Kameswara Rao Namuduri

Fast texture database retrieval using extended fractal features

The increase in the number of multimedia databases consisting of images has created a need for a quick method to search these databases for a particular type of image. An image retrieval system will output images from the database similar to the query image in terms of shape, color, and texture. For the scope of our work, we study the performance of multiscale Hurst parameters as texture features for database image retrieval over a database consisting of homogeneous textures. These extended Hurst features represent a generalization of the Hurst parameter for fractional Brownian motion (fBm) where the extended parameters quantize the texture roughness of an image at various scales. We compare the retrieval performance of the extended parameters against traditional Hurst features and features obtained from the Gabor wavelet. Gabor wavelets have previously been suggested for image retrieval applications because they can be tuned to obtain texture information for a number of different scales and orientations. In our experiments, we form a database combining textures from the Bonn, Brodatz, and MIT VisTex databases. Over the hybrid database, the extended fractal features were able to retrieve a higher percentage of similar textures than the Gabor features. Furthermore, the fractal features are faster to compute than the Gabor features.

Computation and performance trade-offs in motion estimation algorithms

Real-time video/visual communication applications require trade-offs in terms of processing speed, visual image quality and power consumption. Motion estimation is one of the tasks in video coding that requires significant amount of computation. Block matching motion estimation algorithms such as the three-step search and the diamond search algorithms are being used in video coding schemes as alternatives to full search algorithms. Fast motion estimation algorithms reduce the computational complexity, at the expense of reduced performance. Special purpose fast processors can be employed as an alternative to meet the computational demand. However, the processing speed comes at the expense of higher power consumption. This paper investigates motion estimation algorithms and presents the computational, and performance trade-offs involved in choosing a motion estimation algorithm for video coding applications. Fast motion estimation algorithms often assume monotonic error surface in order to speed up the algorithm. The argument against this assumption is that the search might be trapped in local minima and may result in a noisy motion field. Prediction methods have been suggested in the literature as a solution to avoid these local minima and noisy motion field. The paper also investigates the effects of the monotonic error surface assumption as well as the appropriate choice of initial motion vectors that results in better performance of the motion estimation algorithms.

Detection of targets in low-resolution FLIR images using two-dimensional directional wavelets

This paper investigates the use of Continuous Wavelet Transform (CWT) features for detection of targets in low resolution FLIR imagery. We specifically use the CWT features corresponding to the integration of target features at all relevant scales and orientations. These features are combined with non-linear transformations (thresholding, enhancement, morphological operations). We compare our previous results using the Mexican hat wavelet with those obtained using the two types of directional wavelets: the Morlet wavelet and the Cauchy wavelets. The algorithm was tested on the TRIM2 data base.

Effect of signal-to-clutter ratio on template-based ATR

In this work, we evaluate the robustness of template matching schemes for automatic target recognition (ATR) against the effects of clutter layover. The results of our experiments indicate the performance of template matching ATR in various image transform domains against the signal to clutter ratio (SCR). The purpose of these transforms is to enhance the target features in a chip while suppressing features representative of background clutter or simple noise. The ATR experiments were performed for synthetic aperture radar imagery using target chips in the public domain MSTAR database. The transforms include pointwise nonlinearities such as the logarithm and power operations. The templates are generated using the training portion of the MSTAR database at the nominal SCR. Many different ATR parameterizations are considered for each transform domain where templates are built to represent different ranges of aspect angles in uniform angular bins of 5, 10, 15, 30, and 45 degree increments. The different ATRs were evaluated using the testing portion of the database where synthetic clutter was added to lower the SCR.

SAR target detection by fusion of CFAR, variance, and fractal statistics

Two texture-based and one amplitude-based features are evaluated as detection statistics for synthetic aperture radar (SAR) imagery. The statistics include a local variance, an extended fractal, and a two-parameter CFAR feature. The paper compares the effectiveness of focus of attention (FOA) algorithms that consist of any number of combinations of the three statistics. The public MSTAR database is used to derive receiver-operator-characteristic (ROC) curves for the different detectors at various signal-to-clutter rations (SCR). The database contains one foot resolution X-band SAR imagery. The results in the paper indicate that the extended fractal statistic provides the best target/clutter discrimination, and the variance statistic is the most robust against SCR. In fact, the extended fractal statistic combines the intensity difference information used also by the CFAR feature with the spatial extent of the higher intensity pixels to generate an attractive detection statistics.

Image metrics for clutter characterization

A large number of parameters affect the fundamental performance of automatic target recognition (ATR) systems including sensor, geometry, and scene parameters. Clutter complexity refers to the scene parameter that measures the extent that the objects in the background of the scene are target-like. This paper describes our initial work to understand how to measure clutter complexity and bound ATR performance as a function of this complexity, given that the other parameters are held constant. For this study, we use an unrealistically omnipotent ATR to approximate performance bounds and characterize the clutter complexity for each scene in the COMANCHE FLIR database. Using this characterization, we generate a clutter complexity metric from a number of image processing features and compare the new metric against the performance of an actual ATR.

Scale-angle CWT features: application in object recognition

This paper discusses the utility of scale-angle continuous wavelet transform features for object classification. These features are used as input to two algorithms: character recognition and target recognition in FLIR images. The corresponding recognition algorithm is robust against noise and allows data reduction. A comparative study is made between two types of directional wavelets derived from the Mexican hat wavelet and the usual template matching.

Target detection during image formation for ultrawideband radar

In this work, we introduce a detection scheme that is able to identify regions of interest during the intermediate stages of an image formation process for ultra-wideband (UWB) synthetic aperture radar. Traditional detection methods manipulate the data after image formation. However, this approach wastes computational resources by resolving to completion the entire scene including area dominated by benign clutter. As an alternative, we introduce a multiscale focus of attention (FOA) algorithm that processes intermediate radar data from a quadtree-based backprojection image formation algorithm. As the stages of the quadtree algorithm progress, the FOA thresholds a detection statistic that estimates the signal-to-background ratio for increasingly smaller subpatches. Whenever a subpatch fails a detection, the FOA cues the image formation processor to terminate further processing of that subpatch. We demonstrate that the FOA is able to decrease the overall computational load of the image formation process by a factor of two. We also show that the new FOA method provides fewer false alarms than the two-parameter CFAR FOA over a small database of UWB radar data.

Perceptual image compression for data transmission on the battlefield

This paper treats the compression of Synthetic Aperture Radar (SAR) imagery. SAR images are difficult to compress, relative to natural images, because SAR contains an inherent high frequency speckle. Todays state-of-the-art coders are designed to work with natural images, which have a lower frequency content. Thus, their performance on SAR is under par. In this paper we given an overview performance report on the popular compressions techniques, and investigate three approaches to improve the quality of SAR compression at low- bit rates. First, we look at the design of optimal quantizers which we obtain by training on SAR data. Second, we explore the use of perceptual properties of the human visual system to improve subjective coding quality. Third, we consider the use of a model that separates the SAR image into structural and textural components. The paper concludes with a subjective evaluation of the algorithms based on the CCIR recommendation for the assessment of picture quality.

Improved template-based SAR ATR performance using learning vector quantization

This paper investigates methods to improve template-based synthetic aperture radar (SAR) automatic target recognition (ATR). The approach utilizes clustering methods motivated from the vector quantization (VQ) literature to search for templates that best represent the signature variability of target chips. The ATR performance using these new templates are compared to the performance using standard templates. For baseline SAR ATR, the templates are generated over uniform angular bins in the pose space. A merge method is able to generate templates that provide a nonuniform sampling of the pose space, and the templates produce modest gains in ATR performance over standard templates.