A New Scheme for the Polynomial Based Biometric Cryptosystems

This paper presents a new scheme for the fuzzy vault based biometric cryptosystems which explore the feasibility of a polynomial based vault for the biometric traits like iris, palm, vein, and so forth. Gabor filter is used for the feature extraction from the biometric data and the extracted feature points are transformed into Eigen spaces using Karhunen Loeve (K-L) transform. A polynomial obtained from the secret key is used to generate projections from the transformed features and the randomly generated points, known as chaff points. The points and their corresponding projections form the ordered pairs. The union of the ordered pairs from the features and the chaff points creates a fuzzy vault. At the time of decoding, matching scores are computed by comparing the stored and the claimed biometric traits, which are further tested against a predefined threshold. The number of matched scores should be greater than a tolerance value for the successful decoding of the vault. The threshold and the tolerance value are learned from the transformed features at the encoding stage and chosen according to the tradeoff in the error rates. The proposed scheme is tested on a variety of biometric databases and error rates obtained from the experimental results confirm the utility of the new scheme.

Performance Evaluation of Noise Reduction Filters for Color Images through Normalized Color Difference (NCD) Decomposition

Removing noise without producing image distortion is the challenging goal for any image denoising filter. Thus, the different amounts of residual noise and unwanted blur should be evaluated to analyze the actual performance of a denoising process. In this paper a novel full-reference method for measuring such features in color images is presented. The proposed approach is based on the decomposition of the normalized color difference (NCD) into three components that separately take into account different classes of filtering errors such as the inaccuracy in filtering noise pulses, the inaccuracy in reducing Gaussian noise, and the amount of collateral distortion. Computer simulations show that the proposed method offers significant advantages over other measures of filtering performance in the literature, including the recently proposed vector techniques.

Novel Approach for Rooftop Detection Using Support Vector Machine

A new method for detecting rooftops in satellite images is presented. The proposed method is based on a combination of machine learning techniques, namely, k-means clustering and support vector machines (SVM). Firstly k-means clustering is used to segment the image into a set of rooftop candidates—these are homogeneous regions in the image which are potentially associated with rooftop areas. Next, the candidates are submitted to a classification stage which determines which amongst them correspond to “true” rooftops. To achieve improved accuracy, a novel two-pass classification process is used. In the first pass, a trained SVM is used in the normal way to distinguish between rooftop and nonrooftop regions. However, this can be a challenging task, resulting in a relatively high rate of misclassification. Hence, the second pass, which we call the “histogram method,” was devised with the aim of detecting rooftops which were missed in the first pass. The performance of the model is assessed both in terms of the percentage of correctly classified candidates as well as the accuracy of the estimated rooftop area.

A Robust Illumination Normalization Method Based on Mean Estimation for Face Recognition

An illumination normalization method for face recognition has been developed since it was difficult to control lighting conditions efficiently in the practical applications. Considering that the irradiation light is of little variation in a certain area, a mean estimation method is used to simulate the illumination component of a face image. Illumination component is removed by subtracting the mean estimation from the original image. In order to highlight face texture features and suppress the impact of adjacent domains, a ratio of the quotient image and its modulus mean value is obtained. The exponent result of the ratio is closely approximate to a relative reflection component. Since the gray value of facial organs is less than that of the facial skin, postprocessing is applied to the images in order to highlight facial texture for face recognition. Experiments show that the performance by using the proposed method is superior to that of state of the arts.

Resection-Intersection Bundle Adjustment Revisited

Bundle adjustment is one of the essential components of the computer vision toolbox. This paper revisits the resection-intersection approach, which has previously been shown to have inferior convergence properties. Modifications are proposed that greatly improve the performance of this method, resulting in a fast and accurate approach. Firstly, a linear triangulation step is added to the intersection stage, yielding higher accuracy and improved convergence rate. Secondly, the effect of parameter updates is tracked in order to reduce wasteful computation; only variables coupled to significantly changing variables are updated. This leads to significant improvements in computation time, at the cost of a small, controllable increase in error. Loop closures are handled effectively without the need for additional network modelling. The proposed approach is shown experimentally to yield comparable accuracy to a full sparse bundle adjustment (20% error increase) while computation time scales much better with the number of variables. Experiments on a progressive reconstruction system show the proposed method to be more efficient by a factor of 65 to 177, and 4.5 times more accurate (increasing over time) than a localised sparse bundle adjustment approach.

Active Object Recognition with a Space-Variant Retina

When independent component analysis (ICA) is applied to color natural images, the representation it learns has spatiochromatic properties similar to the responses of neurons in primary visual cortex. Existing models of ICA have only been applied to pixel patches. This does not take into account the space-variant nature of human vision. To address this, we use the space-variant log-polar transformation to acquire samples from color natural images, and then we apply ICA to the acquired samples. We analyze the spatiochromatic properties of the learned ICA filters. Qualitatively, the model matches the receptive field properties of neurons in primary visual cortex, including exhibiting the same opponent-color structure and a higher density of receptive fields in the foveal region compared to the periphery. We also adopt the “self-taught learning” paradigm from machine learning to assess the model’s efficacy at active object and face classification, and the model is competitive with the best approaches in computer vision.

Towards Understanding the Formation of Uniform Local Binary Patterns

The research reported in this paper focuses on the modeling of Local Binary Patterns (LBPs) and presents an a priori model where LBPs are considered as combinations of permutations. The aim is to increase the understanding of the mechanisms related to the formation of uniform LBPs. Uniform patterns are known to exhibit high discriminative capability; however, so far the reasons for this have not been fully explored. We report an observation that although the overall a priori probability of uniform LBPs is high, it is mostly due to the high probability of only certain classes of patterns, while the a priori probability of other patterns is very low. In order to examine this behavior, the relationship between the runs up and down test for randomness of permutations and the uniform LBPs was studied. Quantitative experiments were then carried out to show that the relative effect of uniform patterns to the LBP histogram is strengthened with deterministic data, in comparison with the i.i.d. model. This was verified by using an a priori model as well as through experiments with natural image data. It was further illustrated that specific uniform LBP codes can also provide responses to salient shapes, that is, to monotonically changing intensity functions and edges within the image microstructure.

Affine-Invariant Feature Extraction for Activity Recognition

We propose an innovative approach for human activity recognition based on affine-invariant shape representation and SVM-based feature classification. In this approach, a compact computationally efficient affine-invariant representation of action shapes is developed by using affine moment invariants. Dynamic affine invariants are derived from the 3D spatiotemporal action volume and the average image created from the 3D volume and classified by an SVM classifier. On two standard benchmark action datasets (KTH and Weizmann datasets), the approach yields promising results that compare favorably with those previously reported in the literature, while maintaining real-time performance.

Vision Measurement Scheme Using Single Camera Rotation

We propose vision measurement scheme for estimating the distance or size of the object in static scene, which requires single camera with 3-axis accelerometer sensor rotating around a fixed axis. First, we formulate the rotation matrix and translation vector from one coordinate system of the camera to another in terms of the rotation angle, which can be figured out from the readouts of the sensor. Second, with the camera calibration data and through coordinate system transformation, we propose a method for calculating the orientation and position of the rotation axis relative to camera coordinate system. Finally, given the rotation angle and the images of the object in static scene at two different positions, one before and the other after camera rotation, the 3D coordinate of the point on the object can be determined. Experimental results show the validity of our method.

Visible and Infrared Face Identification via Sparse Representation

We present a facial recognition technique based on facial sparse representation. A dictionary is learned from data, and patches extracted from a face are decomposed in a sparse manner onto this dictionary. We particularly focus on the design of dictionaries that play a crucial role in the final identification rates. Applied to various databases and modalities, we show that this approach gives interesting performances. We propose also a score fusion framework that allows quantifying the saliency classifiers outputs and merging them according to these saliencies.