The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Typical object detection systems work by training a classifier on features extracted at different scales of an object. In this paper we investigate the performance of an object detection system in which different classifiers which are trained at various scales of an object are combined and compare the performance with a typical object detection system where a single classifier is trained for all the...
This paper investigates the use of self-organizing maps (SOMs) to segment, describe and index free form surfaces. The overall objective of the research is to be able to take a surface region and search a database of surfaces to find matching regions. A free-form surface in this paper is described as a mesh of triangles and is not assumed to be easily parameterized. The three issues considered in this...
The problem of emulsions stability evaluations from images acquired in microscopy is considered. The proposed approach consists of four consecutive steps: 1) images enhancement; 2) segmentation based on Watershed algorithm; 3) drops identification using a template matching procedure; 4) stability evaluation. Finally, an analysis of results is performed by comparing the estimated results with respect...
We propose a stereo camera self-adjustment methodology based on a correlation algorithm. We focus on stereo cameras in vision systems for vehicles and unmanned aerial vehicles. We therefore focus on changes of vergence angle. Our approach uses the following methodology: (1) feature detection using an edge density image, (2) stereo matching to find the lost camera parameters, and (3) a self-adjustment...
In this research, new fractal compression technique is introduced. It is based on using moment features to index the zero-mean range on domain blocks. The moment features have been used to speed up the iterated function system (IFS) matching stage. These features are used to determine the block descriptor "moment's ratio index", which in turn is utilized to classify the image blocks in both...
The objective of this research is to develop an advanced driver assistance system with lane departure warning and forward collision warning functions. The main input of this system is a CMOS camera, which is used to acquire roadway image in front of vehicle. In order to extract lane markings and vehicles from roadway image, the image processing methods such as coordinate systems transformation, object...
Enhanced security can be achieved combining biometrics and cryptographic concepts together. Aiming for security enhancement, this paper presents a scheme for merging multiple fingerprints with a cryptographic concept, the fuzzy vault. Thereby multiple fingerprints are eligible to lock and unlock a secret securely embedded within the multiple-control fuzzy vault. Given either threshold, compartmented...
In this paper, we present a new approach for automatic color image segmentation. It is a multilevel clustering method based on a new proposed non-parametric clustering algorithm, called adaptive medoidshift (AMS) and normalized cuts (N-cut). The AMS algorithm is a modification of recently presented medoidshift algorithm by transforming its global fixed bandwidth to local automatically chosen bandwidth...
In this paper a novel approach to recognising normalised 3D face data is proposed. A robust Hausdorff metric is applied to 3D images from the Face Recognition Grand Challenge v1.0 database. The proposed variant of the Hausdorff distance metric is completely data driven and enforces a consistency check on how well the data between any two faces correlate. This recognition algorithm is combined with...
This paper proposes a new human action recognition method which deals with recognition task in a quite different way when compared with traditional methods which use sequence matching scheme. Our method compresses a sequence of an action into a Motion History Image (MHI) on which low-dimensional features are extracted using subspace analysis methods. Unlike other methods which use a sequence consisting...
One of the more successful approaches to image segmentation involves formulating the problem as the minimisation of a Mumford-Shah functional and then applying region merging algorithms to approximate the minimiser. Moreover, it can be proved mathematically that such segmentations have desirable properties, and further, fast implementations are available. In this paper, we describe improvements to...
This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features...
Automated surveillance system is becoming increasingly important especially in the fields of computer vision and video processing. This paper describes a novel approach for improving the results of detecting foreground objects and their shadows in indoor image sequences. Several previous techniques have been developed in the literature that deal with moving shadows. However, a comparative evaluation...
This paper explores how to exploit shape information to perform object class recognition. We use a sparse part-based model to describe object categories defined by shape. The sparseness allows the relative spatial relationship between parts to be described simply. It is possible, with this model, to highlight potential locations of the object and its parts in novel images. Subsequently these areas...
Hyperspectral imagery generally contains enormous amounts of data due to hundreds of spectral bands. Band selection is often adopted firstly to reduce computational cost and accelerate knowledge discovery of subsequent classificationand analysis. Recently, a new clustering algorithm, named "affinity propagation," is proposed. Different from the popular k-centers clustering technique, affinity...
This paper proposes a dominant color based vector quantization algorithm that automatically categorizes image regions. In contrast to the conventional vector quantization algorithm, the new algorithm effectively handles variable feature vectors like dominant color descriptors. Furthermore, the algorithm is guided by a novel splitting and stopping criterion which is specially designed for dominant...
Many algorithms for image processing and pattern recognition have recently been implemented on GPU (graphic processing unit) for faster computational times. However, the implementation using GPU encounters two problems. First, the programmer should master the fundamentals of the graphics shading languages that require the prior knowledge on computer graphics. Second, in a job which needs much cooperation...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.