Showing papers in "Image and Vision Computing in 2003"

TL;DR: A review of recent as well as classic image registration methods to provide a comprehensive reference source for the researchers involved in image registration, regardless of particular application areas.

TL;DR: The integration of color distributions into particle filtering, which has typically been used in combination with edge-based image features, is presented, as they are robust to partial occlusion, are rotation and scale invariant and computationally efficient.

TL;DR: The state of the art in machine vision inspection and a critical overview of real-world applications are presented and two independent ways to classify applications are proposed.

TL;DR: An algorithm based on bidimensional empirical mode decomposition (BEMD) to extract features at multiple scales or spatial frequencies to apply to texture extraction and image filtering, which are widely recognized as a difficult and challenging computer vision problem.

TL;DR: This paper presents an overview of image processing and analysis tools used in traffic applications and relates these tools with complete systems developed for specific traffic applications, and categorizes processing methods based on the intrinsic organization of their input data and the domain of processing.

TL;DR: A hand gesture recognition system to recognize continuous gesture before stationary background consisting of a real time hand tracking and extraction, feature extraction, hidden Markov model (HMM) training, and gesture recognition.

TL;DR: A genetic algorithm is used for the detection step, allowing an invariance localisation to changes in position, scale, rotation, weather conditions, partial occlusion, and the presence of other objects of the same colour.

TL;DR: This paper presents a method for automatically registering multiple rigid three dimensional (3D) data sets, a process the authors call multi-view surface matching, and applies it to the problem of 3D digital reconstruction of real-world objects and shows results for a collection of automatically digitized objects.

TL;DR: A robust approach for tracking targets in forward looking infrared (FLIR) imagery taken from an airborne moving platform, which combines automatic model update and global motion compensation into one framework is proposed.

TL;DR: A fresh look in the subject that overview classic and latest presented methods of fundamental matrix estimation which have been classified into linear methods, iterative methods and robust methods and their accuracy analyzed in synthetic and real images.

TL;DR: A global approach for the automatic inspection of defects in randomly textured surfaces which arise in sandpaper, castings, leather, and many industrial materials is presented, based on a global image reconstruction scheme using the Fourier transform.

TL;DR: A system to detect passenger cars in aerial images along the road directions where cars appear as small objects is presented as a 3D object recognition problem to account for the variation in viewpoint and the shadow.

TL;DR: Progress in the development of flexible, generative models that can explain visual input as a combination of hidden variables and can adapt to new types of input are reviewed.

TL;DR: An important result of this article is that the recovery of the three-dimensional properties of a moving person, or even the two-dimensional tracking of the person's limbs need not precede action recognition.

TL;DR: This paper presents a novel approach for eliminating unexpected shadows from multiple pedestrians from a static and textured background using Gaussian shadow modeling, and demonstrates that approximately 94% of shadows can be successfully eliminated from the scene background.

TL;DR: Performance comparisons show that the KPF is an improvement over Condensation, while the UPF has a much higher computational cost for equal tracking error.

TL;DR: This work proposes a method that outperforms state-of-the-art face detection methods in environments with stable lighting and can potentially perform well invironments with variable lighting conditions.

TL;DR: This paper shows the system successfully tracking multiple people moving independently and the ability of the approach to maintain trajectories in the presence of occlusions and background clutter.

TL;DR: Experimental results show that the new fitness function outperforms the other three fitness functions and the GA driven by it selected a good subset of features to discriminate the targets from clutters effectively.

TL;DR: Experimental results show that the decomposed subimages and the number of resolution levels determined by the automatic band selection scheme are similar to the manual selection results, and the defects in a variety of real textures including machined surfaces, natural wood, sandpaper and textile fabrics are well detected.

TL;DR: It is shown that extracting color and texture information in the locations given by the salient points provides significantly improved results in terms of retrieval accuracy, computational complexity, and storage space of feature vectors as compared to global feature approaches.

TL;DR: Results show that the localisation accuracy of facial features is considerably increased using this appearance representation under diffuse and directional lighting and at multiple scales.

TL;DR: The diffusion snake is introduced as a hybrid model combining the externalEnergy of the Mumford-Shah functional with the internal energy of the snake to facilitate segmentation of objects of interest in images which are corrupted by noise, clutter or occlusion.

TL;DR: A novel continuous medial repre- sentation for describing object geometry and a deformable templates method for tting the representation to images and prelim- inary results of segmenting 2D and 3D medical images are presented.

TL;DR: The contour detection algorithm is formulated as a constrained optimization problem based on active contour model and the optimization problem has been solved using Genetic Algorithm (GA).

TL;DR: A method for modeling thermal emission from human skin that can be used for the purpose of segmenting and detecting faces and other exposed skin regions in IR imagery is presented and the segmentation model is applied to the CONDENSATION algorithm for tracking the head regions over time.

TL;DR: A new classification method using color, texture and regions to prune irrelevant database images for each query image and the k-NN rule is used to assign a class label to the query image to achieve effective classification results.

TL;DR: A texture-constrained active shape model (TC-ASM) to localize a face in an image that performs stable to initialization, accurate in shape localization and robust to illumination variation, with low computational cost.

TL;DR: A fast method that combines curve matching techniques with a surface matching algorithm to estimate the positioning and respective matching error for the joining of three-dimensional fragmented objects is presented.

TL;DR: The results support the use of corners as robust, stable beacons suitable for use in this application of power line inspection from a helicopter using video surveillance techniques.