XML
-
-
List of Articles
-
Open Access Article
1 - Modification of medium transfer detector for target tracking with variable radiation pattern
Payman Moallem عليرضا معمارمقدم جواد عباس پور masoud kavoshtehraniOne of the conventional methods in the field of image tracking of non-rigid targets is to use a repetitive procedure called average transfer in determining the central mode position of the target. The display of the target in the average transfer tracker is based on the MoreOne of the conventional methods in the field of image tracking of non-rigid targets is to use a repetitive procedure called average transfer in determining the central mode position of the target. The display of the target in the average transfer tracker is based on the histogram of spatial interpolation feature with a direction-independent kernel. The most critical challenge in the medium transfer detector is the kernel scaling. So far, no efficient and perfect method to adjust or adapt the kernel dimensions when the target dimensions change has been presented. Another problem of the average transmission detector occurs when facing a target with a variable radiation pattern. In this article, with the approach of solving these problems, the average transmission tracking algorithm with strong adaptive scaling is presented, while it solves the problem of the average transmission algorithm in the face of changes in the radiation pattern of the target by adapting the target model in each frame. In the proposed method, the dimensions of the window in the next frame are set first by using the power calculation method resulting from the time-space derivatives of the intensity of the image pixels. Then, the results of the window scaling in the next frame are applied to the average transfer detector. The results show that the use of the proposed algorithm, while reducing the target positioning error in comparison with the standard average transfer algorithm, also shows a significant efficiency against the changes of contrast 2 and target radiation pattern. Manuscript profile -
Open Access Article
2 - Determining optimal support vector machines in classification of hyperspectral images based on genetic algorithm
farhad samadzadegan Hadis Hasani۱٬۳۸۵ / ۵٬۰۰۰ Today, hyperspectral images are considered a powerful and efficient tool in remote sensing due to the wealth of spectral information and provide the possibility of distinguishing between similar complications. Considering the stability of support vector m More۱٬۳۸۵ / ۵٬۰۰۰ Today, hyperspectral images are considered a powerful and efficient tool in remote sensing due to the wealth of spectral information and provide the possibility of distinguishing between similar complications. Considering the stability of support vector machines in spaces with high dimensions, they are considered a suitable option in the classification of hyperspectral images. Nevertheless, the performance of these classifiers is influenced by their input parameters and feature space. In order to use support vector machines with the highest efficiency, the optimal values of the parameters and also the optimal subset of the input features should be determined. In this research, the ability of the genetic algorithm as a meta-heuristic optimization technique has been used in determining the optimal values of support vector machine parameters and also selecting the subset of optimal features in the classification of hyperspectral images. The practical results of applying the above method on the hyperspectral data of AVIRIS sensor show that the input features and parameters each have a great effect on the performance of support vector machines, but the best performance of the classifier is obtained by solving them simultaneously. In the simultaneous solution of parameter determination and feature selection, for Gaussian kernel and polynomial, 5% and 15% increase in accuracy was achieved by removing more than half of the image bands. Also, the gradual cooling simulation optimization algorithm was implemented in order to compare with the genetic algorithm, and the results indicate the superiority of the genetic algorithm, especially with the large and complicated search space in the simultaneous solution approach of parameter determination and feature selection. Manuscript profile -
Open Access Article
3 - Applying the combined SPIHT-DCT method using spatial and spatial-temporal scaling to encode video images
vahid Seirafian siamak talebiIn this paper, a hybrid encoder using two features of spatial scalability and spatio-temporal scalability is presented for high resolution video coding. In the combined method, Intra and Inter video frames are coded in two different ways. Intra frames are coded using SP MoreIn this paper, a hybrid encoder using two features of spatial scalability and spatio-temporal scalability is presented for high resolution video coding. In the combined method, Intra and Inter video frames are coded in two different ways. Intra frames are coded using SPIHT1 algorithm which is based on wavelet transform. Inter frames are coded in the usual MPEG-2 standard way and based on DCT conversion. By coding the video with a high degree of resolution in two ways: spatial scalability and spatial-temporal scalability, the video is sent through two or three layers. The data sent from the layers provide a video with different resolution and quality to the user. In this way, the user can choose the right service based on his needs. In spatial scalability, the base layer and the upgrade layer have the same coding structure. But in the spatio-temporal scalability of the second upgrade layer, because it only includes Inter frames, it is only coded based on the standard method. The results of the simulations performed on different videos with a high degree of resolution show the improvement of the final image quality in the proposed hybrid method with scalability in different layers, compared to the method based on the MPEG-2 standard. Manuscript profile -
Open Access Article
4 - Segmentation of exterior color images for the purpose of object recognition using histogram with double accuracy
javad rasti amirhasan Monjimie abbas vafaeiOne of the important issues in the automatic processing of external images is how to divide these images for the purpose of recognizing something in them. The special characteristics of these images, including color diversity, different light effects, the presence of co MoreOne of the important issues in the automatic processing of external images is how to divide these images for the purpose of recognizing something in them. The special characteristics of these images, including color diversity, different light effects, the presence of colored shadows, many texture details, and the existence of small and heterogeneous objects, make the problem of segmentation of external images, especially color segmentation, face serious challenges. In previous researches, a method based on the k-means clustering algorithm was proposed in a multi-accuracy bed for color clustering of external images for the purpose of primary segmentation. This method uses deliberate blurring of image textural details and removal of specific classes in blurred images and then added The classification of classes in images with higher accuracy showed a suitable performance for the initial segmentation of these images in comparison with the normal k-means method. In this article, an image-adaptive method using the ring histogram of the dark color to identify specific classes in blurred images in the bed is presented. It has been proposed with double precision. The efficiency of this algorithm has been investigated with the help of a supervised evaluation method on two databases of external images, which shows a 20% reduction in pixel error in segmentation, as well as a 30% higher accuracy and speed in the convergence of the clustering algorithm, indicating a higher quality. The proposed method is better than the normal method. Manuscript profile -
Open Access Article
5 - Reinforcement of the central axis of tubular structures and its application in extracting the central axis of the portal vein
amirhossein forouza reza aghaeizade یوشی¬نبو ساتو ماساتوشی هوریIn this article, by presenting a new description of the characteristic of the central axis points of tubular structures, a method to strengthen these structures is proposed. In this method, in a multi-scale framework and using special vectors of the Hessian matrix of th MoreIn this article, by presenting a new description of the characteristic of the central axis points of tubular structures, a method to strengthen these structures is proposed. In this method, in a multi-scale framework and using special vectors of the Hessian matrix of the image points, we obtain the distance of each point from the edges of the image. For the points located on the central axis, this distance from the bisector of any arbitrary direction is symmetrical. In this step, by sampling the distance of each point from the edges of the image in different directions, we assign a greater value to the points that have more symmetry. In the next step, we use a filter based on the Pock method to strengthen the central axis of the tubes. The evaluation of the proposed method has been done using two-dimensional and three-dimensional phantom images and medical data qualitatively and quantitatively with the criteria of maximum error in determining the central axis and detection rate, which shows the advantage of this method over the existing methods. Manuscript profile -
Open Access Article
6 - پردازش تصاویر ورق های فولادی به منظور آشکارسازی عیوب به کمک موجک گابور
Mostafa Sadeghie masoud shafieeIn different stages of steel production, many defects appear on the surface of the sheet. Regardless of the causes of failures, accurate detection of their types helps to correctly classify the steel sheet and thus occupies a high percentage of the quality control proce MoreIn different stages of steel production, many defects appear on the surface of the sheet. Regardless of the causes of failures, accurate detection of their types helps to correctly classify the steel sheet and thus occupies a high percentage of the quality control process. Quality control of steel sheets is of great importance in order to improve product quality and maintain a competitive market. In this article, while reviewing the used image processing techniques, by using image processing with the help of two-dimensional Gabor wavelet, a fast and high-accuracy solution is presented for revealing textural defects of steel sheets. At first, using Gabor wavelet, it extracts significant textural features from the images, which includes both different directions and different frequencies. Then, using the statistical method, the images that contain the defects are selected more clearly and the location of the defect is determined. By presenting test samples, the accuracy and speed of the method used have been shown. Manuscript profile
-
The rights to this website are owned by the Raimag Press Management System.
Copyright © 2017-2024