توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱A Novel Iris Segmentation Method based on Balloon Active Contour
اطلاعات انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
Image segmentation is a tool which is widely used in many applications related to image processing, and it comprises one of the most difficult steps of the process. This matter becomes more significant when we try to use the algorithms presented in complicated systems, such as the identity recognition systems. Different methods of image segmentation have been presented so far. In this article, a twostep algorithm has been proposed for iris segmentation. In the first step, a median filter has been applied to eliminate the noise, and in the next step, the modified active contour has been used for iris segmentation. The proposed algorithm was tested on the CASIA image data base and the obtained results showed that the proposed method has an acceptable accuracy.<\div>

۲A Novel Iris Recognition System based on Greedy–Balloon SnakeAlgorithm
اطلاعات انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر، سال
تعداد صفحات: ۵
A biometric system provides automatic identificationof an individual based on unique features or characteristicspossessed by the individual. Iris recognition is regarded as themost reliable and accurate biometric identification systemavailable. The pattern of the human iris differs from person toperson. The most important step in the iris recognition system isthe segmentation process. Different methods of irissegmentation have been presented so far. In this paper a noveltype of active contour has been developed which can beemployed in iris segmentation. In fact, the proposed method is acomposition of the greedy snake algorithm and the balloonactive contour. The novel active contour has been named greedy– balloon. Both of the greedy and balloon active contours havemore advantages than traditional active contour. That is whywe used this active contour for our research. The proposedalgorithm was tested on the CASIA Iris Image Database 1.0 andthe obtained results showed that the proposed method has anacceptable accuracy.<\div>

۳A Novel Iris Recognition System Based on Active Contour
اطلاعات انتشار: هفدهمین کنفرانس مهندسی پزشکی ایران، سال
تعداد صفحات: ۴
Image segmentation is a method which is widely used in image processing application, and it is one of the most difficult steps of the process. This matter becomes more significant when we try to use the algorithms presented in complicated systems, such as the biometric systems. Different methods of iris segmentation have been presented so far. In this article, a new algorithm has been proposed for iris segmentation. We tried to use the greedy snake algorithm for the iris segmentation process. The proposed algorithm was tested on the CASIA Iris Image Database 1.0 and the obtained results showed that the proposed method has an acceptable accuracy.<\div>

۴Pattern Recognition using Adaptive Convolutional Neural Network
نویسنده(ها): ،
اطلاعات انتشار: هفتمین کنفرانس ملی مهندسی برق و الکترونیک ایران، سال
تعداد صفحات: ۷
Deep learning is an appreciate framework to deal with high–level data in order to find meaningful relationships between the features of the data. One of the well–known architecture of deep learning scheme is Convolutional Neural Network (CNN) which includes one or more convolutional layers with fully connected layers. Despite of the abilities of CNN, it suffers from parameter setting where the parameters with different values have high impacts on the performance of CNN. In this paper, parameter adaptation of CNN using new metaheuristic algorithm is proposed. The used metaheuristic algorithm is Harmony Search (HS) which is improved in this paper. Finally, the proposed method which is name Adaptive Convolutional Neural Network (ACNN) is applied on handwritten digit recognition field. Experimental results on MNIST dataset prove the superiority of the proposed ACNN to CNN.<\div>

۵An Automated Lumen Contour Segmentation In Intravascular Ultrasound Images Using An Efficient Variational Approach
نویسنده(ها): ، ،
اطلاعات انتشار: اولین کنفرانس بین المللی دستاوردهای نوین پژوهشی در مهندسی برق و کامپیوتر، سال
تعداد صفحات: ۵
Intravascular ultrasound (IVUS) is a minimally invasive medical imaging that produces cross–sectional images of blood vessels. IVUS processing could help experts to put in accurate diagnosis and proper treatment by measuring stenosis size, and the disposal location. Lumen border detection in IVUS images represents a necessary step just before the reliable quantitative valuation of atherosclerosis. In this work an automated technique is proposed for the lumen border detection in IVUS images. At first a novel variational minimax algorithm is used to make local threshold. Then simple classifier classified threshold to extract lumen border. The method is validated through a comparison with expert manual segmentation on a challenging database and compared with recent methods for the lumen border detection in IVUS. The obtained averaged values for the mean Hausdorff distance and the percentage of Jaccard similarity index are 0.361mm and 95.0%, respectively.<\div>

۶A Low–Voltage, Low–Power, Two–Stage Amplifier for Switched–Capacitor Applications in 90 nm CMOS Process
نویسنده(ها): ،
اطلاعات انتشار: Iranian Journal of Electrical and Electronic Engineering، ششم،شماره۴، Dec ۲۰۱۰ ، سال
تعداد صفحات: ۶
novel low–voltage two–stage operational amplifier employing resistive biasing is presented. This amplifier implements neutralization and correction common mode stability in second stage while employs capacitive dc level shifter and coupling between two stages. The structure reduces the power consumption and increases output voltage swing. The compensation is performed by simple miller method. For each stage an independent common–mode feedback circuits has been used. Simulation results show that power consumption is 2.1 mW at 1V supply. The dc gain of the amplifier is about 70 dB while its output swing is as high as around 1.2V.
نمایش نتایج ۱ تا ۶ از میان ۶ نتیجه