توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱AN UNSUPERVISED FAST COLOR TRANSFER METHOD
نویسنده(ها): ،
اطلاعات انتشار: سیزدهیمن کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۵
Each image has its own color that greatly influences the perception of human observer. In this paper, after a very brief review of the available literature on color transfer among color images, a novel fuzzy principle component analysis (FPCA) based color transfer method is proposed that uses an efficient fuzzy clustering method. Results show more robustness and higher speed when comparing the performance of the proposed method with other available approaches.<\div>

۲Text Segmentation From Images With Textured and Colored Background
نویسنده(ها): ،
اطلاعات انتشار: سیزدهیمن کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
In this paper, a method to segment the text regions from color images with textured background is proposed. The method is based on
finding the text edges using decomposed color information content of the subimage coefficients obtained from the discrete wavelet transformed
input images. Detected edges are then combined in order to form the exact location of the characters. In the next stage, the regions that are not
acceptable as the text regions (due to some general structural rules) are removed to improve the total performance. The final outputs of the algorithm are the characters on a smooth background. The experimental results show that the proposed method is robust to size, font, language, color and direction changes of the text regions.<\div>

۳A Fast and Efficient Wavelet–Based Active Contour Method
نویسنده(ها): ،
اطلاعات انتشار: چهارمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۴
In this paper, we propose a new method for fast and effective image segmentation using snakes (active contours). This method incorporates the active contour models with the wavelet transform features using directional edges in high and low frequency content sub–images. The proposed method takes advantages of these features to improve the boundary attraction process in active contour models. It also enhances the speed of image segmentation process by using a multi–scale approach. The analytical results show the efficiency of the proposed method in extraction of objects in images while performing the image segmentation at a higher speed compared to previously proposed active contour models.<\div>

۴Moving Cast Shadow Detection Using Texture Information
نویسنده(ها): ،
اطلاعات انتشار: دوازدهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۴
In this paper, we have proposed an efficient moving cast shadow detecti on using texture features. Texture features are estimated using fractal dimension and is employed to discriminate between shadow region and moving foreground region. Complexity and noise reduction is achieved using wavelet transform which has not been performed before in the literature. Block–wise calculation has accelerated the method. The proposed texture modeling method unlike most other approaches is able to cope with very dark shadows as well as light shadows<\div>

۵A New Objective Test Criterion for Multispectral Dimension Reduction Evaluation
نویسنده(ها): ،
اطلاعات انتشار: شانزدهیمن کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
In this paper, we have proposed an objective test criterion to investigate the performance of dimension reduction capability of multispectral images. We evaluate four transform–based satellite image dimension reduction methods by using this criterion. This transform are principal omponent analysis, real wavelet transform, complex wavelet transform, and contourlet transform. The proposed objective test method is based on computing some image feature parameters and comparing their associated destruction rate. We have clarified the efficiency of this objective test criterion by implementing the four mentioned methods on various multispectral data sets. The experimental results show the efficiency of the proposed objective test criterion.<\div>

۶MULTI–LAYER REPRESENTATION OF GRAYSCALE IMAGES AND ITS GENERALIZATION
نویسنده(ها): ،
اطلاعات انتشار: چهاردهمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
Thresholding is one of the earliest concepts developed in the image processing community. Many researchers have worked on the generalization of the thresholding problem as multithresholding. However, multithresholding only increases the number of threshold values used in the process. Here, we de ne multithresholding as computing layers which add up together to give better approximations of the given image. The paper contains comprehensive mathematical formulation of the problem and a proper solution to it. Simulation results show the ef ciency of the proposed algorithm.<\div>

۷New Principle Component Analysis Based Colorizing Method
نویسنده(ها): ،
اطلاعات انتشار: دوازدهیمن کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۸
Although many modern imaging systems are still producing grayscale images, colored–images are more preferred for the larger amount of information they are carrying. Computing the grayscale representation of a color image is a straightforward task, while the inverse
problem has no objective solution. The search through out literature has not revealed much history of the past works. In this paper, after a
brief review of related research, a new dimensionreduction method is proposed for natural color images and approved by both quantitative (PSNR) and subjective tests. Based on it a new class of colorizing methods is proposed and two sample formulations are presented, where the authors are aware of many other formulations available. Subjective test shows dominancy of our proposed
method when our method is much faster than others. Our method is leading in face image colorizing where other methods have failed. Such colorization method can be used greatly in medical image processing, surveillance systems, and information visualization.<\div>

۸A FAST VOP EXTRACTION TECHNIQUE BASED ON WAVELET TRANSFORM AND WATERSHED SEGMENTATION
اطلاعات انتشار: دوازدهیمن کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
In this paper, a very fast, noise robust and accurate video object plane (VOP) extraction algorithm based on wavelet transform and watershed segmentation techniques is proposed. The proposed algorithm firstly, applies the wavelet transform on incoming frames and uses the approximation coefficient matrix of the first level through out the algorithm. This not only increases the speed of the algorithm but also reduces the camera noise. The proposed method subsequently uses a prediction method to apply the watershed algorithm on those areas of the sub–image that might contain a moving object. This prediction stage increases the speed of the segmentation process efficiently. The experimental results show the superiority of the proposed algorithm when compared with other available schemes.<\div>

۹A Novel Vehicle Tracking Method with Occlusion Handling Using Longest Common Substring of Chain–Codes
نویسنده(ها): ،
اطلاعات انتشار: چهاردهمین کنفرانس بین المللی سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
Vehicle tracking is an essential requirement of any vision based Intelligent Transportation System for extracting different traffic parameters, efficiently. Handling inter–object occlusion is the most challenging part of tracking as a process of finding and following interested objects in a sequence of video frames. In this paper we present a system, based on code–book background model for motion segmentation and Kalman filter for tracking with a new approach for occlusion. This approach separates occluded vehicles based on longest common substring of chain codes. We use this tracking system to estimate some traffic parameters. Experimental results show the efficiency of the method<\div>

۱۰Cellular Learning Automata–Based Color Image Segmentation using Adaptive Chains
نویسنده(ها): ، ،
اطلاعات انتشار: چهاردهمین کنفرانس بین المللی سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
This paper presents a new segmentation method for color images. It relies on soft and hard segmentation processes. In the soft segmentation process, a cellular learning automata analyzes the input image and closes together the pixels that are enclosed in each region to generate a soft segmented image. Adjacency and texture information are encountered in the soft segmentation stage. Soft segmented image is then fed to the hard segmentation process to generate the final segmentation result. As the proposed method is based on CLA it can adapt to its environment after some iterations. This adaptive behavior leads to a semi content–based segmentation process that performs well even in presence of noise. Experimental results show the effectiveness of the proposed segmentation method<\div>

۱۱Real–Time Multiple Face Detection and Tracking
نویسنده(ها): ، ،
اطلاعات انتشار: چهاردهمین کنفرانس بین المللی سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
In recent years, processing the images that contain human faces has been a growing research interest because of establishment and development of automatic methods especially in security applications, compression, and perceptual user interface. In this paper, a new method has been proposed for multiple face detection and tracking in video frames. The proposed method uses skin color, edge and shape information, face detection, and dynamic movement analysis of faces for more accurate real–time multiple face detection and tracking purposes. One of the main advantages of the proposed method is its robustness against usual challenges in face tracking such as scaling, rotation, scene changes, fast movements, and partial occlusions.<\div>

۱۲Skin Detection using Contourlet Texture Analysis
نویسنده(ها): ، ،
اطلاعات انتشار: چهاردهمین کنفرانس بین المللی سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
A combined texture– and color–based skin detection is proposed in this paper. Nonsubsampled contourlet transform is used to represent texture of the whole image. Local neighbor contourlet coefficients of a pixel are used as feature vectors to classify each pixel. Dimensionality reduction is addressed through principal component analysis (PCA) to remedy the curse of dimensionality in the training phase. Before texture classification, the pixel is tested to determine whether it is skin–colored. Therefore, the classifier is learned to discriminate skin and non–skin texture for skin colored regions. A multi–layer perceptron is then trained using the feature vectors in the PCA reduced space. The Markov property of images is addressed in post–processing to join separate neighbor skin detected regions. Comparison of the proposed method with other state–of–the–art methods shows a lower false positive rate with a little decrease in true positive rate<\div>

۱۳Tensor–Based Face Representation and Recognition Using Multi–Linear Subspace Analysis
نویسنده(ها): ،
اطلاعات انتشار: چهاردهمین کنفرانس بین المللی سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
Discriminative subspace analysis is a popular approach for a variety of applications. There is a growing interest in subspace learning techniques for face recognition. Principal component analysis (PCA) and eigenfaces are two important subspace analysis methods have been widely applied in a variety of areas. However, the excessive dimension of data space often causes the curse of dimensionality dilemma, expensive computational cost, and sometimes the singularity problem. In this paper, a new supervised discriminative subspace analysis is presented by encoding face image as a high order general tensor. As face space can be considered as a nonlinear submanifold embedded in the tensor space, a decomposition method called Tucker tensor is used which can effectively decomposes this sparse space. The performance of the proposed method is compared with that of eigenface, Fisherface, tensor LPP, and ORO4×2 on ORL and Weizermann databases. Conducted experimental results show the superiority of the proposed method.<\div>

۱۴Adaptive Search Range Decision for Fast Intra– and Inter–Prediction Mode Decision in H.264\AVC
نویسنده(ها): ،
اطلاعات انتشار: دومین کنفرانس ملی مهندسی برق، سال
تعداد صفحات: ۶
H.264\AVC, the latest video coding standard, adopts rate–distortion optimization (RDO) technique to obtain the best intra– and inter–prediction, while maximizing visual quality and minimizing the required bitrate. However, the full RD cost calculation for all intra–prediction modes, the exhaustive searches for finding optimal motion vectors for all block sizes, and the multiple references frame procedure considerably increase its computational complexity with the allowed number of prediction modes. In order to reduce the complexity, the authors have previously proposed an approach for both interand intra–mode decisions that takes into account the several effective parameters, image content type, quantization parameter, correlation of motion vectors and motion details of video objects. In order to reduce the complexity, here we propose a new two–step adaptive search range decision by developing a combination of previous algorithm. The first step of our adaptive search range decision determines the search range for current MB according to the motion vectors of the previous MBs. In the second step, the motion vector obtained in the current frame is used to adaptively searching the window size of the previous reference frame for multi–frame motion estimation. As such, only a subset of inter– and intramodes is chosen for RDO calculation. Experimental results show that the proposed algorithm reduces the total encoding cost with negligible loss in PSNR and a slightly increase in the required bitrate, when compared to our previous algorithm and other algorithms reported in the literature.<\div>

۱۵Exemplar–Based Multi–resolution Image Completion
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۶
This paper presents a multi–resolution approach for completion and object removal of digital images using valid patches of the image. While the multi–resolution hierarchy provides a good ability to complete large holes in different resolutions, a priority–based best–first algorithm is used to refine the result at each level. It tries to maintain the content structure when estimating the texture inside the missing area. Also, in order to improve the quality of patch search, different patch sizes are employed for search and completion. Demonstrated experimental results show the efficiency of the proposed algorithm for a variety of input images in comparison with a number of recent works, but with relatively reduced computational complexity.<\div>

۱۶NOVEL METHOD FOR UNSUPERVISED FUZZY CHANGE DETECTION IN MULTISPECTRAL REMOTELY SENSED IMAGES
نویسنده(ها): ،
اطلاعات انتشار: سومین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۸
Analysis of the multi–spectral remotely sensed images of the areas destructed by an earthquake is proved to be a helpful tool for construction assessments. In this paper, we propose a new fast and reliable fuzzy change detection method for multi–spectral images. The proposed fuzzy change detection method is mathematically and experimentally investigated and shown to be efficient and effective.<\div>

۱۷a new fast robust color image watermarking method using FPCA clustering
نویسنده(ها): ،
اطلاعات انتشار: دهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۶
there is a genrally –accepted tendency to consider and process color images as a set of parallel gray –scale planes insteadof an ensemble of a 3–D realization. Although even now many researchers make the same assumption but it is proved that using vector geometries leads to more promising results in this paper by processing the color images as vector geometries a novel method is proposed to decompose a natural image into three eigenimages. based on the proposed eigenimage extraction method a new color image watermarking method is proposed<\div>

۱۸a new tree decomposition method for color images
نویسنده(ها): ،
اطلاعات انتشار: دهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۵
two decades ago quad–tree decomposition was proposed as a fast tool for decomposing an image into a set of homogenous rectangular regions since then many researchers have tried to generalize the method to enhance the results in thid paper a new tree decomposition method is proposed which uses the rectangular regions in a more adaptive way this paper gives a comprehensive performance comparsison between the quad–tree and the new proposed bi–tree decomposition methods.<\div>

۱۹fast registration of remotely sensed images
نویسنده(ها): ،
اطلاعات انتشار: دهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۷
the developents in remote–sensing technologies has offered new opportunities and applications in environmental monitoring in recent years researchers have focused on using this informacion to assess earthquake damages and afterwards reconstructions a crucial step in change detectionprocesses is to register the multi –spectral temporal images in this paper we propose a new fast and efficient PCA based method for remote sensing image registration. the proposed method works in realtime<\div>

۲۰new fast fuzzy method for query region extraction in color images
نویسنده(ها): ،
اطلاعات انتشار: دهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۸
finding the region similar to a given query region has many applications incomputer vision and computer graphics the first step towards an efficient query region extraction is to have a proper likelihood measure this issue has been neglected in the computer vision community and the researchers commonly used the euclidean distance for query region extraction in some standard color spaces in this paper we analyze the performance of the euclidean distancein 12 standard color spaces each one examined in 7 distinct possible representations. also we investigate the mahalanobis distance and the linear partial reconstruction error LPRE.<\div>

۲۱Line Scratch Detection and Restoration in Motion Picture Sequences
نویسنده(ها): ،
اطلاعات انتشار: یازدهمین کنفرانس مهندسی برق، سال
تعداد صفحات: ۸
In motion picture films, because of the contacts of the film with the mechanical parts of the camera or projector, some parts of the film emulsion may be removed which causes degradations in a line form, so called line scratches. During the re–projection, line scratches may produce an annoying effect on the viewer. In this paper, we will give a review on the existing methods for removing line scratches and then introduce a new method for detection and removal of them. Our method relies on morphological filtering methods for detection and polynomial interpolation for restoration of the line scratch areas<\div>

۲۲Error Concealment using Wide Motion Vector Space for H.264\AVC
اطلاعات انتشار: نوزدهمین کنفرانس مهندسی برق ایران، سال
تعداد صفحات: ۶
Due to fast growth of wireless mobile networks, video transmission over wireless media has been widely studied. As wireless networks are error prone, there is a high possibility of loss in sent packets. Since time limitations in real–time video applications should be met, the delay– related to resending packets –is not acceptable and the error should to be concealed at receiver side. With respect to different concealment methods, two new methods for temporal error concealment are proposed. In the first method, an optimized set of motion vectors is formed using motion vectors in surrounding blocks of the lost macroblock,and then this set is searched for the best motion vector.For extending the candidate vector set, two best vectors –chosen by a distortion measure–are combined. The second method utilizes the first method but a pre–process is required for determining a better set of motion vectors to be searched. The preprocess consists of searching the motion vectors of neighbouring blocks to determine the range of search space. Distortion measure for choosing the best motion vectors is the MSE. When the macroblocks are more independent this method results in much higher PSNR compared to previous methods<\div>

۲۳Robust H.264 Video Streaming Under Erroneous Transmission Conditions over GPRS Wireless Networks
نویسنده(ها): ، ،
اطلاعات انتشار: پنجمین کنفرانس بین المللی پیشرفتهای علوم و تکنولوژی، سال
تعداد صفحات: ۱۲
Channel errors have a very detrimental effect on the perceptual video quality. Despite the research done in the field of wireless multimedia, delivery of real–time interactive video over noisy wireless channels is still a challenge for researchers. This paper presents a method for improving the quality of video transport using H.264\AVC over wireless networks that is the prioritization of different parts of I– and P–frames. The effectiveness of the technique is demonstrated by examining its performance when the transport of the prioritized video streams can be accomplished using packet switching technology over the enhanced general packet radio service (GPRS) access network infrastructure<\div>

۲۴An Efficient Down–sampling Method for Multiresolution ImageCompletion
اطلاعات انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۷
Image completion is an active subject in image andvideo processing, which deals with recovering the missing orremoved parts of a given 2–D or 3–D data. Here, we present amethod to efficiently build the multiresolution pyramid for apartially–missing image, by which, multiresolution imagecompletion can be efficiently initialized and performed. Usingthis approach, we improve our previous algorithm formultiresolution image completion, especially when the inputssuffer spread missing areas. In comparison with the overallprocess of image completion, the computational and spacecomplexity of the proposed method for building multiresolutionpyramid is eligible. The obtained results of our proposedmethod show the effectiveness<\div>

۲۵Dynamic Temporal Error Concealment for Video Data in Error–prone Environments
اطلاعات انتشار: هشتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
Error concealment is a useful method forimproving the damaged video quality in the decoder side. In thispaper, a dynamic method with low computational complexity ispresented to improve the visual quality of videos when up to 50%of the frames are damaged. In the proposed method, temporalreplacement and the improved outer boundary matchingalgorithm are used for dynamical error concealment in interframesof videos. With the use of motion vectors (MVs) which areclose to the damaged macroblock (MB) the method can determinewhether the motion in specific areas is either regular, irregular,or zero. Then, based on this knowledge, different methods areperformed. It adaptively selects a set of candidate MVs andexternal boundaries for comparison purposes. Furthermore, toincrease the accuracy, depending on the correctness of adjacentMVs, a specific weight is given to the boundaries of adjacentMBs. Experimental results show that the proposed methodenhances both objective and subjective quality of damagedframes without any considerable increase in complexity. Theaverage PSNR in some frames of test sequences has increasedabout 1.01 dB more than the outer boundary matchingalgorithm.<\div>
نمایش نتایج ۱ تا ۲۵ از میان ۲۶ نتیجه