Detecting Illicit Drug Abuse for Improved Face Recognition
Illicit drug abuse has become one of the primary health and social concerns in today’s world. The problem of illicit drug abuse is becoming more apparent, considering that 1 out of 10 drug users is a problem drug user, who is suffering from drug dependence. Illicit drug abuse and its detection has applications in health and medical areas as well as in face recognition. In this research, we demonstrate the impact of facial variations caused due to illicit drug abuse on face recognition. We also propose a non-invasive classification algorithm using dictionary learning to detect face images affected due to illicit drug abuse such that it can be used in conjunction with current face recognition systems.
- D. Yadav, N. Kohli, P. Pandey, R. Singh, M. Vatsa, A. Noore, “Effect of Illicit Drug Abuse on Face Recognition”, IEEE Winter Conference on Applications of Computer Vision, 2016. (Received Best Paper Award)
Recognizing Faces Altered by Plastic Surgery
Researchers have shown that the changes in face features due to plastic surgery can be modeled as a covariate that reduces the ability of algorithms to recognize a person's identity. We propose a novel solution to discriminate plastic surgery faces from regular faces by learning representations of local and global plastic surgery faces using multiple projective dictionaries and by using compact binary face descriptors.
- N. Kohli, D. Yadav, and A. Noore. “Multiple Projective Dictionary Learning to Detect Plastic Surgery for Face Verification,” IEEE Access, Vol.3, pp. 2572-2580, 2015.
- H.S. Bhatt, S. Bharadwaj, R. Singh M. Vatsa, and A. Noore, "Evolutionary Granular Computing Approach for Recognizing Face Images Altered due to Plastic Surgery", Proc. IEEE International Conference on Face and Gesture Recognition, pp. 720-725, 2011.
- R. Singh, M. Vatsa, H.S. Bhatt, S. Bharadwaj, A. Noore, and S.S. Nooreyezdan, "Plastic Surgery: A New Dimension to Face Recognition", IEEE Trans. on Information Forensics and Security, vol. 5, no. 3, pp. 441 – 448, 2010.
- R. Singh, M. Vatsa, and A. Noore, "Effect of Plastic Surgery on Face Recognition: A Preliminary Study", Proc. IEEE Computer Society Workshop on Biometrics at Computer Vision and Pattern Recognition Conference, pp. 72-77, 2009.
Kinship Verification using Faces
Kinship verification has a number of applications such as organizing large collections of images and recognizing resemblances among humans. A hierarchical Kinship Verification via Representation Learning (KVRL) framework is utilized to learn the representation of different face regions in an unsupervised manner. We propose a novel approach for feature representation termed as filtered contractive deep belief networks (fcDBN). The proposed feature representation encodes relational information present in images using filters and contractive regularization penalty. A compact representation of facial images of kin is extracted as an output from the learned model and a multi-layer neural network is utilized to verify the kin accurately.
- N. Kohli, M. Vatsa, R. Singh, A. Noore, and A. Majumdar, “Hierarchical Representation Learning for Kinship Verification,” IEEE Transactions on Image Processing, vol. 26, no. 1, pp. 289-302, 2017.
Detecting Medley of Iris Spoofing Attacks
Iris is one of the most reliable and accurate biometric modalities due to the highly unique character of iris tissue structure. It has been used successfully in numerous applications including national ID projects and border security. The success of large scale identity applications using iris recognition, in turn, means there are now individuals who can gain advantage by defeating these applications to gain unauthorized access to locations or resources or to escape recognition as an individual of interest. In real-world scenarios, iris recognition systems have to handle and detect various types of spoofing attacks including fake/printed iris images, synthetic images, and textured contact lenses. This research presents a novel framework utilizing structural and textural features to detect multiple complex spoofing attacks.
- N. Kohli, D. Yadav, M. Vatsa, R. Singh, A. Noore, “Detecting Medley of Iris Spoofing Attacks using DESIST”, Proc. IEEE International Conference on Biometrics: Theory, Applications and Systems, pp. 1-6, 2016.
Biometrics based CAPTCHA for Improved Security
CAPTCHAs (Completely Automated Public Turing Test to tell Computers and Humans Apart) have been a common tool for preventing unauthorized access to websites for over a decade. However, increasingly sophisticated optical character recognition algorithms and attack strategies have rendered traditional CAPTCHAs insecure. In this research, we have designed a new CAPTCHA incorporating biometric information such as face detection and face recognition. The proposed CAPTCHA is language independent and easy to solve by humans but difficult to attack by automated algorithms.
- B.M. Powell, A. Gupta, J. Thapar, G. Goswami, R. Singh, M. Vatsa, A. Noore, “A Multibiometrics-based CAPTCHA for Improved Online Security”, Proc. IEEE International Conference on Biometrics: Theory, Applications and Systems, pp. 1-6, 2016.
- B.M. Powell, G. Goswami, M. Vatsa, R. Singh, and A. Noore, "fgCAPTCHA: Genetically Optimized Face Images CAPTCHA", IEEE Access, vol. 2, pp. 473-484, 2014.
- G. Goswami, B.M. Powell, M. Vatsa, R. Singh, and A. Noore, "FR-CAPTCHA: CAPTCHA based on Recognizing Human Faces", PLoS ONE, vol. 9, no. 4, e91708, 2014.
- G. Goswami, B.M. Powell, M. Vatsa, R. Singh, and A. Noore, "FaceDCAPTCHA: Face Detection based Color Image CAPTCHA", Future Generation Computer Systems - Special Issue on Human-Involved Computational Systems, Elsevier, vol. 31, pp. 59-68, 2014.