最新刊期
卷 20 ， 期 8 ， 2015
- 摘要：Present color management model pays attention to the color rendering principle analysis of different color devices. Alternatively, it only controls the input and output of the model that makes color conversion accuracy low. With regard to these problems, a new color management model is presented by analyzing the color rendering principle of CRT monitor. The standard color target is taken for experimental sample, and the paper substitutes color blocks in color shade district for complete color space to solve the difficulty of sample color block selecting in color adjustment of CRT monitor by deducing final color management model. Second, parameters of Yule-Nielson equation are reinterpreted. Thus, it can be used for nonprinting dot image, which can only be used for printing dot image originally. Then, the color management model for CRT monitor is deduced gradually though single color, double color, and tricolor conversion correction based on corrected contraction-expansion fitting and color rendering principle of CRT monitor. Experimental results show that the model can improve color management accuracy of CRT monitor above 54% and can be practically used in its color management. With the help of the color rendering principle of other color devices, the model has superior reference value for color management.关键词：color management of monitor image;Yule-Nielson equation;contraction-expansion fitting algorithm;standard color target2759|272|0更新时间：2024-05-07
- 摘要：This study aims to overcome the challenges of traditional image inpainting algorithms, wherein texture extension may occur and some incorrect samples may be selected as candidate patches when sample-based algorithms are employed to inpaint the damaged region with complex geometric structure and rich texture. An image inpainting method based on weight variation of neighborhood window is proposed. In the method, so-called weight variation is introduced by combining total variation and intrinsic variation in a neighborhood window to modify the priority measure in Criminisi's algorithm. With the proposed method, the ability of identifying geometric and texture information has been improved and geometric information can be urgently inpainted. Meanwhile, matching accuracy has been improved by introducing structure difference operator in combination with pixel color comparison. Compared with other recent algorithm, the proposed algorithm can settle the problem of texture expansion and block mismatching and can maintain visual connectivity. Moreover, the peak signal-to-noise ratio(PSNR) of its inpainting result is improved by 2 dB to 3 dB. Compared with the original Criminisi's algorithm and its improved algorithms, the proposed algorithm can achieve better result in inpainting the damaged region with both geometric structure and rich texture, as well as in inpainting some ordinary damaged region. Thus, the proposed algorithm has generality.关键词：image inpainting;priority;weight variation;optimal match2883|460|4更新时间：2024-05-07
- 摘要：After analyzing several schemes for determining filtering window size for the removal of salt-and-pepper noise, we propose a distance-weighted image denoising method based on adaptive filtering window. The proposed method first identifies the pixels with gray level 0 or 255 as noise pixels. Then, for each noise pixel, the minimum window with noise-free pixels is found. If the minimum window of a certain noise pixel is smaller than a given threshold, then noise-free pixels within the minimum window are used to perform distance-weighted filtering. Otherwise, the current noise pixel should be located in the regions composed of noise-free pixels with gray level 0 or 255, and a majority strategy is used to generate the restored gray level. The proposed method is evaluated by comparing it with seven other image denoising methods. Simulation results show that the new method achieves a better effect than its counterparts on images that contain noise-free pixels with gray level 0 or 255. Among all the compared methods, the new method achieves the best denoising effect on images that contain few or even no pixels with gray level 0 or 255. The proposed method effectively removes salt-and-pepper noise and is also suitable for images that contain many noise-free pixels with gray level 0 or 255.关键词：distance-weighted;density estimation;salt and pepper noise;image restoration2894|313|7更新时间：2024-05-07
- 摘要：Outliers inevitably exist in image matching, and they may result in a significantly high mismatching ratio when the overlapping region of two images is small. Some normal matching algorithms cause a high mismatching ratio. A robust purifying algorithm for rough matched pairs can be designed to solve this problem by reducing difficulties in image matching. Since Hough transform was proposed, it has been used to detect certain kinds of curves. It establishes a mathematical model for curves and votes in the para-meter space and determines exact parameters of the curve via maximum value in the parameter space. Based on the same voting idea, Hough transform is introduced in this paper to purify rough matched pairs. First, we assume that those truly matched pairs obey a certain transform model equation. Then, a common transform model can be established, and Hough transform is used to obtain parameters of model equation. In particular, each matched pair votes on the corresponding hypersurface, which is in the parameter space and determined by Hough transform. Thus, parameters of the transform model equation can be determined by the global maximum value in the parameter space. Then, all matched pairs that obey model equation are saved. Thus, the rough matched pairs can be purified in this way. Compared with traditional algorithms, such as random sample consensus, the proposed algorithm is not only robust to outliers with a good recall ratio but also more efficient. Moreover, experimental results indicate that the proposed method can be robust when the ratio of outliers is as high as 85%, and even when the ratio is up to 95%, it still can work very well with a probability of 50%. Hough transform can be applied to purify matched pairs, and many experiments prove its feasibility. Corresponding models should be chosen to obtain a good performance when aiming at rigid-body transformation and affine transformation. However, the proposed method is not suitable when many parameters (more than four) exist in the model equation, given that a high-dimensional space determined by parameters of the model equation is memory expensive and time consuming when searching and voting in the high dimensional parameters space.关键词：matched pairs purified;Hough transform;outliers;parameter space;voting3472|403|3更新时间：2024-05-07
- 摘要：In this paper, a new natural image segmentation method based on Gestalt rules is proposed to reduce the effect of illumination and other factors, as well as improve segmentation accuracy. The novelty of the proposed method lies in three aspects: first, the original image is segmented into several subregions with the use of normalized cut algorithm to reduce the effects of illumination, background smooth, and other natural factors. Second, the Gestalt rules are introduced to measure the regions, and a quantitative calculation model based on the regions, which can obtain the ratio region and agrees with human visual perception, is proposed. Third, a new merge algorithm based on the ratio region is proposed. The final segmentation result is obtained by merging the regions through the simple and highly efficient merge algorithm. Quantitative and visual inspections of 30 images show the effectiveness of the Gestalt rules on image segmentation. The results of the comparative experiments show that the effect of the algorithm is more aligned with human visual perception and that our algorithm performs better than the comparative experiments overall in the evaluation index of probabilistic Rand index, variation of information, and global consistency error. The results of our algorithm are closer to the results of artificial labels. A natural image segmentation method based on Gestalt rules is proposed. The method adopts oversegmentation and measures the region by applying the Gestalt rules that can effectively reduce the effect of natural factors in the segmentation process and improve segmentation accuracy. Experimental results show that the proposed image segmentation algorithm based on Gestalt rules exhibits better efficiency and accuracy than other algorithms, but the effect is not good for natural image with some sharp and thin object.关键词：natural image;over-segmentation;Gestalt rules;region merging4118|266|2更新时间：2024-05-07
- 摘要：Variational image segmentation methods, which are based on energy minimization process, have received significant attentions for years and gained fruitful achievements. However, the use of image information alone often leads to poor segmentation and results in presence of noise, clutter, or occlusion. Introducing shape prior to contour evolution process has been shown as an effective way to address these problems. However, problems associated with this method is nontrivial. The traditional solution is to estimate several pose parameters within each step of level set iteration. This solution is complicated and time consuming. Based on the kernel principal component analysis (KPCA) shape model, we propose a novel KPCA-based shape prior model with intrinsic pose invariance, and we then combine it with C-V image segmentation model. The complete segmentation model explicitly eliminates pose parameter estimation during level set iteration. Furthermore, segmenting correct ratio is increased by 7.47% compared with C-V model. We present an adaptive method to calculate parameter for the Gaussian kernel in KPCA shape model. Experimental results show the robustness of the combined model against noise, clutter, or occlusion and the ability to deal with the affine pose variance between prior shapes and object to be detected.关键词：image segmentation;variational method;shape priors;Kernel PCA;pose invariance2979|300|2更新时间：2024-05-07
- 摘要：To further improve the accuracy and speed of image threshold segmentation, an image segmentation method is proposed based on fast iteration for two-dimensional gray entropy threshold selection. First, a fast iterative algorithm for threshold selection that uses one-dimensional gray entropy is proposed. Gray level uniformity within the object cluster and background cluster is then considered, and two-dimensional gray entropy criterion for threshold selection based on gray level-neighborhood average gray level histogram is presented. Finally, a fast iterative algorithm for threshold selection that uses two-dimensional gray entropy is proposed. In addition, recursive algorithms are adopted to calculate the intermediate variables involved in criterion function, thereby avoiding their repetitive computation. Thus, calculating speed is accelerated and calculation amount is greatly reduced. A large number of experimental results show that, compared with three threshold segmentation methods, which have been recently presented, the proposed method has superior image segmentation performance. In the segmented image, object region is complete, edges are clear, and details are rich. Moreover, running time is short and is only approximately 3% of the running time of reciprocal entropy thresholding method with two-dimensional histogram oblique division based on niche chaotic mutation particle swarm optimization. The proposed method has obvious advantages in segmentation results and algorithmic running speed for various gray level images. It is a fast and effective segmentation method that can be used in practical systems.关键词：image segmentation;threshold selection;gray entropy;fast iteration3456|370|3更新时间：2024-05-07
- 摘要：Accurate visual guidance information is needed when unmanned underwater robots are implementing interactive tasks. Structured light measurement system is widely used in 3D reconstruction of an underwater target because its measuring accuracy is basically unaffected by light refraction and attenuation effects. However, the positioning of an underwater target becomes more difficult considering the underwater unstructured scenarios, the overlap and occlusion between a target and other underwater objects, and the single visual and scattered measurement data. For the problem of position estimation of an underwater man-made object, a 3D object localization algorithm is proposed based on the line feature of an image and the surface feature of a point cloud. Owing to the edge characteristics of the image and surface features of man-made objects, the proposed algorithm describes the object as a combination of line feature and surface feature, and the combination is provided for the localization algorithm as prior information. First, the whole field-of-view image is segmented into several regions of interest (ROIs) that contain different targets, and then the edges of the ROIs are detected. According to the specified line type in prior information, the feature lines are identified from the image edges of the ROIs. The position of the target in the whole field is confirmed with the region of potential target being selected on the basis of identification results. Second, the point cloud that was projected onto the object region is extracted based on the mapping relationship between the image and the point cloud of structured light measurement system. The random sample consensus algorithm is adopted to detect the surface feature from the extracted point cloud, which includes the points of the target, other partial objects, and noise in the field of view. Meanwhile, the parameters of the surface are approximated and the points of the target are extracted. Finally, taking superquadrics as the part-based model for the 3D object, a nonlinear objective function for the 3D object parameter estimation is established using the aforementioned initial approximations. Then, the objective function is minimized using target points, and the optimized parameters can be used as localization result. The reproducibility experiment indicates that the proposed algorithm for ellipse detection is robust; even semi-ellipses can be identified accurately. The validity of the proposed localization algorithm is verified through underwater experiments. For multi-targets whose symmetry axes are parallel to each other, the localization results show that the axis deviations are less than 2°. The relative position deviation of the two spheres, whose center distance is known, is no more than 1%. The time consumed for single-object localization in a complex underwater environment is no longer than 5 s. Unlike other localization algorithms, the proposed algorithm needs to neither segment the point cloud from the target scene nor target offline modeling. Autonomous positioning can be achieved by simply providing the line feature in target imaging edges and the contained surface feature. To verify the validity of the proposed algorithm, some practical experiments are performed. Experimental results show that the proposed algorithm can obtain accurate localization results, is fast and effective for a man-made object of unknown size, and has good applicability to complex underwater environments.关键词：machine vision;man-made object localization;ellipse detection;RANSAC;superquadrics2685|241|1更新时间：2024-05-07
- 摘要：A novel approach to coal pile location and recognition, which is based on entropy energy, is proposed in this paper to solve interference problems in a complex environment, which inhibit detection efficiency in coal mines. First, continuous information sampling units are scattered in the image, and the distribution area and gray levels of the larger probability density in the sampling unit are determined. All energy frequencies of the sampling unit are then calculated, the weakest of which is removed by filtration, and the edge of coal pile is calculated by second-order partial derivatives. The sampling unit is moved to the edge of the coal pile. Finally, the early warning based on the coal pile height and radius is ready for the upper limit, which is calculated according to the sampling unit. The average processing speed of the single image is 0.35 seconds per frame, the maximum of coal accident warning time interval is 0.35 seconds, and the average recognition accuracy is 97.1 percent, which is the method text results on the coal pile videos of coal mines. Experiments show that. This method can overcome the effects of noise and blurred image on the recognition of coal pile by taking advantage of the ability of entropy energy to identify a fuzzy edge and its resistance to environmental noise. Experiments show that the proposed approach has good adaptability to coal pile location and recognition, and is of significant and practical value to improve the efficiency and safety of coal mine production.关键词：coal pile image;entropy energy;sampling unit;energy frequency2503|258|2更新时间：2024-05-07
- 摘要：During object tracking, motion information can predict the location of the object. If motion information is ignored or motion is inaccurately modeled, then tracking may fail. To deal with this issue, we introduce visual saliency, which can quickly capture the interesting object, in tracking. Furthermore, we propose a tracking algorithm based on spatio-temporal motion saliency. First, we propose a bottom-up computational model for spatio-temporal motion saliency according to the hierarchical motion processing in the visual cortex. We adopt 3D spatio-temporal filters for the coding of underlying motion signals and max-pooling operation for the coding of local features. Considering the temporal relationship between the spatio-temporal motion features in the historical and current frames, we construct the spatio-temporal motion saliency map by measuring the difference between consecutive frames. Second, in the frame of particle filter, we measure the correlation between the predictive state and the observation by combining spatio-temporal motion saliency with color histogram. The object state can then be determined and tracked. Compared with other methods, our approach can stably track the objects under unfavorable situations, such as variable lighting, background clutter, motion blurs, occlusion, and deformation. We can improve the tracking performance in terms of central position error, precision, and success rate. In addition, we integrate the spatio-temporal motion saliency into other tracking methods and achieve better results, which demonstrates the effectiveness of the spatio-temporal motion saliency for object tracking. The spatio-temporal motion saliency can improve tracking performance as it measures motion information effectively, thereby enhancing the salient area and suppressing interference.关键词：visual saliency;object tracking;spatio-temporal filter;motion information3579|519|2更新时间：2024-05-07
- 摘要：Visual saliency, which is a relative property that depends on the degree of difference between a pixel or a region and its background, is difficult to obtain accurately. IG approach, a global-based contrast method, achieves good results on a public dataset. However, this method ignores important local details and inhibits contrast definition between target and background. Thus, this method needs to be improved in terms of the local details. This study proposes a novel saliency detection method based on global consistency and local difference, in which global contrast and local difference are considered two factors for saliency detection. In addition, the application of saliency characteristics to target segmentation is proposed and has achieved better experimental results. Different angles show different saliency characteristics. Thus, we compute image saliency from two angles: global feature and local details. The method consists of three basic steps. First, we detect the global consistency by IG, and the global saliency value of the target is achieved by the detection. However, to avoid ignoring the local details and inhibiting the contrast definition between the target and background,we propose the use of the NIF algorithm to overcome the drawbacks of IG. Second, we introduce the NIF method to detect the local difference of the target. Concretely, each pixel is the center pixel, and the square neighborhood of each center pixel is taken as its local scope. Thus, for every pixel, we can obtain corresponding local difference values in relation to its local scope. Finally, we derive the final saliency value by combining the saliency values that originate from the global and local contrasts. The saliency map produced by the proposed algorithm achieved a consistent effect compared with artificial segmentation map. To verify the efficiency of the proposed method, experiments are performed using MSRA-1 000 dataset, which is one of the largest public available datasets. Results show that our method outperforms several existing salient object detection methods in terms of precision, recall and F-feasure. In comparison with other popular algorithms, our algorithm has a higher efficiency in image segmentation. In this paper, we propose a novel saliency detection method, which treats an image as being composed of global consistency and local difference. We mainly focus on the problem of the local difference of the target and combine both global contrast and local difference for final saliency detection. Compared with some popular methods on a public dataset, our approach achieves the best results in terms of saliency measure evaluation. Furthermore, it obtains good performance in integrating saliency feature in image segmentation. Experimental results show that the algorithm can detect natural images more accurately and can be successfully applied to natural image segmentation.关键词：global consistency;local difference;visual saliency;similarity measure;target segmentation3489|277|1更新时间：2024-05-07
- 摘要：Texture classification,which is the key technology for computer vision and equipment monitoring, plays an important role in industrial production.Texture classification improves not only the efficiency of production but also product quality and reliability. For signal processing technology, a new method with a higher efficiency is provided for image texture classification. The projection of texture as a time domain signal is analyzed using empirical mode decomposition. The main projection direction is selected, and then two-dimensional signals are converted into one-dimensional signals by Radon transform. The end effects of the projection signal are restrained and divided into intrinsic mode functions (IMFs). After the statistical characteristics of the IMFs are calculated, they are compressed and simplified using principal component analysis to reduce their dimension. Once the effect of the principal characteristics is accessed with a support vector machine,classification is realized. Texture classification experiments are conducted in multiple directions and at multiple scales using Brodatz and KTH-TIPS datasets. A statemonitoring system for printing machines based on texture has been established. The calculation velocities of the proposed Radon-EMD, GLCM, and Gabor were compared using several Brodatz images, and the average times of the three texture analysis methods are approximately 5 s, 9.5 s, and 24 s, respectively. The study proved that IMFs of projection are good at texture classification and have the significant advantage of computational simplicity. This method obtains a good classification result in multiple directions and at multiple scales. Thus, the method has good computational efficiency.关键词：empirical mode decomposition;gray projection;texture classification;image characteristics;printing dots2243|219|2更新时间：2024-05-07
- 摘要：With the rapid development of spectral imaging technology in recent years, hyperspectral remote sensing images can provide abundant data on surface features. However,the sizable data of hyperspectral images make their storage, transmittal, and application quite difficult. As a result, how to validly code hyperspectral images has become a hot issue. The distributed source coding based on coset codes has received much attention because of its good compression performance and low coding complexity. In this study,we present a scheme for lossless distributed source coding of hyperspectral images based on adaptive quadtree segmentation. Assuming that the first frame in every group of spectrum frames is the key frame, the other frames are Wyner-Ziv frames. First, we perform adaptive quadtree segmentation on the key frame and then optimum linear prediction on each block of each Wyner-Ziv frame. Afterwards, the index of the coset codes to be transferred and the least significant bits of every pixel in this block are ascertained using prediction residuals. In this study, adaptive quadtree segmentation scheme has been proved to strengthen the adaptability of the formed coset codes. The proposed scheme can achieve a good compromise between coding efficiency and calculating complexity. This scheme is better able to meet the lossless coding requirement for hyperspectral images under low-complexity environment.关键词：hyperspectral remote sensing images;distributed source coding;quadtree segmentation;coset code;block information record;prediction2448|236|2更新时间：2024-05-07
- 摘要：Texture feature extraction has always been a hot topic and a source of difficulty in remote sensing image analysis. Most existing studies on texture feature extraction methods use single-band grayscale remote sensing images. How the texture feature can be extracted from a multi-band color remote sensing image is a relatively new field in multispectral remote sensing. The paper presents a color remote sensing image fractal dimension estimation method based on manifold learning. With the use of locally linear embedding, the 5D Euclidian hyperspace, which consists of color attributes, has been reduced, and then the reduced color attributes have been used for fractal dimension estimation. Experimental results on the Landsat-7 satellite data and GeoEye-1 satellite data show that the presented method has a smaller fitting error compared with other fractal dimension estimation methods. For instance, the average fitting errors, , of four other fractal dimension estimation methods are 26.2, 5, 26.3, and 5 times more than the average fitting error, , of the presented method. In addition, the presented method can provide not only a fractal dimension with better classification feature but also a more robust fractal dimension than the four other methods. For medium-and low-resolution true-color remote sensing images, medium-and low-resolution false-color remote sensing images, and high-resolution pan-sharpened remote sensing images, the presented method can use the color attribute information of different types of terrains to extract the corresponding texture feature information and then improve the ability of fractal dimension to distinguish different types of terrains. This work may prove useful to follow-up studies on the distributions of different types of terrains in several areas and further regional planning and development based on different distribution characteristics. Future research can add other spectra and analyze the effects of different spectral combinations on the effectiveness of the color texture feature.关键词：color texture analysis;color remote sensing image;fractal dimension;Manifold learning;feature extraction2429|513|0更新时间：2024-05-07
- 摘要：In recent years, the water surface area of Bosten Lake, which greatly influences local economic development, has exhibited significant fluctuations. To understand the water area variability of Boston Lake and its association with climate change, change analysis is conducted to provide information for the formulation of strategies that are necessary for the protection and sustainable management of the lake. First, a long temporal series of Landsat-5 TM, Landsat=7 ETM+, and Landsat 8 OLI, which consists of 25 scene images, was used to compute the surface area of Bosten Lake from 1988 to 2014. Radiometric, geometric, and atmospheric corrections were executed on the raw remote sensing images to obtain reflectance data, and then the modified normalized difference water index and Otsu image segmentation method were combined to separate water body information from the background in the images. The inter-annual changes and spatial changesin the lake surface area in the past 27 years were monitored and analyzed. Second, the effects of annual precipitation and annual mean temperature changes in Bosten Lake basin on the lake surface area were each investigated using meteorological data; the impact of human activities on the area changes with reference to existing research about the lake water resources was also examined. Third, to compare and verify the accuracy of the lake surface area results derived from the long temporal series of Landsat images,two additional data were used, namely, the lake surface area computed using MODIS images from 2000 to 2014 and the in situ measurement of the water level from 1987 to 2011 by the local water resources survey bureau. With 2002 as the dividing line, theinter-annual changes in the lake surface area that had occurred in the past 27 years can be divided into two stages. 1) From 1988 to 2002, the lake surface area showed a significantly increasing trend, with a total increase of 288.88 km(31.62%) and a mean annual increase of 20.63 km. 2) From 2002 to 2014, the lake surface area showed a sharply decreasing trend,with a total decrease of 281.56 km(23.42%) and a mean annual decrease of 23.46 km. According to the differences in the climatic condition distributions, the Bosten Lake basin was divided into the mountain area and the plain area. Analysis reveals that, from 1988 to 2002, the annual precipitation and annual mean temperature that occurred in the mountain area increased, which shows a significantly positive relationship with the lake surface area. Since 2002, a relative decline had been detected in the annual precipitation in the mountain area, whereas the annual mean temperature in the plain area had increased; water consumption by human activities increased. The lake surface area was affected by climate change, mainly in the mountain area, and human activities from 1988 to 2002. However, after 2002, temperature rise and water consumption increase may be the causes of the decrease in lake surface area.关键词：Bosten Lake;Landsat image;remote sensing monitor;lake surface area change4128|258|7更新时间：2024-05-07
- 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