Bhagavatula Vijaya Kumar

BIOMETRIC ENCRYPTION USING IMAGE PROCESSING

Biometric EncryptionTM is an algorithm which has been developed to securely link and retrieve a digital key using the interaction of a biometric image, such as a fingerprint, with a secure block of data, known as a BioscryptTM. The key can be used, for example, as an encryption/decryption key. The BioscryptTM comprises a filter function, which is calculated using an image processing algorithm, and other information which is required to first retrieve, and then verify the validity of, the key. The key is retrieved using information from an output pattern formed via the interaction of the biometric image with the filter function. Therefore, the filter function must be designed so that it produces a consistent output pattern (and thus, key). The filter function must also be designed to be secure (i.e. information about the fingerprint cannot be retrieved from the filter function). The consistency of the output pattern and the security of the filter function are the two topics discussed in this paper.

Simultaneous super-resolution and feature extraction for recognition of low-resolution faces

Face recognition degrades when faces are of very low resolution since many details about the difference between one person and another can only be captured in images of sufficient resolution. In this work, we propose a new procedure for recognition of low-resolution faces, when there is a high-resolution training set available. Most previous super-resolution approaches are aimed at reconstruction, with recognition only as an after-thought. In contrast, in the proposed method, face features, as they would be extracted for a face recognition algorithm (e.g., eigenfaces, Fisher-faces, etc.), are included in a super-resolution method as prior information. This approach simultaneously provides measures of fit of the super-resolution result, from both reconstruction and recognition perspectives. This is different from the conventional paradigms of matching in a low-resolution domain, or, alternatively, applying a super-resolution algorithm to a low-resolution face and then classifying the super-resolution result. We show, for example, that recognition of faces of as low as 6 times 6 pixel size is considerably improved compared to matching using a super-resolution reconstruction followed by classification, and to matching with a low-resolution training set.

Correlation Pattern Recognition for Face Recognition

Two-dimensional (2-D) face recognition (FR) is of interest in many verification (1:1 matching) and identification (1:N matching) applications because of its nonintrusive nature and because digital cameras are becoming ubiquitous. However, the performance of 2-D FR systems can be degraded by natural factors such as expressions, illuminations, pose, and aging. Several FR algorithms have been proposed to deal with the resulting appearance variability. However, most of these methods employ features derived in the image or the space domain whereas there are benefits to working in the spatial frequency domain (i.e., the 2-D Fourier transforms of the images). These benefits include shift-invariance, graceful degradation, and closed-form solutions. We discuss the use of spatial frequency domain methods (also known as correlation filters or correlation pattern recognition) for FR and illustrate the advantages. However, correlation filters can be computationally demanding due to the need for computing 2-D Fourier transforms and may not match well for large-scale FR problems such as in the Face Recognition Grand Challenge (FRGC) phase-II experiments that require the computation of millions of similarity metrics. We will discuss a new method [called the class-dependence feature analysis (CFA)] that reduces the computational complexity of correlation pattern recognition and show the results of applying CFA to the FRGC phase-II data

Eigenphases vs eigenfaces

In this paper, we present a novel method for performing robust illumination-tolerant and partial face recognition that is based on modeling the phase spectrum of face images. We perform principal component analysis in the frequency domain on the phase spectrum of the face images and we show that this improves the recognition performance in the presence of illumination variations dramatically compared to normal eigenface method and other competing face recognition methods such as the illumination subspace method and fisherfaces. We show that this method is robustly even when presented with partial views of the test faces, without performing any pre-processing and without needing any a-priori knowledge of the type or part of face that is occluded or missing. We show comparative results using the illumination subset of CMU-PIE database consisting of 65 people showing the performance gain of our proposed method using a variety of training scenarios using as little as three training images per person. We also present partial face recognition results that obtained by synthetically blocking parts of the face of the test faces (even though training was performed on the full face images) showing gain in recognition accuracy of our proposed method.

Biometric Encryption: enrollment and verification procedures

Biometric EncryptionTM is an algorithm which has been developed to securely link and retrieve a digital key using the interaction of a biometric image, such as a fingerprint, with a secure block of data, known as a BioscryptTM. The key can be used, for example, as an encryption/decryption key. The Bioscrypt comprises a stored filter function, produced by a correlation-based image processing algorithm, as well as other information which is required to first retrieve, and then verify the validity of, the key. The process of securely linking a key with a biometric is known as enrollment, while the process of retrieving this key is known as verification. This paper presents details of the enrollment and verification procedures.

Low complexity LDPC codes for partial response channels

This paper constructs and analyzes a class of regular LDPC codes with column weight of j=2, in contrast to the often-used j/spl ges/3 setting. These codes possess several significant features. First, they are free of 6-cycle, and can be easily constructed for a large range of code rates. Secondly, the parity check matrix of the code can be represented by a simple set, thus lending itself to a low complexity implementation. Thirdly, the proposed codes concatenated with proper precoder outperform j/spl ges/3 LDPC codes for partial response (PR) channels. Finally, they exhibit block error statistics significantly different from LDPC codes with j/spl ges/3, making them more compatible with Reed-Solomon error correction codes. The LDPC coded partial response (PR) channel is formulated as a dynamical model and analyzed using density evolution technique, which is used to explain the behavior of the concatenated system. A high rate (8/9) code with block size 4608 is constructed as an example, and its bit error rate (BER), block error statistics, and decoding convergence over ideal PR channel are investigated using simulation. The simulation results are consistent with the density evolution analysis, both indicating that LDPC codes with j=2 are attractive for partial response channels. PR targets for magnetic recording channel are used as examples to illustrate the performance of the proposed codes.

Redundant Class-Dependence Feature Analysis Based on Correlation Filters Using FRGC2.0 Data

In this paper we propose a new method called redundant class-dependence feature analysis (CFA) based on the advanced correlation filters to perform robust face recognition on the Face Recognition Grand Challenge (FRGC) data set. The FRGC contains a large corpus of data and a set of challenge problems. The data is divided into training and validation partitions, with the standard still-image training partition consisting of 12,800 images, and the validation partition consisting of 16,028 controlled still images, 8,014 uncontrolled stills, and 4,007 3D scans. We have tested the proposed CFA method and compared it with the PCA and LDA methods in a recognition scenario on the FRGC2.0 data. The preliminary results show that the CFA outperforms the other two compared methods in our experiments. We also show the improved performance of the CFA method on the FRGC experiments #1 and #4.

Large girth cycle codes for partial response channels

In this paper, we present a general approach for constructing high-rate cycle codes having girth 12 which achieve the lower bound on the block length. An efficient encoding algorithm is also proposed for this class of codes. We estimate the word error rate of the cycle codes for additive white Gaussian noise (AWGN) channels under maximum likelihood decoding, using the minimum distance and its multiplicity. These estimates are compared to simulation results with iterative soft decoding. The performance of these codes for partial response channels is studied under iterative soft decoding using computer simulations.

Iterative decoding for partial response (PR), equalized, magneto-optical (MO) data storage channels

Turbo codes and low-density parity check (LDPC) codes with iterative decoding have received significant research attention because of their remarkable near-capacity performance for additive white Gaussian noise (AWGN) channels. Previously, turbo code and LDPC code variants are being investigated as potential candidates for high-density magnetic recording channels suffering from low signal-to-noise ratios (SNR). We address the application of turbo codes and LDPC codes to magneto-optical (MO) recording channels. Our results focus on a variety of practical MO storage channel aspects, including storage density, partial response targets, the type of precoder used, and mark edge jitter. Instead of focusing just on bit error rates (BER), we also study the block error statistics. Our results for MO storage channels indicate that turbo codes of rate 16/17 can achieve coding gains of 3-5 dB over partial response maximum likelihood (PRML) methods for a 10/sup -4/ target BER. Simulations also show that the performance of LDPC codes for MO channels is comparable to that of turbo codes, while requiring less computational complexity. Both LDPC codes and turbo codes with iterative decoding are seen to be robust to mark edge jitter.

Minimum squared error synthetic discriminant functions

A new synthetic discriminant function (SDF) design approach is presented that yields the best approximation of arbitrary output correlation shapes in the minimum squared error (MSE) sense. We term such filters as MSE-SDFs. Simulation results are presented to illustrate the advantages of MSE-SDFs. Also, we show that MSE-SDFs generalize minimum average correlation energy filters.