Alex Mathew

Local Histogram Based Descriptor for Tracking in Wide Area Imagery

In this paper we propose a novel feature extraction technique and show its application in tracking in low resolution videos. The aspects that make tracking particularly challenging are global camera motion, large target movement, poor gradient and texture information and absence of color information. Global camera motion is reduced or eliminated by registering the images from frame to frame employing SURF (Speeded Up Robust Feature). The proposed method is based on intensity histogram, but with a variant that encodes both spatial and intensity information. The method is evaluated on CLIF (Columbus Large Image Format) data. The robustness of the feature eliminates the need for background subtraction in videos. A performance comparison of our approach with other object descriptors such as HOG (Histogram of Gradients), SURF and SIFT (Scale Invariant Feature Transform) shows the effectiveness of the proposed descriptor.

Local Difference of Gaussian Binary Pattern: Robust Features for Face Sketch Recognition

Automatic recognition of face sketches is a challenging problem with application in criminal investigations. We propose a method that allows face sketch recognition across modalities called Local Difference of Gaussian Binary Pattern (LDoGBP). LDoGBP is based on the fact that the sketches are similar to their corresponding photos even though they are prone to shape distoration. This similarity between sketch and photo is captured and used for recognition across modalities. In this method, the face image characteristics are captured in the Difference of Gaussian (DoG) representation of the image patches. The Local Binary Pattern(LBP) corresponding to the DoG representation is then generated. These histograms are concatenated to generate the feature vector corresponding to input image. These feature vectors are compared using Earth Movers Distance for recognition. Experiments on the CUFS(Chinese University of Hong Kong (CUHK) Face Sketch Database) and CUFSF (CUHK Face Sketch FERET Database) datesets prove the effectiveness of this feature in Face Sketch Recognition.

Local region statistical distance measure for tracking in Wide Area Motion Imagery

In this paper we propose a novel tracking method in Wide Area Motion Imagery (WAMI) data based on local region histogram feature and a statistical distance measure. The aspects that make tracking particularly challenging are global camera motion, large movement of targets, poor gradient and texture information and absence of color information. Global camera motion is reduced or eliminated by registering the images from frame to frame employing SURF (Speeded Up Robust Feature). The proposed method is based on a variant of intensity histogram that encodes both spatial and intensity information. The method is evaluated on aerial WAMI data. The robustness of the feature eliminates the need for background subtraction in videos. A performance comparison of our feature descriptor with other descriptors such as HOG (Histogram of Gradients), SURF and SIFT (Scale Invariant Feature Transform) shows the effectiveness of the proposed method. We also show a comparison of our method with mean-shift tracking to show its effectiveness in tracking on WAMI data.

Local Alignment of Gradient Features for Face Sketch Recognition

Automatic recognition of face sketches is a challenging problem. It has application in forensics. An artist drawn sketch based on the descriptions from the witnesses can be used as the test image to recognize a person from the photo database of suspects. In this paper, we propose a novel method for face sketch recognition. We use the edge features of a face sketch and face photo image to create a feature string called ’edge-string’. The edge-strings of the face photo and face sketch are then compared using the Smith-Waterman algorithm for local alignments. The results on CUHK (Chinese University of Hong Kong) student dataset show the effectiveness of the proposed approach in face sketch recognition.

Rotation-invariant Histogram Features for Threat Object Detection on Pipeline Right-of-Way

We present a novel algorithm that automatically detects anomalies in pipeline right of the way (ROW) regions in aerial surveillance videos. Early detection of anomalies on pipeline ROWs avoids failures or leaks. Vehicles that are potential threats vary in size, shape and color. The detection algorithm should be fast to enable detection in real-time. In this paper, we propose a rotation-invariant gradient histogram based descriptor built in CIELab color space. An SVM with radial basis kernel is used as the classifier. We use only the a and b components since they represent the color values. The region of interest is divided into concentric circular regions. The number of such concentric regions is based on the size of the target. The inner regions capture the local characteristics and finer details of the image. Larger regions capture the global characteristics. A noise reducing differentiation kernel is used to compute the gradient of the region to cope with motion blur and noise introduced by atmospheric aberrations. A gradient orientation histogram is constructed in each region by voting the magnitude of gradients. The final descriptor is build by concatenating the magnitude of DFT of orientation histograms collected from a component and b components. The magnitude of Discrete Fourier Transform (DFT) of the histogram is invariant to rotations. DFT can be efficiently computed as Fast Fourier Transfrom (FFT). Since the algorithm uses a sliding window detector, it can easily be parallelized.

Tracking small targets in wide area motion imagery data

Object tracking in aerial imagery is of immense interest to the wide area surveillance community. In this paper, we propose a method to track very small targets such as pedestrians in AFRL Columbus Large Image Format (CLIF) Wide Area Motion Imagery (WAMI) data. Extremely small target sizes, combined with low frame rates and significant view changes, make tracking a very challenging task in WAMI data. Two problems should be tackled for object tracking frame registration and feature extraction. We employ SURF for frame registration. Although there are several feature extraction methods that work reasonably well when the scene is of high resolution, most methods fail when the resolution is very low. In our approach, we represent the target as a collection of intensity histograms and use a robust statistical distance to distinguish between the target and the background. We divide the object into m ×n regions and compute the normalized intensity histogram in each region to build a histogram matrix. The features can be compared using the histogram comparison techniques. For tracking, we use a combination of a bearing-only Kalman filter and the proposed feature extraction technique. The problem of template drift is solved by further localizing the target with a blob detection algorithm. The new template is taken as the detected blob. We show the robustness of the algorithm by giving a comparison of feature extraction part of our method with other feature extraction methods like SURF, SIFT and HoG and tracking part with mean-shift tracking.

Neighborhood dependent approximation by nonlinear embedding for face recognition

Variations in pose, illumination and expression in faces make face recognition a difficult problem. Several researchers have shown that faces of the same individual, despite all these variations, lie on a complex manifold in a higher dimensional space. Several methods have been proposed to exploit this fact to build better recognition systems, but have not succeeded to a satisfactory extent. We propose a new method to model this higher dimensional manifold with available data, and use a reconstruction technique to approximate unavailable data points. The proposed method is tested on Sheffield (previously UMIST) database, Extended Yale Face database B and AT&T (previously ORL) database of faces. Our method outperforms other manifold based methods such as Nearest Manifold and other methods such as PCA, LDA Modular PCA, Generalized 2D PCA and super-resolution method for face recognition using nonlinear mappings on coherent features.

A Linear Manifold Representation for Color Correction in Digital Images

Images captured using a camera loses its dynamic range of colors as they are digitized. This problem is not encountered by the human visual system as it supports a wider dynamic range. Our enhancement model is based on the human visual system involving three processing steps-color characterization, color enhancement and color correction. Each pixel in an image, along with its neighborhood forms color manifolds in RGB space. In the proposed color characterization method, these manifolds are modeled as lines. In the color enhancement step, a hyperbolic tangent function compresses the dynamic range of the image. This nonlinear function enhances the image preserving its details, but not the color relationships. Each enhanced pixel is projected to a point on the best fit line corresponding to its manifold to restore the original color relationships. Being a single-step convergence algorithm, it is faster than other iterative methods.

A manifold based methodology for color constancy

In this paper, we propose a manifold-based methodology for color constancy. It is observed that the center surround information of an image creates a manifold in color space. The relationship between the points in the manifold is modeled as a line. The human visual system is capable of learning these relationships. This is the basis of color constancy. In illumination correction, the image in the reference illumination is operated on with a wide Gaussian function to extract the global illumination information. The global illumination information creates a manifold in color space which is learnt by the system as a line. An image in a different color perception creates a different manifold in color space. To transform the color perception of a scene in a given illumination to the reference color perception, the color relationships in the reference color perception are applied on the new image. This is achieved by projecting the pixels in the new image to the line representing the manifold of reference color perception. This model can be used for color correction of images with different color perceptions to a learnt color perception. This method, unlike other approaches, has a single step convergence and hence is faster.