Research Topics


Environment Perception for Unmanned Vehicle: For unmanned vehicles, environment perception is a core component. We can use kinds of sensors to get environmental information around the vehicle, including image sensors, Lidar, ultrasonic radar, etc. We focus on how to deal with the information obtained from various kinds of sensors.

Our works:

  1. Lin Zhang, Junhao Huang, Xiyuan Li, and Lu Xiong, "Vision-based Parking-slot Detection: A DCNN-based Approach and A Large-scale Benchmark Dataset"IEEE Trans. Image Processing, to appear. (website and source code)

  2. Lin Zhang, Xiyuan Li, Junhao Huang, Ying Shen*, and Dongqing Wang, "Vision-based parking-slot detection: A benchmark and a learning-based approach", Symmetry, vol. 10, no. 3, pp. 64:1-18, 2018. (website and source code)

  3. Linshen Li, Lin Zhang*, Xiyuan Li, Xiao Liu, Ying Shen, and Lu Xiong, Vision-Based Parking-Slot Detection: A Benchmark and A Learning-Based Approach, in: Proc. ICME, pp. 649-654, 2017.


Perceptual image/video quality assessment: Perceptual IQA/VQA research aims to design computerized algorithms that can evaluate the quality of a given image or a video clip in consistency with the perception of human observers. In order to design high-accuracy IQA/VQA algorithms, knowledge about HVS usually should be carefully incorporated. According to the availability of the high-quality distortion free reference image/video, IQA/VQA can be categories to three types, full-reference, reduced-reference, and no-reference. We mainly focus on how to model human vision systems and how to make use of machine learning and pattern recognition theories to solve these issues.

Our works:

  1. Lijun Zhang, Lin Zhang*, and Lida Li, Illumination Quality Assessment for Face Images: A Benchmark and a Convolutional Neural Networks Based Model, in Proc. ICONIP, 2017. (website and source code)

  2. Lin Zhang, Lei Zhang, and Alan C. Bovik, "A feature-enriched completely blind image quality evaluator", IEEE Trans. Image Processing, vol. 24, no. 8, pp. 2579-2591, 2015. (website and source code)

  3. Lin Zhang, Ying Shen, and Hongyu Li, "VSI: A visual saliency induced index for perceptual image quality assessment", IEEE Trans. Image Processing, vol. 23, no. 10, pp. 4270-4281, 2014. (website and source code)

  4. Lin Zhang, Zhongyi Gu, Xiaoxu Liu, Hongyu Li, and Jianwei Lu, "Training quality-aware filters for no-reference image quality assessment", IEEE Multimedia Magazine, vol. 22, no. 4, pp. 67-75, 2014.

  5. Zhongyi Gu, Lin Zhang*, Xiaoxu Liu, Hongyu Li, and Jianwei Lu, Learning quality-aware filters for no-reference image quality assessment, in: Proc. ICME, 2014.

  6. Xueyabo Liu, Lin Zhang*, Hongyu Li, and Jianwei Lu, Integrating visual saliency information into objective quality assessment of tone-mapped images, in: Proc. ICIC, pp. 376-386, 2014.

  7. Lin Zhang, Zhongyi Gu, and Hongyu Li, SDSP: A novel saliency detection method by combining simple priors, in: Proc. ICIP, pp. 171-175, 2013. (website and source code)

  8. Zhongyi Gu, Lin Zhang*, and Hongyu Li, Learning a blind image quality index based on visual saliency guided sampling and Gabor filtering, in: Proc. ICIP, pp. 186-190, 2013. (website and source code)

  9. Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang, A comprehensive evaluation of full reference image quality assessment algorithms, in: Proc. ICIP, pp. 1477-1480, 2012. (website)

  10. Lin Zhang and Hongyu Li, SR-SIM: A fast and high performance IQA index based on spectral residual, in Proc. ICIP, pp. 1473-1476, 2012. (website and source code)

  11. Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang, FSIM: a feature similarity index for image quality assessment, IEEE Trans. Image Processing 20 (8) 2378-2386, 2011. (website and source code)

  12. Lin Zhang, Lei Zhang, and Xuanqin Mou, RFSIM: a feature based image quality assessment metric using Riesz transforms, in: Proc. ICIP, pp. 321-324, 2010. (website and source code)


2D images based biometrics: Biometrics is a discipline focusing on devising algorithms and systems that can authenticate a person's identity based on his behavioral or physiological characteristic. Existing biometric identifiers may include fingerprint, palmprint, finger-knuckle-print, face, iris, ear, gait, voice, hand vein etc. From the signal collection view, biometric technologies may be classified as normal lighting based systems, infrared systems, 3D systems, multi (hyper) -spectral systems. Among these technologies, 2D image signal based systems are the most popular ones. In this research, we lay our focus on developing new kinds of biometric technologies and novel high performance feature extraction and matching methods.

Our works:

  1. Lin Zhang, Zaixi Cheng, Ying Shen*, and Dongqing Wang, "Palmprint and Palmvein Recognition Based on DCNN and A New Large-Scale Contactless Palmvein Dataset", Symmetry, vol. 10, no. 4, pp. 78:1-15, 2018. (data website)

  2. Lin Zhang, Lida Li, Anqi Yang, Ying Shen, and Meng Yang, Towards contactless palmprint recognition: A novel device, a new benchmark, and a collaborative representation based identification approach",  Pattern Recognition, vol. 69, pp. 199-212, 2017. (website and source code)

  3. Lin Zhang, Qingjun Liang, Ying Shen, Meng Yang, and Feng Liu, Image set classification based on synthetic examples and reverse training, Neurocomputing, vol. 228, pp. 3-10, 2017.

  4. Qingjun Liang, Lin Zhang*, Hongyu Li, and Jianwei Lu, Image set classification based on synthetic examples and reverse training, in: Proc. ICIC, pp. 282-288, 2015.

  5. Qingjun Liang, Lin Zhang*, Hongyu Li, and Jianwei Lu, Palmprint recognition based on image sets, in: Proc. ICIC, pp. 305-315, 2015.

  6. Guangwei Gao, Jian Yang, Jianjun Qian, and Lin Zhang, Integration of multiple orientation and texture information for finger-knuckle-print verification, Neurocomputing, vol. 135, no. 7, pp. 180-191, 2014.

  7. Guangwei Gao, Lei Zhang, Jian Yang, Lin Zhang, and David Zhang, Reconstruction based Finger-Knuckle-Print verification with score level adaptive binary fusion, IEEE Trans. Image Processing, vol. 22, no. 12, pp. 5050-5062, 2013.

  8. Lin Zhang and Hongyu Li, Encoding local image patterns using Riesz transforms: With applications to palmprint and finger-knuckle-print recognition, Image and Vision Computing 30 (12) 1043-1051, 2012.

  9. Lin Zhang, Hongyu Li, and Junyu Niu, Fragile bits in palmprint recognition, IEEE Signal Processing Letters 19 (10) 663-666, 2012.

  10. Lin Zhang, Lei Zhang, David Zhang, and Zhenhua Guo, Phase congruency induced local features for finger-knuckle-print recognition, Pattern Recognition 45 (7) 2522-2531, 2012. (website)

  11. Lin Zhang, Lei Zhang, David Zhang, and Hailong Zhu, Ensemble of local and global information for finger-knuckle-print recognition, Pattern Recognition 44 (9) 1990-1998, 2011. (website)

  12. Jie Zhou, Lin Zhang, and Lei Zhang, New members in the biometrics family, Communications of the China Computer Federation 7 (5) 16-22, 2011. (in Chinese)

  13. Lin Zhang, Hongyu Li, and Ying Shen, A novel Riesz transforms based coding scheme for finger-knuckle-print recognition, in: Proc. ICHB, pp. 204-209, 2011.

  14. Lin Zhang, Lei Zhang, David Zhang, and Hailong Zhu, Online finger-knuckle-print verification for personal authentication, Pattern Recognition 43 (7) 2560-2571, 2010. (website)

  15. Meng Yang, Lei Zhang, Lin Zhang, and David Zhang, Monogenic binary pattern (MBP): a novel feature extraction and representation model for face recognition, in: Proc. ICPR, pp. 2680-2683, 2010.

  16. Lin Zhang, Lei Zhang, and David Zhang, MonogenicCode: A novel fast feature coding algorithm with applications to finger-knuckle-print recognition, in: Proc. ETCHB, 2010.

  17. Lin Zhang, Lei Zhang, and David Zhang, Finger-knuckle-print: a new biometric identifier, in: Proc. ICIP, pp. 1981-1984, 2009.

  18. Lin Zhang, Lei Zhang, and David Zhang, Finger-knuckle-print verification based on band-limited phase-only correlation, in: Proc. CAIP, pp. 141-148, 2009.


3D biometrics: in this field, researchers want to achieve the goal of personal identification or verification by matching their 3D range images. Usually, expression, missing data, occlusion etc are the potential challenges. Now the prevalent biometric identifiers used in 3D include face, ear, hand, palmprint, etc.

Our works:

  1. Lin Zhang, Lida Li, Hongyu Li, and Meng Yang, "3D ear identification using block-wise statistics based features and LC-KSVD", IEEE Trans. Multimedia, vol. 18, no. 8, pp. 1531-1541, 2016. (website and source code)

  2. Lin Zhang, Ying Shen, Hongyu Li, and Jianwei Lu, 3D palmprint identification using block-wise features and collaborative representation, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 37, no. 8, pp. 1730-1736, 2015. (website and source code)

  3. Lin Zhang, Zhixuan Ding, Hongyu Li, Ying Shen, and Jianwei Lu, 3D face recognition based on multiple keypoint descriptors and sparse representation, PLoS One, vol. 9, no. 6, pp. e100120:1-9, 2014. (website and source code)

  4. Lin Zhang, Zhixuan Ding, Hongyu Li, and Jianwei Lu, 3DMKDSRC: A novel approach for 3D face recognition, in: Proc. ICME, 2014.

  5. Lin Zhang, Zhixuan Ding, Hongyu Li, and Ying Shen, 3D ear identification based on sparse representation, PLoS One, vol. 9, no. 4, pp. e95506:1-9, 2014. (website and source code)

  6. Zhixuan Ding, Lin Zhang*, and Hongyu Li, A novel 3D ear identification approach based on sparse representation, in: Proc. ICIP, pp. 4166-4170, 2013.


Image retrieval and classification: in this research, we aim to propose efficient and effective image representation and classification methods. We also focus on extracting semantic features from images for specific applications, such as medical image analysis.

Our works:

1. Zhenhua Guo, Qin Li, Lin Zhang, Jane You, David Zhang, and Wenhuang Liu, Is local dominant orientation necessary for the classification of rotation invariant texture?, Neurocomputing 116 (9) 182-191, 2013.

2. Hongyi Li, Zhujing Wu, Lin Zhang*, and Jussi Parkkinen, SR-LLA: A novel spectral reconstruction method based on locally linear approximation, in: Proc. ICIP, pp. 2029-2033, 2013.

3. Guizi Li, Lin Zhang*, and Hongyu Li, Real-time visual tracking based on an appearance model and a motion mode, in: Proc. ICIC, pp. 533-540, 2013.

4. Weichao Fu, Lin Zhang*, Hongyu Li, Xinfeng Zhang, and Di Wu, Efficient 3D reconstruction for urban scenes, in: Proc. ICIC, pp. 546-555, 2013.

5. Lin Zhang, Zhiqiang Zhou and Hongyu Li, Binary Gabor pattern: an efficient and robust descriptor for texture classification, in: Proc. ICIP 2012.  (website and source code)

6. Hongyu Li, Junyu Niu, and Lin Zhang, Entropy based image semantic cycle for image classification, in: Proc. ICONIP, pp. 533-540, 2012.

7. Hongyu Li, Chen Lin, Junyu Niu, Lin Zhang, and Jussi Parkkinen, Manifold analysis of spectral munsell colors, in: Proc. ICONIP, pp. 543-550, 2012.

8. Hongyu Li, Junyu Niu, Lin Zhang, and Bo Hu, Spatio-temporal LTSA and its application to motion decomposition, in: Proc. ICONIP, pp. 498-505, 2012.

9. Yi Wang, Hongyu Li, Junyu Niu, and Lin Zhang, Local tangent space based manifold entropy for image retrieval, in: Proc. ICPR, pp. 262-265, 2012.

10. Zhenhua Guo, Qin Li, Lin Zhang, Jane You, Wenhuang Liu, and Jinghua Wang, Texture image classification using complex texton, in: Proc. ICIC, pp. 98-104, 2011.

11. Lin Zhang, Lei Zhang, Zhenhua Guo, and David Zhang, Monogenic-LBP: a new approach for rotation invariant texture classification, in: Proc. ICIP, pp. 2677-2680, 2010. (website and source code)

12. Bob Zhang, Lin Zhang, Lei Zhang and Fakhri Karray, Retinal vessel extraction by matched filter with first-order derivative of Gaussian, Computers in Biology and Medicine 40 (4) 438-445, 2010.

13. Lin Zhang, Lei Zhang, and David Zhang, A multi-scale bilateral structure tensor based corner detector, in: Proc. ACCV, pp. 618-627, 2009.


Bioinformatics: in this research, we aim to make use of pattern recognition, machine learning, and geometric methods to solve problems in biology.

Our works:

  1. Ying Shen and Lin Zhang*, Gene function prediction with knowledge from Gene Ontology, Int. J. Data Mining and Bioinformatics 13 (1) 50-62, 2015.

  2. Huizhu Ren, Ying Shen, and Lin Zhang, The -turn: A new structural motif in ribosomal RNA, in: Proc. ICIC, pp. 456-466, 2015.

  3. Ying Shen, Shaohong Zhang, Hau-San Wong, and Lin Zhang, Characterization of semantic similarity on Gene Ontology based on a shortest path approach, International Journal of Data Mining and Bioinformatics 10 (1) 33-48, 2014. (website and source code)

  4. Ying Shen, Hausan Wong, Shaohong Zhang, and Lin Zhang, RNA structural motif recognition based on least-squares distance, RNA 19 (9) 1183-1191, 2013.

  5. Ying Shen and Lin Zhang*, Improving classification accuracy using Gene Ontology information, in: Proc. ICIC, pp. 171-176, 2013.


Created on: May 06, 2012

Last updated on: Jul. 16, 2018