List of Articles
-
Open Access Article
1 - Using Prominent Regions in Search Space Reduction for Recognition of Printed Farsi Subwords
H. Davoudi E. KabirIn the most common Lexicon reduction methods, lexicon words are clustered based on their holistic shape features and then each query word image is classified into the closest cluster. As the errors at this stage propagate to the subsequent stages, relevant clusters shou MoreIn the most common Lexicon reduction methods, lexicon words are clustered based on their holistic shape features and then each query word image is classified into the closest cluster. As the errors at this stage propagate to the subsequent stages, relevant clusters should be selected with a high degree of accuracy. In this paper we present a novel verification method which decides on the validity of the recognized clusters based on a proposed confidence measure. The level of confidence to the selected clusters is measured using local shape features in the verification phase, where it is determined that the selected cluster is acceptable or not. For this purpose, some local shape features of the input subword image are compared to the “prominent regions” of the corresponding cluster. The prominent regions of a cluster are some local regions that discriminate the members of that cluster compared to the other clusters. The proposed verification method along with some predefined rules is used to reduce the lexicon size of Farsi subwords. The experiments conducted on a set of 6895 common Farsi subwords show that our proposed method significantly reduces the search space while preserving the accuracy in an acceptable rate. Manuscript profile -
Open Access Article
2 - A Hybrid Algorithm for Terrain Simplification
F. Dabaghi Zarandi Mohammad GhodsiTerrain simplification problem is one of fundamental problems in computational geometry and it has many applications in other fields such as geometric information systems, computer graphics, image processing. Terrain is commonly defined by a set of n points in three dim MoreTerrain simplification problem is one of fundamental problems in computational geometry and it has many applications in other fields such as geometric information systems, computer graphics, image processing. Terrain is commonly defined by a set of n points in three dimension space. Major goal of terrain simplification problem is removing some points of one terrain so that maximum error of simplified surface is a certain threshold. There are two optimization goals for this problem: (1) min-k, where for a given error threshold , the goal is to find a simplification with the minimum number of points for which the error is that most , and (2) min-, where for a given number n, the goal is to find a simplification of at most m points that has the minimum simplification error. Simplification problem is NP-hard in optimal case. In this paper we present a hybrid algorithm for terrain simplification that performs in three phases. First, terrain is divided to some clusters, then any cluster is simplified independently and finally, the simplified clusters are merged. Our algorithm solves the problem in . The proposed algorithm is implemented and verified by experiments. Manuscript profile -
Open Access Article
3 - Left Ventricular Segmentation in Echocardiography Images by Manifold Learning and Dynamic Directed Vector Field Convolution
N. Mashhadi H. Behnam Ahmad Shalbaf Z. Alizadeh SaniCardiac diseases are the major causes of death throughout the world. The study of left ventricular (LV) function is very important in the diagnosis of heart diseases. Automatic tracking of the boundaries of the LV wall during a cardiac cycle is used for quantification o MoreCardiac diseases are the major causes of death throughout the world. The study of left ventricular (LV) function is very important in the diagnosis of heart diseases. Automatic tracking of the boundaries of the LV wall during a cardiac cycle is used for quantification of LV myocardial function in order to diagnose various heart diseases including ischemic disease. In this paper, a new automatic method for segmentation of the LV in echocardiography images of one cardiac cycle by combination of manifold learning and active contour based dynamic directed vector field convolution (DDVFC) is proposed. In this method, first echocardiography images of one cardiac cycle have been embedded in a two dimensional (2-D) space using one of the most popular manifold learning algorithms named Locally Linear Embeddings. In this new space, relationship between these images is well represented. Then, segmentation of the LV wall during a cardiac cycle is done using active contour based DDVFC. In this method, final contour of each segmented frame is used as the initial contour of the next frame. In addition, in order to increase the accuracy of the LV segmentation and also prevent the boundary distortion, maximum range of the active contour motion is limited by Euclidean distances between consequent frames in resultant 2-D manifold. To quantitatively evaluate the proposed method, echoacardiography images of 5 healthy volunteers and 4 patients are used. The results obtained by our method are quantitatively compared to those obtained manually by the highly experienced echocardiographer (gold standard) which depicts the high accuracy of the presented method. Manuscript profile -
Open Access Article
4 - Color Reduction of Hand-painted Carpet Patterns Before Discretization
M. Fateh E. KabirCarpet patterns are in two categories: machine-painted and hand-painted. Hand-painted patterns are divided into two groups: before and after discretization. The purpose of this study is color reduction of hand-painted patterns before discretization. There are some artic MoreCarpet patterns are in two categories: machine-painted and hand-painted. Hand-painted patterns are divided into two groups: before and after discretization. The purpose of this study is color reduction of hand-painted patterns before discretization. There are some articles about color reduction of hand-painted carpet patterns after discretization, but so far, there is not an article on patterns before discretization. The proposed algorithm consists of the following steps: image segmentation, finding the color of each region, color reduction around the edges and final color reduction with C-means. For 80 segments of different 20 patterns, the algorithm has an approximate of 96% accuracy. In other words, the colors of 96% of image pixels are found correctly. The high accuracy of this method is due to its fitness to the application. The proposed method is not fully automatic and requires the total number of colors as its input. Manuscript profile -
Open Access Article
5 - The Effects of SIP Register Flood Attack and Detection by Using Kullback–Leibler Distance
S. R. Chogan M. Fathy M. RamezaniVoice communications through internet uses VOIP which includes several protocols while its secrecy is very important issue. SIP is the most important signaling protocol whose attack detection may help system immunization. This paper is dedicated to the issue of SIP regi MoreVoice communications through internet uses VOIP which includes several protocols while its secrecy is very important issue. SIP is the most important signaling protocol whose attack detection may help system immunization. This paper is dedicated to the issue of SIP registration flood attacks. Attackers can send registration signals which have several dangers for registration server. In this paper, SIP register flood attacks is investigated by details and the effects of attack over registration server is illustrated. Finally, the effects of attack, regarding the ratios compared with a regular situation of the network, are evaluated in experiments done in a real network. Moreover, instead of Hellinger distance, Kullback–Leibler distance is used for register flood attacks detection and corresponding ROC curves show this approach has better performance. Manuscript profile -
Open Access Article
6 - Sub-Threshold 8T SRAM Cell with Improved Write-Ability and Read Stability
Gh. Pasandi S. M. FakhraieConventional 6T SRAM cell suffers from poor write-ability and poor read stability at low supply voltages. In this paper a new 8T SRAM cell is proposed that achieves improved write-ability and increased read stability at the same time. The proposed SRAM cell can successf MoreConventional 6T SRAM cell suffers from poor write-ability and poor read stability at low supply voltages. In this paper a new 8T SRAM cell is proposed that achieves improved write-ability and increased read stability at the same time. The proposed SRAM cell can successfully operate at small supply voltages as low as 275 mV whereas conventional 6T SRAM cell cannot. To show the prominence of the proposed cell and for better comparison, our SRAM cell, conventional 6T SRAM cell, and also three other SRAM cells from recent literature are designed in a 90nm industrial CMOS technology with the same conditions. Simulation results show that the proposed 8T SRAM cell decreases write and read delays by 47.5% and 50%, respectively at supply voltage of 800 mV. Our SRAM cell also improves power consumption for single write operation by 40% over the best design at supply voltage of 800 mV. Among the five designs compared, our design is the only one that operates at supply voltages as low as 275 mV. Finally, layout of the proposed SRAM cell is developed in 180 nm industrial CMOS technology and results of post-layout simulations are discussed. Manuscript profile -
Open Access Article
7 - Throughput Optimization in a Broadcast Network Using Adaptive Modulation, Coding and Transmit Power Provisioning Security Constraint
M. TakiA new transmission scheme is presented to improve utilization of resource in a broadcast network provisioning physical layer security. In the designed scheme, data of each user is only detectable at its corresponding receiver with a proper bit error rate (BER), while de MoreA new transmission scheme is presented to improve utilization of resource in a broadcast network provisioning physical layer security. In the designed scheme, data of each user is only detectable at its corresponding receiver with a proper bit error rate (BER), while detection BER at other unintended receivers is high enough for improper detection. Adaptive modulation, coding and transmit power is utilized based on the SNRs. Exact and approximate solutions for the formulated problem are presented where approximate solution has acceptable complexity and leads to the comparable results with the exact solution. Numerical evaluations show that a performance degradation is seen at the cost of providing security. Manuscript profile -
Open Access Article
8 - Select the Optimal Subset of LABP Features Based on CLA-EC Method in Face Recognition System
A. Hazrati Bishak K. Faez H. Barghi Jond S. GhateiIn this paper, we present a new efficient method based on local binary pattern descriptor, for face recognition. Because, the calculations in Local binary pattern are done between two pixels values, so, small changes in the binary pattern affect its performance. In this MoreIn this paper, we present a new efficient method based on local binary pattern descriptor, for face recognition. Because, the calculations in Local binary pattern are done between two pixels values, so, small changes in the binary pattern affect its performance. In this paper, a new local average binary pattern descriptor is presented based on cellular learning automata and evolutionary computation (CLA-EC). In the proposed method, first, the LABP operator are used to extract uniform local binary patterns from face images; it should be noted that, in LABP operator to obtain more robust feature representation, many sample points has been used. Then, the best subset of patterns found by CLA-EC methods, and the histogram of these patterns is obtained. Finally, support vector machine is used for classification. The results of experiment on FERET data base show the advantage of the proposed algorithm compared to other algorithms. Manuscript profile -
Open Access Article
9 - Spectral Shaping of Reconstruction Noise in Backward ADPCM Coding
قاسم علیپور محمدحسن ساوجیThe main idea in ADPCM coding is to remove the redundancies of the speech signal before quantization. One of the important characteristics of this coding scheme is the spectral flatness of the reconstruction noise in spite of its low level. It has been tried, in the pre MoreThe main idea in ADPCM coding is to remove the redundancies of the speech signal before quantization. One of the important characteristics of this coding scheme is the spectral flatness of the reconstruction noise in spite of its low level. It has been tried, in the present research, to improve the perceptual quality of the reconstructed signal by shaping the spectrum of the reconstruction noise using an all-zero filter in the backward ADPCM coding. By doing so, a useful compromise is achieved between the level and the spectral shape of the reconstruction noise. The obtained results show an improvement in the perceptual quality of the reconstructed signal (higher PESQ score) and an increase in the noise level (lower SNR). Manuscript profile