Showing papers by "Nalini K. Ratha published in 2012"

Matching cross-resolution face images using co-transfer learning

Abstract: Face recognition systems, trained in controlled environment, often fail to efficiently match low resolution images with high resolution images. In this research, a co-transfer learning framework is proposed in which knowledge learnt in controlled high resolution environment is transferred for matching low resolution probe images with high resolution gallery. The proposed framework seamlessly combines transfer learning and co-training to perform knowledge transfer by updating classifier's decision boundary with low resolution probe instances. Experiments are performed on the CMU-Multi-PIE and SCface database with gallery images of size 72 × 72 and size of probe images varying from 48 × 48 to 16 × 16. The results show that, in terms of rank-1 identification accuracy, the proposed algorithm outperforms existing approaches by at least 5%.

Fusing biographical and biometric classifiers for improved person identification

Abstract: Several citizen service databases such as, police, national citizen identity, passport and vehicle registration, store both biographical and biometric information containing huge number of records Achieving scalability and high accuracy for a 1:N person identification task on these databases is a huge challenge In this work, we propose to use complementary information present in the biographical data along with biometric information of a user to improve 1:N person identification task for large systems We show that a likelihood ratio based method for score level fusion of the biometric and biographical classifiers results in high accuracy identification as compared to using only the biometric classifiers or the biographical classifiers

Unique Cardiovascular Measurements for Human Identification

Abstract: A method, an apparatus and an article of manufacture for generating a cardiovascular measurement for individual identification. The method includes acquiring at least one depiction of cardiac anatomy from an individual, extracting at least one quantified representation of cardiac anatomy from the at least one depiction, defining at least one comparison technique between the at least one quantified representation of cardiac anatomy and at least one additional quantified representation of cardiac anatomy, and identifying the individual based on the at least one defined comparison technique.

Cardiac anatomy as a biometric

Abstract: In this study, we propose a novel biometric signature for human identification based on anatomically unique structures of the left ventricle of the heart. An algorithm is developed that analyzes the 3 primary anatomical structures of the left ventricle: the endocardium, myocardium, and papillary muscles. Comparisons of these analyses between probe and gallery images produces a similarity score that is used as the basis of the biometric. The performance of the algorithm is tested on a cohort of 10 de-identified subjects imaged by Cardiac MRI. Perfect matching between individuals is obtained with good separation between the genuine and impostor classes. In summary, this study demonstrates using anatomy of the left ventricle of the human heart for the purposes of a biometric signature.

Vision-based integrated systems for intelligent data analysis

Abstract: It is becoming increasingly clear that it is humanly impossible to analyze a deluge of data from cameras and other sensors in a variety of applications including surveillance, railroad inspection, driver assistance. The practical systems that we built, although in pursuit of different business objectives, share a common goal, which is to intelligently and efficiently analyze and extract the most important actionable information from an overwhelming amount of data, while being able to effectively ignore a large portions of uneventful and/or noisy data. This presentation will focus on computer vision, machine learning and system optimization techniques that we used to successfully address different technical and business challenges, and to deliver differentiating performance to meet our customers' expectations.