最新刊期
卷 17 ， 期 2 ， 2012
- 摘要：With the rapid growth of the diversity and versatility of display devices which all come in different aspect ratios and resolutions, the content-aware image resizing has become one of the hot research fields in image processing. The main objective of such a technique is to preserve the image features when changing its size. The most content-aware image resizing methods have two basic steps: content significance recognition and image resizing based on a significance map. Firstly, the classic methods of the significance recognition are surveyed.Secondly, the resizing technologies based on significance maps are summarized. According to resizing methods based on pixel level discrete operating, sub-pixel level continuous operation or combination of the discrete operating and continuous operation, it can be categorized into image resizing based on seam carving, image resizing based on warping or multi-operator resizing. Thirdly, the algorithm effect comparisons between classes are given and their suitable image types are presented. Finally, future directions are discussed.关键词：content-aware image resizing;importance map;saliency map;seam carving;image warping;multi-operation5005|289|0更新时间：2024-05-08
- 摘要：Textile image enhancement aims to extract textural features of textiles which facilitates manual testing and machine vision inspection of textile.In this paper,a method for textile image enhancement is proposed in the framework of non-local means (NLM) filtering.Due to the periodic nature of textiles,there exists a lot of redundant information in textile images which can be used to enhance the texture information.However,the complex structures of textile images as well as the presence of image noise tend to distort similarity measures of the NLM algorithm.To solve this problem,principal component analysis (PCA) is used to decompose textile images into information components and noise components,and remove the correlation between the components for improving the accuracy of the similarity measure between textile textures.The experimental results demonstrate that the proposed method has substantially improved the performance of texture enhancement relative to the existing texture enhancement methods.关键词：textile image;texture enhancement;non-local means;principal component analysis3226|207|0更新时间：2024-05-08
- 摘要：Humans are sensitive to edges and the contrast of images.We propose a novel image zooming method which preserves the edges and enhances the contrast of an image synchronously. In our system, images are reconstructed by solving a Poisson equation after Canny edges detection, gradients scaling and smoothing on edges. The gradients along the image edges are scaled, which preserves the edges for image scaling. Our method not only preserves the image edges, but also enhances the image contrast which reveals more image details. This method is easy to implement, and can be applied to several areas such as image scaling and contrast enhancement.关键词：image scaling;edge detection;Poisson equation;contrast enhancement4559|194|0更新时间：2024-05-08
- 摘要：For image authentication, a fragile digital watermarking method is proposed. This method embeds watermarking into fractal transform, and embeds fractal coding parameters as watermark into the host image. It can not only locate altered areas, but also automatically recover the original image through extracting the fractal coding parameters. Experimental results show that the proposed method is capable of tamper localization, and effective for automatic recovery.关键词：fractal image coding;fragile watermarking;image authentication2840|148|0更新时间：2024-05-08
- 摘要：Global motion estimation is one of the important research topics in video processing and computer vision.In this paper, a new approach for global motion estimation is proposed by combining the block motion vectors and pixel recursive algorithm. The proposed method first establishes a vector histogram based on the block motion vectors, and then finds the main block motion vector as initial global motion orientation, to set the initial motion parameters. The threshold of motion segmentation is obtained and outlier areas are adaptively eliminated by using the distance between motion vectors and the variance between clusters. One or two feature pixels in each background block are selected to estimate the global motion parameters according the gradient sum. Experimental results show that the proposed algorithm is accurate, fast,and efficient.关键词：global motion estimation;motion vector;parameter model;outlier detection;gradient pixels selection3656|136|0更新时间：2024-05-08
- 摘要：A raster data pyramid is a basic data structure in spatial information systems.The boundary issue caused by blocking must be considered in a wavelet-based pyramid construction method.This issue is not mentioned in most existing algorithms or a large amount of calculations is needed to eliminate the border gap in those other methods.This paper presents a wavelet coefficient stitching algorithm for data blocks,which addresses the block boundaries in the wavelet transformation.The key point of our stitching algorithm is that one block coefficients is patched by its adjoining blocks boundary coefficients.The stitching result is equivalent to proceeding wavelet transformation on the whole data.A pyramid construction method is proposed that is named seamless wavelet pyramid construction method (SWPCM).In the SWPCM,the whole data is divided into a large number of blocks and a wavelet transformation is performed on each block.Then,the stitching algorithm is executed on the blocks' wavelet coefficients.The boundary coefficients are eliminated and data seamless organization is achieved with SWPCM.The experiments show that the stitching algorithm can significantly reduce the sizes of high level coefficients and that the proposed method is easy to implement.关键词：image pyramid;data seamless organization;wavelet transformation;wavelet coefficients stitching3139|124|0更新时间：2024-05-08
- 摘要：Detecting completely unstructured road may improve the adaptability for different environments,which is crucial for intelligent autenomous vehicle driving. In this paper, a road detection algorithm combined with cubic spline curve model and block sub-region growing model (CSCM_BSG) is proposed for true-color information of real-time road images.The algorithm applies the cubic spline interpolation to achieve the pseudo-color mapping at first, and accomplishes road region detection using the sub-region growing method combining the primary and secondary pseudo-hues with textures.The tests and comparative experiments on field images show that the algorithm is not only more accurate and applicable in real-time for road regions, but also has stronger counter-interference capability for shadows, water stains.关键词：unstructured road detection;cubic spline curve;sub-region growing model;image processing2981|162|0更新时间：2024-05-08
- 摘要：Because of the unevenness of terrain and the uncertainty of the position and orientation of a mobile robot,it is difficult to get the obstacle characteristics in unknown environments.In order to detect the obstacle characteristics accurately,a 3D camera is used to obtain a gray image and the depth information of the environment.Then a threshold method based on the obtained gray image and the 3D information is presented to determine the area of an obstacle.But inaccurate feature detections will still exist in the above 3D information threshold method,caused by different factors,for example,too much transition regions between the ground and the obstacle are eliminated or the relative position between the robot and the slope is uncertain.In order to solve these problems,a region recovery algorithm and a computation method of slope degree estimation are developed.Experimental results show that our algorithm has the merits of simplicity,effectiveness,accuracy and high robustness.关键词：robot;3D-camera;environment perception;obstacle3657|177|0更新时间：2024-05-08
- 摘要：The geodesic active contour (GAC) model based on regions is not applicable to images with intensity inhomogeneity. In this paper,we propose a new model of the GAC based on local regions. Information of the local mean is used to overcome the intensity inhomogeneity effect of the segmentation result. A local signed pressure force function is constructed so that the contour shrinks when outside of the object, or expands when inside of the object. In order to improve the algorithm's effectively and steadily, the model is implemented by a binary level set function. Experimental results with medical images show that the new model can get the better results in a more efficient way.关键词：GAC model;signed pressure force function;local regional information;binary level set5708|173|0更新时间：2024-05-08
- 摘要：Spectral clustering algorithms have wide applications in pattern recognition and image segmentation.They can cluster samples in any form of the feature space and have global optimal solutions.In this paper,a new graph-based spectral cluster algorithm called Dcut is applied to image segmentation.Dcut completely satisfies the general criterion of the cluster algorithms:maximizing the within-cluster similarities while minimizing between-cluster associations.Compared with Ncut,Dcut has better grouping performance in image segmentation.In order to overcome Dcut's shortcoming i.e.slow speed for image segmentation,two fast Dcut algorithms,i.e.subspace-based Dcut (SDcut) and block-based SDcut (BSDcut),are proposed.SDcut and BSDcut have Dcut's grouping performance whihe at the same time reducing the computational complexity.Experiments based on texture images and real images demonstrate the advantages of the proposed algorithms.关键词：spectral clustering;Dcut;SDcut;BSDcut;subspace;image segmentation4870|241|0更新时间：2024-05-08
- 摘要：Pupil can not be extracted as a similar standard ellipse because of some interferences caused by reflections, eyelashes and eyelids, which have some difficulties to measuring pupil accurately. In order to solve the problem of eyelid occlusion, an improved method of pupil measurement under eyelid occlusion is presented. It acquires the region of interesting on pupil image and removes reflections by filtering and Sweepline based on threshold segmentation. Then, the center of the pupil is determined using inscribed parallelogram after rotating according to the dividing line for the eyelid. A proposed algorithm of center correction based on circle detection can detect the intersections of two circles, which can be used as the intersections between the pupil and eyelid in order to compute the angle of the pupil and refine the center. Furthermore, the initial parameters of the pupil ellipse obtain from the five-point method and the ellipse is optimal in the sense of non-linear least squares by minimizing the Euclidean distance between fitting ellipse and edge points. Experimental results demonstrate, this method achieves good performance in terms of robustness and accuracy and obtains accurate locations and boundaries in the case of occlusion no more than half of the pupil area.关键词：pupil measurement;occlusion;parallelogram method;ellipse detection4007|147|0更新时间：2024-05-08
- 摘要：Obtaining various tissues from microscopic of wood images has important significance for the analysis of wood properties, weather changes, and wood species, which relies on the results of image segmentation techniques. Level Set is conducted in the segmentation of wood images in our experiments described in this paper.After the combination of the edge-based and region-based models in Level Set,we introduce the local cues in image to improve the image segmentaion performance for the wood tissue's inhomogeneity and reduce the noise caused by the production of wood specimens. Then, an area threshold is used to get rid of blisters and other impurities in the image to obtain the wood pores at last. Experiments show that the proposed method can smoothly segment images of local non-uniform wood microstructure,and significantly reduced the noise.关键词：image segmentation;intensity inhomogeneity;level set;energy function;wood microscopic image3212|118|0更新时间：2024-05-08
- 摘要：A new automatic algorithm for line generalization based on key point detection is presented in this paper.An adaptive threshold corner detector is used to detect all corner points,from which key points are selected.To keep the shape characteristic of lines,all key points must be reserved.For the segmented lines at these key points,each sub-line is generalized with the Li-Openshaw algorithm.Compared with conventional algorithms,the results of our experiments show that the shape of lines is better preserved and the positions are more accurate.关键词：line generalization;corner detection;adaptive threshold;key point detection;Li-Openshaw algorithm3614|137|0更新时间：2024-05-08
- 摘要：High resolution digital elevation models (DEM) used in digital terrain analysis are becoming more and more prevalent. There are various curvilinear structure extracting algorithms, but the main limitation of them is the high computing cost, making them less efficient when extracting topographic feature lines from high resolution DEM images. We propose an efficient strategy to speed them up using Steger's curvilinear structure detection algorithm imple mented on graphic processing units (GPU). We choose to speed up the most computation intensive modules of the algorithm (Hessian matrix generation and feature point detection) using NVIDIA's compute unified device architecture (CUDA). This method can achieve more than five times speedup compared with the original algorithm on central process units (CPU) for large scale DEM images with millions of pixels.关键词：digital elevation model;topographic feature line detection;graphic processing unit;compute unified device architecture3807|156|0更新时间：2024-05-08
- 摘要：To address issues about the initialization of Snakes' contour,computational inefficiency,and poor positioning accuracy of the traditional gradient vector field Snakes model,an improved GVF Snakes Model is proposed based on the analysis of the distribution and the deformation principle of the model.In the new model,edges are detected exploiting the SUSAN algorithm firstly:afterwards,a snake contour is initialized using the convex hull generated by the edge points.Then,according to the edges and the deformation principle,the model modifies the distribution of the GVF.Finally,the improved model detects the edges of synthetic images and natural images accurately.The experimental results show that the proposed model not only is efficient,but also has better performance on the weak edges and sharp corners.关键词：gradient vector field;snakes model;SUSAN;edge detection;deforming3652|124|0更新时间：2024-05-08
- 摘要：The curvelet transform has the characteristic of anisotropy and the ability of good curve singularity expression. To overcome the shortage of invariant wavelet moments and Hu's invariant moments,curvelet transform is introduced into the wear particle feature extraction process and combined with Hu's invariant moments. Thus,an image invariant moment extracting method utilizing curvelet transform is proposed. First the wear particle images are decomposed and reconstructed by a curvelet transform,and their sub images of different scales are obtained. Then,the curvelet invariant moments are achieved by extracting Hu's invariant moments. Finally,the proposed method is applied for typical wear particle recognition,and a total successful recognition rate of 83.33% is accomplished. The experimental results indicate that compared with Hu's invariant moments and invariant wavelet moments,the curvelet invariant moments can better express wear particle appearance characteristics.关键词：Hu's invariant moments;curvelet transform;feature extraction;wear particle recognition3849|412|0更新时间：2024-05-08
- 摘要：In this paper we propose a two-step approach to recognize free-form objects in range images. First, feature points are calculated based on the contour curve, then mapped to the original shape space. Then a landmark list is determined and used to form a rejection classifier, which quickly eliminates a large number of candidates for an efficient recognition. The remaining free-form objects are then verified using a novel local patch-based matching approach, which is robust to occlusions and noise. The key points are determined based on the scale invariant feature transform (SIFT), and the local surface descriptor is characterized by its two 1D histograms. The two histograms show the frequency of occurrence of the shape index values and the angles between the normal of a key point and that of its neighbors. In order to speed up the retrieval of surface descriptors and save the restore space, the modal data includes shape and surface information. The local surface patched of modal are indexed into a hash table. Verification is performed by running the Iterative Closest Point algorithm. Experimental results with ideal range image are presented to demonstrate the effectiveness, efficiency of the proposed approach.The approach is robust to occlusions and noise.关键词：3D object recognition;range images;contour curve;SIFT;local surface patch3434|182|0更新时间：2024-05-08
- 摘要：Systematic errors are the main factors affecting the accuracy of airborne LiDAR system. To attain high-precision airborne LiDAR data, it is of great theoretic and practical value to research the key techniques and methods to eliminate these systematic errors. In our paper we propose a new method for airborne LiDAR strip adjustment based on least Z-difference(LZD) algorithm and then introduce the Gauss-Markov model to improve the adjustment accuracy. Experimental results show that after reasonable parameters configuration of the Gauss-Markov model, our improved strip adjustment method can significantly improve the adjustment accuracy. The accuracy of airborne LiDAR data strip adjustment based on LZD can meet our project accuracy requirements. Compared to the commercial software TerraMatch, the LZD and TerraMatch accuracy are at the same level.关键词：LiDAR;strip adjustment;least Z-difference;Gauss-Markov model3588|106|0更新时间：2024-05-08
- 摘要：Tile spatial index is a key technology to improve the tile fetching efficiency and its performance directly affects the overall performance of geographic information network services. This article analyzes the basic principles of grid index and quad-tree index which are widely used in tile map service.Because Z curve has good locality-preserving behavior and a good reduction of dimensionality behavier,we design a new tile spatial index based on Z-curve, called Z-Index. Experimental results show that the performance of Z-Index is better than grid and quad-tree indexing when applied on massive tile datasets.关键词：tile map service;spatial index;Z curve;tile quadtree index;grid index3751|123|0更新时间：2024-05-08
- 摘要：The visualization of natural phenomena visualization is an important research area in computer graphics and virtual reality.In this paper we analyze and imprave the traditional ray casting algorithm by proposing a graphics processing units(GPU)based spherical shell ray casting algorithm. GPU are used in the spherical shell data field volume rendering, and spherical shell.Vertex shader and pixel shader programs for spherical shell data field rendering are designed. The format of the typhoon source data is analyzed and the typhoon volume data to be visualized is generated. The visualization of typhoon clouds and factors are implemented by using the proposed algorithm. Experiment results show that a good real-time visualization of a typhoon is obtained by the GPU-based spherical shell ray casting algorithm.关键词：GPU acceleration;typhoon visualization;ray casting algorithm;spherical shell3524|153|0更新时间：2024-05-08
- Postal code：100190
- Tel：010-58887035/58887030/58887418 Email：jig@aircas.ac.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05080539号-4
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0