جستجوی مقالات مرتبط با کلیدواژه « similarity measure » در نشریات گروه « برق »

Image registration is a fundamental issue in medical image analysis. It refers to the matching process between two or more images using the optimization of a similarity metric to find an optimal transformation function. In recent decades, many studies have been done on the medical image registration topic. Therefore, this paper has investigated four main methodologies to solve the registration problem in medical applications. One of the most important topics in this area is the registration of multi-modal images. In this paper, we have reviewed various multimodal image registration techniques based on deep learning and proposed a classification for these methods. Also one of the essential components of the medical image registration framework is the similarity measure function. There are different similarity metrics in this area and choosing an appropriate measure according to the application is a challenging problem. This paper is to present a review of different similarity measures in medical applications and a classification of these methods. Based on this classification, techniques are investigated and each subclass is evaluated using performance criteria. Therefore, the main goals of this article are as follows: 1) Investigating the most significant image registration approaches. 2) Systematic review of deep learning-based multimodal medical image registration and classify them. 3) Providing classification for various similarity measure techniques according to registration applications. 4) Creating an appropriate platform for evaluating these approaches and introducing the main challenges.

This paper proposes an approach to improve color images suffering from low dynamic range, by employing both histogram matching and histogram stretching techniques. Firstly, the color image is transformed from RGB into HSV color space, in which the color information is separated from intensity. Then, an appropriate reference image is selected by comparing component V of the enhancing image with component V of the data base images using a similarity measure. This selected image is used as the goal image in histogram matching algorithm in order to enhance image brightness (Automatic Histogram Matching). Secondly, components V and S are linearly stretched in order to recover the image color information. Finally, using the treated V and S components and untreated component of H, the enhanced image is obtained in RGB color space by inverse transform. The qualitative and quantitative results show that the contrast and color of resultant images are greatly improved using the proposed method, which outperforms the current state-of-the-art methods.

State-of-the-art researches in unsupervised automatic keyphrase extraction focused on graph analysis. Keyphrase ranking is critical step in graph-based approaches. In this paper, we follow two main purposes including choice of good candidate phrases and computing importance of candidate phrase by considering the mutual information between words. Our documents representation improves the process of candidate phrases selection by constructing a single graph for all documents in the collection. We enjoy from parallel minimum spanning tree to prune irrelevant edge relations. We also consider second order co-occurrence of words by point-wise mutual information as a similarity measure and importance of terms to increase the performance of keyphrase ranking. We formed a single graph of cooccurrence network for all documents in the collection and analyze co-occurrence network with different settings. We compare our method with three baseline approaches of keyphrase extraction. Experimental results show that applying second order co-occurrence analysis improves keyphrases identification accuracy.

Due to increasing criminal activities by anonymous E-mails in the cyber world, it is a challenging task to extract beneficial knowledge from E-mail systems. This problem in cyber world attracts many researchers in cyber-crime domain. Recent studies in this area concentrate on traditional classification approaches such as Decision Tree and Support Vector Machines (SVM). These approaches are employed to identify the author. The main goal of these researches is increasing the accuracy of identification, but the quality of evidence is ignored and also it is hard to be traced. So, in this paper, we propose a new approach based on data mining methods for improving the quality of evidence which leads to boost the accuracy of identification. We use writeprints as the evidence and extract them from each E-mail of individuals. The next step for author identification, is matching the writeprints with anonymous E-mails by applying Earth Mover Distance (EMD) criterion to identify the plausible author. In addition to high accuracy, EMD can help cybercrime investigators in making decision about anonymous intruder. Experiments with real data in both English and Persian languages, demonstrate the proposed approach can effectively identify the author and capture strong evidence to prove the identification.

This paper proposed a Fuzzy monotonic inclusion (FMI) approach in order to measure similarity between images. Firstly, an image is segmented to several regions, then each region is described by a fuzzy set. Finally, extracted features from each region are mapped into a fuzzy similarity model. FMI scheme makes relation between regions and based on the relations, the regions are selected for the comparison process. Thus, for every image region, both parameters of fuzzy location and area is extracted. We investigated FMI From the conceptual point of view and Semantic relation among Objects. The experimental results on Label Me database, a real world image dataset including 163,000 images, show superiority of the FMI in compared with UFM and Fuzzy Histogram.

Today, with the advent of digital imagery, the volume of digital images has been growing rapidly in different fields. So, there is an increasing need for providing an effective image retrieval system. In this paper, a semi-supervised k-means clustering method was introduced for image database clustering and image annotation. One of the most important parts of image clustering algorithms is to determine similarity of the images. To compute exact similarity measures, a new CM similarity measure was proposed here to make normalized and weighted features simultaneously so that similarity measure exploits normalized or weighted features in its formula to reach better performance. However, due to semantic gap, some images may be false clustered. A hybrid of three relevance feedback (RF) schemes was used to improve the accuracy of image clustering. (1) The images with the user who knows their irrelevance to a cluster were conducted to correct cluster by a long-term RF. (2) With regard to the images with the user who knows they are relevant to a cluster, feature weight of the clusters was estimated in order to provide a multiple similarity measure using a re-weighting RF. (3) To discover the exact place of the cluster centers, a cluster center movement (CCM) RF was used. Experimental results based on the Corel database including 1000 images and a satellite image database of Tehran city including 2400 images demonstrated the superiority of the proposed method in image database clustering.