Sharif Digital Repository

Nowadays, OCR (Optical Character Recognition) is widely used for converting written documents to digital documents. One of the OCR phases is page segmentation. In page segmentation, text regions must be found in input image. In addition, text parts like text columns must be separated. In this paper, a new method for segmenting Persian/Arabic printed text is proposed. This method is based on Ink Spread Effect idea, a new idea that has particular features. Main features of Persian/Arabic scripts are considered in designing this method. This method is skew resistant and can segment text within frames and tables or regions with gray background. © 2006 ICASE  

Integral imaging could be considered as one of the prospective methods for recording and displaying 3D images based on its distinct features. Some of the most important challenges with this approach are the field of view and resolution limitation. In this work we investigate using frequency division multiple access (FDMA) idea for solving this problem. Simulation results show an increase of more than ten percent in the performance of the 3D reconstructed images using the proposed method  

In this paper, a novel approach for foreground extraction has been proposed based on a popular three-dimensional imaging technique in optics, called integral imaging. In this approach, multiple viewpoint images captured from a three-dimensional scene are used to extract range information of the scene and effectively extract an object or a person, even in the presence of heavy occlusion. The algorithm consists of two parts: depth estimation and reconstruction of the targeted object at the estimated depth distance. Further processing of the resulting reconstructed image can lead to the detection of a face or a pedestrian in the scene, which may not otherwise be detectable due to partial... 

In many fast MR imaging techniques, K-space is sampled sparsely in order to gain a fast traverse of K-space. These techniques use non-Cartesian sampling trajectories like radial, zigzag, and spiral. In the reconstruction procedure, usually interpolation methods are used to obtain missing samples on a regular grid. In this paper, we propose an iterative method for image reconstruction which uses the black marginal area of the image. The proposed iterative solution offers a great enhancement in the quality of the reconstructed image in comparison with conventional algorithms like zero filling and neural network. This method is applied on MRI data and its improved performance over other methods... 

In this paper, a closed-form two-dimensional reconstruction technique for hybrid frequency and mechanical scanning millimeter-wave (MMW) imaging systems is proposed. Although being commercially implemented in many imaging systems as a low-cost real-time solution, the results of frequency scanning systems have been reconstructed numerically or have been reported as the captured raw data with no clear details. Furthermore, this paper proposes a new framework to utilize the captured data of different frequencies for three-dimensional (3D) reconstruction based on novel proposed closed-form relations. The hybrid frequency and mechanical scanning structure, together with the proposed... 

During the past two decades, the lattice Boltzmann (LB) method has been introduced as a class of computational fluid dynamic methods for fluid flow simulations. In this method, instead of solving the Navier Stocks equation, the Boltzmann equation is solved to simulate the flow of a fluid. This method was originally developed based on uniform grids. However, in order to model complex geometries such as porous media, it can be very slow in comparison with other techniques such as finite differences and finite elements. To eliminate this limitation, a number of studies have aimed to formulate the lattice Boltzmann on the unstructured grids. This paper deals with simulating fluid flow through a... 

In this research we have proposed a new definition for three-dimensional (3-D) integral imaging resolution. The general concept of two-dimensional (2-D) resolution used also for 3-D is failed to describe the 3-D resolvability completely. Thus, the researches focused on resolution improvement in 3-D integral imaging systems, didn't investigate thoroughly the effect of their method on the 3-D quality. The effect has only been shown on the 2-D resolution of each lateral reconstructed image. The newly introduced 3-D resolution concept has been demonstrated based on ray patterns, the cross-section between them and the sampling points. Consequently the effect of resulting sampling points in 3-D... 

In this paper, a Kalman filter technique which is operated in time is introduced for noise reduction on CT set of projections to reconstruct medical images. The experiments were done on medical image of kidneys and the simulated projections are captured by CT scanner. Evaluation results indicated that as the number of projections increase in the collected ray sums corrupted by noise the quality of reconstructed image becomes better in terms of contrast and transparency. However, for the comparison issue, the same conditions are applied for reconstruction of medical image in frequency domain using filter back projection technique. It observes that filter back projection technique does not... 

Inpainting refers to the task of filling in the missing or damaged regions of an image in an undetectable manner. We have an image to be reconstructed in a user-defined region. We use a fast decomposition method to obtain two components of the image, namely structure and texture. Reconstruction of each component is performed separately. The missing information in the structure component is reconstructed using a structure inpainting algorithm, while the texture component is repaired by a texture synthesis technique. To obtain the inpainted image, the two reconstructed components are composed together. Taking advantage of both the structure inpainting methods and texture synthesis techniques,... 

A novel CT imaging structure based on Compressive Sensing (CS) is proposed. The main goal is to mitigate the CT imaging time and, thus, X-ray radiation dosage without compromising the image quality. The utilized compressive sensing approach is based on radial Fourier sampling. Thanks to the intrinsic relation between captured radon samples in a CT imaging process and the radial Fourier samples, partial Fourier sampling could be implemented systematically. This systematic compressive sampling helps in better control of required conditions such as incoherence and sparsity to guarantee adequate image quality in comparison to previous CS-based CT imaging structures. Simulation results prove the... 

Continuous-domain visual signals are usually captured as discrete (digital) images. This operation is not invertible in general, in the sense that the continuous-domain signal cannot be exactly reconstructed based on the discrete image, unless it satisfies certain constraints (e.g., bandlimitedness). In this paper, we study the problem of recovering shape images with smooth boundaries from a set of samples. Thus, the reconstructed image is constrained to regenerate the same samples (consistency), as well as forming a shape (bilevel) image. We initially formulate the reconstruction technique by minimizing the shape perimeter over the set of consistent binary shapes. Next, we relax the... 

In this paper, we propose an algorithm for recovery of sparse and low-rank components of matrices using an iterative method with adaptive thresholding. In each iteration of the algorithm, the low-rank and sparse components are obtained using a thresholding operator. The proposed algorithm is fast and can be implemented easily. We compare it with the state-of-the-art algorithms. We also apply it to some applications such as background modeling in video sequences, removing shadows and specularities from face images, and image restoration. The simulation results show that the proposed algorithm has a suitable performance with low run-time. © 2017 Elsevier Inc  

In this study, a thorough analysis of image reconstruction in an active millimetre-wave (MMW) cylindrical imaging system is performed. To improve the system's performance in terms of the total cost as well as the coupling effect, sparse multistatic arrays are desired. Nevertheless, the existing reconstruction methods fail to operate in sparse multi-static antenna-array systems. Therefore, to address these shortcomings, in this study, at first, the existing MMW mono-static cylindrical image reconstruction methods are modified in both single-frequency and wideband reconstruction platforms. Moreover, in order to further improve the image quality and the system cost, a sparse multi-static... 

In this paper, the performance of the sparse reconstruction (SR) and the delay-and-sun (DAS) methods for damage localization, were evaluated for various environmental and operational conditions, both numerically and experimentally. To assess these damage localization methods, a methodology based on the Taguchi method was used to make the experimental design, and a modified performance-index was defined to represent the quality of reconstructed images. Then, the robustness and the accuracy of each method, in a well-defined performance region relevant to in-service aerospace structures, were investigated using the Taguchi and analysis of variance methods. It was concluded that for the defined... 

In this paper, the relationship between the position of ultrasound transducers from the photoacoustic source and the reconstructed image is investigated. Our studies have shown that the distance of the transducer and its location from the photoacoustic source specifically affects and is closely related to the quality of the reconstructed image of the source. Also, we introduce a concept called blind angle for photoacoustic computed tomography (PACT) that have planar or circular limited-view geometry. Complete and accurate equations of this relationship are presented in this paper for all different 2D photoacoustic geometries. The main source of these equations is the spherically of the... 

During the past two decades, the lattice Boltzmann (LB) method has been introduced as a class of computational fluid dynamic methods for fluid flow simulations. In this method, instead of solving the Navier Stocks equation, the Boltzmann equation is solved to simulate the flow of a fluid. This method was originally developed based on uniform grids. However, in order to model complex geometries such as porous media, it can be very slow in comparison with other techniques such as finite differences and finite elements. To eliminate this limitation, a number of studies have aimed to formulate the lattice Boltzmann on the unstructured grids. This paper deals with simulating fluid flow through a... 

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods... 

Electrical Impedance Tomography (EIT), is one of the medical imaging technologies. It can also be used in industrial process monitoring. In this method, the image of the electrical conductivity distribution of the inner part of a conductive subject can be reconstructed. The image reconstruction process is done by injecting an accurate current into the boundary of a conductive subject (e.g. body), measuring the voltages around the boundary and transmitting them to a computer, and processing on acquired data with a software (e.g., MATLAB). The images are obtained from the peripheral data by using an algorithm. Precise EIT instrumentation plays an important role in the final images quality. In... 

Medical images contain information about vital organic tissues inside of human body and are widely used for diagnoses of disease or for surgical purposes. Image reconstruction is essential for medical images for some applications such as suppression of noise or de-blurring the image to provide images with better quality and contrast. In this paper Kalman filter technique is introduced for medical image reconstruction. This technique is operated in time domain unlike the filtered back projection which operates in frequency domain. Results indicated that as the number of projection increases in both the collected ray sum corrupted by noise and by blurring the quality of reconstructed image... 

Medical images contain information about vital organic tissues inside of human body and are widely used for diagnoses of disease or for surgical purposes. Due to vital rule of image reconstruction in medical sciences the corresponding algorithms with better efficiency and higher speed is desirable. Most algorithms in image reconstruction are operated on frequency domain such as filtered back projection. In this paper, a Kalman filter technique which is operated in time domain is introduced for reconstruction of CT medical images. Results indicated that as the number of projection increases in both normal collected ray sum and the collected ray sum corrupted by noise the quality of...