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.
This paper presents a non-person specific appearance model for modeling nonlinear facial expression variations. A combined express ion-and-texture similarity measure (ETSM) is proposed to reliably find the nearest neighborhoods of the novel image. In the ETSM, we consider both shape and texture differences. The shape is coded using MPEG-4 facial animation parameters (FAP), which can provide a compact...
We propose a computationally feasible adaptive noise smoothing algorithm that considers the local dependency characteristics of images under the complex dual-tree discrete wavelet transform (DWT). The wavelet coefficients with complex dual-tree discrete wavelet are assumed to be zero-mean Gaussian random variables. The variances of local statistics of each coefficient are estimated with a centered...
Typically, the almost SRR (super-resolution reconstruction) estimations are based on L1 or L2 statistical norm estimation therefore these SRR methods are usually very sensitive to their assumed model of data and noise that limits their utility. This paper reviews some of these SRR methods and addresses their shortcomings. We propose a novel SRR approach based on the stochastic regularisation technique...
Computational cost is the main drawback for two-dimensional (2-D) thresholding methods. GAs can accelerate the calculation, but still fail to satisfy most of applications. By introducing an implantation, which replaces the selection of GAs, an evolution mechanism was proposed. An excellent schema is implanted in the low performance strings to improve both the performance and diversity of population...
We propose two novel methods for reconstructing d-dimensional signals with irregular samples, without any restriction on their positions. First approach is an approximation with a fixed number of compactly supported radial basis functions (CSRBFs). Whereas the second one is a multiresolution approach with a fixed error bound, in which we only add CSRBFs where the largest local error at the previous...
A new wavelet domain algorithm for speech enhancement is presented. The main idea of the proposed algorithm can be described as follows: noisy speech is first split into low frequency band signal and high frequency band signal via one scale of DWT. Then, three scales of DWT and three scales of WPD are applied to the low frequency signal and the high frequency signal respectively. The denoised speech...
Extended 2 dimensional MMR Code is a kind of facsimile signal source code. Vertical relativity is utilized when MMR code is coded. In addition, there is no line synchronized code in MMR code. So when an error occurs, the bitstream cannot be decoded after the error point. To prevent error diffusion in MMR coding, this paper introduces a method: moving window error-correcting arithmetic which can partly...
In this paper, we propose an architecture that performs discrete wavelet transform (DWT) using a lifting-based scheme and integer arithmetic units in JPEG2000. The proposed architecture requires only 3 fixed-point multipliers, 17 integer adders and 3 shifters. The architecture has been designed to generate an output every cycle for the JPEG2000 default filters and has been implemented in behavioral...
An improved genetic fuzzy c-means clustering(FCM) algorithm is proposed for color image segmentation in the paper. The first component of color feature set discovered by Ohta is chosen as the one-dimensional eigenvector and the mapping from pixel space to eigenvector space is used here for modifying the object function in order to lower the computational complexity. Feature distance which is applied...
This paper deals with the automatic threat detection for accompanied baggage based on multi- energy X-ray imagery, we propose a structural segmentation method based on ARG matching. The proposed segmentation algorithms are a series of graph-matching algorithms based on models under a kind of similarity measure, fuzzy similarity distance. The results show a good average integrity of objects segmented...
The finite ridgelet transform proposed by Donoho has successful application in edge detection and segmentation of images with high-noise, but it has a drawback which is due to annoying "wrap-around" effect to the finite Radon transform. As a result, it may also produce "alias" edges and "holes" in the reconstructed image. In this paper, we present a new finite ridgelet...
This paper introduces the keren sub-pixel registration method and point out its disadvantage. Moreover, this paper put forward a new improvement approach about keren method and its iterative method. The improvement approach base on the four parameters affine transformation model and abandon the rigid body transformation model. This change avoids the error that is brought on by the tailor series expansion...
In fractal image coding, the main consuming time is the process of finding the best matched domain block in a large domain pool for a given range block. In this paper, we propose a fast algorithm for fractal image coding based on the following lemma and fine granularity successive elimination (FGSE). The lemma describes the relationship between fractal image coding and FGSE. This algorithm can decrease...
In this paper, I put forward and discuss multiform covering templates and algorithms of fractional derivative for digital image. The computer experiment shows the textural detail enhancing capability of fractional derivative-based texture operator is much better than integral derivative-based one for rich-grained digital image
Inconsistent color between different viewpoints is a serious problem in multi-view image processing. A multi-view image color correction method is proposed. We first estimate whether global correction satisfied for the target image and source image. If no global correction is satisfied, image segmentation and Karhunen-Loeve (K-L) transform are performed. Then, local mapping relations between target...
The wavelet packet provides an accurate method for image fusion. However, the computation and time cost will increase with the size of image. Therefore it is difficult to achieve real-time fusion. After having analyzed the wavelet packet based image fusion algorithm on the single computer, according to the time complexity and the parallel character of the wavelet packet algorithm, we propose a wavelet...
In this paper, a two-step scheme based on the maximum variance cluster algorithm was presented to detect and recognize bridges over water with the complicated background from the remote sensing images. First, the water including bridges was detected in all region of image; then, image segmentation and feature extraction and recognition were performed over the water having been detected. According...
In H.264/AVC fractional pixel motion compensation is adopted in order to achieve more accurate motion description and higher compression efficiency. It, however, remarkably increased computation load in motion estimation (ME) process for video coder. In this paper an improved fractional pixel ME algorithm is proposed to reduce its computation load, which is based on the fact that the distribution...
Vertex-based operational-rate-distortion (ORD) shape coding algorithms frequently use a sliding window (SW) to both avoid trivial solutions and improve computational efficiency, with the choice of the SW-width enabling the encoder to trade between bit-rate and computational complexity. This paper presents some new strategies for dynamically determining the SW-width adaptive within the rate-distortion...
Image interpolation is a key aspect of digital image processing. This paper presents a novel interpolation method based on reproducing kernel filter (RKF) and global texture orientation. With the kernel function in H1 (R) space, it can be shown that the RKF is constructed and a one-dimensional interpolation function is derived. According to H1 (R) norm, the RKF has the advantage of offering good approximation...
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.