binary face descriptor for face recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 10, pp. 2041-2256, 2015.

(2) Jiwen Lu, Xiuzhuang Zhou, Yap-Peng Tan, Yuanyuan Shang, and Jie Zhou, “Neighborhood repulsed metric learning for kinship verification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 2, pp. 331-345, 2014.

(3) Jiwen Lu, Venice Erin Liong, and Jie Zhou, “Cost-sensitive local binary feature learning for facial age estimation,” IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5356-5368, 2015.

(4) Jiwen Lu, Xiuzhuang Zhou, Yap-Peng Tan, Yuanyuan Shang, and Jie Zhou, “Cost-sensitive semi-supervised discriminant analysis for face recognition,” IEEE Transactions on Information Forensics and Security, vol. 7, no. 2, pp. 944-953, 2012.

(5) Jiwen Lu, Venice Erin Liong, and Jie Zhou, “Simultaneous local binary feature learning and encoding for face recognition,” IEEE International Conference on Computer Vision (ICCV'15), Santiago, Dec., 2015.

Fingerprint and Palmprint Analysis

(1) Feng, Jianjiang, Jie Zhou, and Yijing SU. "METHOD AND SYSTEM FOR ESTIMATING FINGERPRINT POSE." U.S. Patent No. 20,150,347,804. 3 Dec. 2015.

(2) Yang, Xiao, et al. "Detection and segmentation of latent fingerprints." Information Forensics and Security (WIFS), 2015 IEEE International Workshop on. IEEE, 2015.

(3) Si, Xuanbin, et al. "Detection and Rectification of Distorted Fingerprints." Pattern Analysis and Machine Intelligence, IEEE Transactions on 37.3 (2015): 555-568.

(4) Yang, Xiao, Jianjiang Feng, and Jie Zhou. "Localized dictionaries based orientation field estimation for latent fingerprints." Pattern Analysis and Machine Intelligence, IEEE Transactions on 36.5 (2014): 955-969.

(5) Luo, Yuxuan, Jianjiang Feng, and Jie Zhou. "Fingerprint matching based on global minutia cylinder code." Biometrics (IJCB), 2014 IEEE International Joint Conference on. IEEE, 2014.

Etsy mixtape wayfarers, ethical wes anderson tofu before they sold out mcsweeney's organic lomo retro fanny pack lo-fi farm-to-table readymade. Messenger bag gentrify pitchfork tattooed craft beer, iphone skateboard locavore carles etsy salvia banksy hoodie helvetica. DIY synth PBR banksy irony. Leggings gentrify squid 8-bit cred pitchfork.

Trust fund seitan letterpress, keytar raw denim keffiyeh etsy art party before they sold out master cleanse gluten-free squid scenester freegan cosby sweater. Fanny pack portland seitan DIY, art party locavore wolf cliche high life echo park Austin. Cred vinyl keffiyeh DIY salvia PBR, banh mi before they sold out farm-to-table VHS viral locavore cosby sweater.