9:30, IMDSP-P2.1
BLOCKINESS DETECTION IN COMPRESSED DATA
G. TRIANTAFYLLIDIS, D. TZOVARAS, M. STRINTZIS
A novel frequency domain technique for image blocking artifact detection is presented in this paper. The algorithm detects the regions of the image which present visible blocking artifacts. This detection is performed in the frequency domain and uses the estimated relative quantization error calculated when the DCT coefficients are modeled by a Laplacian probability function. Experimental results illustrating the performance of the proposed method are presented and evaluated.

9:30, IMDSP-P2.2
MOVING TARGETS DETECTION USING SEQUENTIAL IMPORTANCE SAMPLING
G. QIAN, R. CHELLAPPA
In this paper, we describe a new technique for detecting moving targets from image sequences captured from moving platforms. Feature points are detected and tracked through the image sequences. A validity vector is used to describe the consistency of the feature trajectories with the platform motion. By using the sequential importance sampling method, an approximation of the a posterior distribution of the sensor motion and the validity vector is derived and the feature points belonging to the moving target are then segmented out. Real image examples are included.

9:30, IMDSP-P2.3
ALGORITHMS TO ESTIMATING FRACTAL DIMENSION OF TEXTURED IMAGES
W. CHEN, S. YUAN, H. HSIAO, C. HSIEH
Fractal dimension is an attracting characteristic highly correlated with the human perception of surface roughness. Two algorithms that can obtain more accurate estimate of fractal dimension are proposed in this paper. One is the shifting DBC (SDBC) algorithm and the other one is the scanning BC (SBC) algorithm. It is theoretically proven that the SDBC algorithm approaches the estimated value closer to the exact fractal dimension than the DBC method. Simulation results show that the proposed algorithms consistently give more satisfactory results on textured images.

9:30, IMDSP-P2.4
SHADOW IDENTIFICATION AND CLASSIFICATION USING INVARIANT COLOR MODELS
E. SALVADOR, A. CAVALLARO, T. EBRAHIMI
A novel approach to shadow detection is presented in this paper. The method is based on the use of invariant color models to identify and to classify shadows in digital images. The procedure is divided into two levels: first, shadow candidate regions are extracted; then, by using the invariant color features, shadow candidate pixels are classified as self shadow points or as cast shadow points. The use of invariant color features allows to obtain a low complexity of the classification stage. Experimental results show that the method succeeds in detecting and classifying shadows within the environmental constrains assumed as hypotheses, which are less restrictive than state-of-the-art methods with respect to illumination conditions and scene's layout.

9:30, IMDSP-P2.5
INFRARED-IMAGE CLASSIFICATION USING EXPANSION MATCHING FILTERS AND HIDDEN MARKOV TREES
P. BHARADWAJ, P. RUNKLE, L. CARIN
Forward-looking infrared (FLIR) images of targets are characterized by the different target components visible in the image, with such dependent on the target-sensor orientation and target history (i.e., which target components are hot). We define a target class as a set of contiguous target-sensor orientations over which the associated image is relatively invariant, or statistically stationary. Given an image from an unknown target, the objective is proper target-class association (target identity and pose). Our principal contribution is an image classifier in which a distinct set of templates is designed for each image class, with templates linked to the object sub-components, and the associated statistics are characterized via a hidden Markov model. In particular, we employ expansion matching (EXM) filters to identify the presence of the target components in the image, and use a hidden Markov tree (HMT) to characterize the statistics of the correlation of the image with the various templates. We achieve a successful classification rate of 92% on a data set of FLIR vehicle images, compared with 72% for a previously developed wavelet-feature-based HMT technique.

9:30, IMDSP-P2.6
VIDEO GENRE CLASSIFICATION USING DYNAMICS
M. ROACH, J. MASON, M. PAWLEWSKI
The problem addressed here is classification of videos at the highest level into pre-defined genre. The approach adopted is based on the dynamic content of short sequences (about 30 secs). This paper presents two methods of extracting motion from a video sequence: foreground object motion and background camera motion. These dynamics are extracted, processed and applied to classify 3 broad classes: sports, cartoons and news. Experimental results for this 3 class problem give error rates of 17%, 8% and 6% for camera motion, object motion and both combined respectively, on about 30 second sequences.

9:30, IMDSP-P2.7
FINGERPRINT IMAGE ENHANCEMENT USING A BINARY ANGULAR REPRESENTATION
T. RANDOLPH, M. SMITH
We explore a novel approach to enhancing fingerprint images using a new binary directional filter bank (DFB). Automated fingerprint identification systems (AFIS) are used to classify a fingerprint in a large volume of images. Many approaches to AFIS have been suggested, most sharing in common the idea of extracting discriminate feature representations. As part of that process, the raw fingerprints are often smoothed, converted to binary and thinned. Conventional directional methods provide representations that delineate the directional components in the fingerprint image enabling separation, and enhancement. Our binary DFB receives a binary input and outputs a binary image set comprised of directional components. Through proper weighting and manipulation of the subbands, specific features within the fingerprint can be enhanced. We propose a new enhancement approach that remains in the binary domain for the entire process. We paper provide a description of a new binary DFB and its application to fingerprint pre-processing.

9:30, IMDSP-P2.8
TEXTURE CLASSIFICATION WITH A BIORTHOGONAL DIRECTIONAL FILTER BANK
J. ROSILES, M. SMITH
Classifying textures is a problem that has been considered by many researchers. Many of the high performance methods are based on extracting features from the textures and performing classification in the feature space. In this paper, we consider the application of a new directional filter bank (DFB) to the problem of texture classification. The DFB is used to provide a compact and efficient representation in which fast classification can be performed using classical statistical methods. The resulting method is shown to yield higher performance than feature-based techniques reported previously. Furthermore, the approach has the added attraction that both the computational complexity and storage requirements are relatively low. Experimental comparisons using the Brodatz texture database are presented at the end of the paper.