Sharif Digital Repository

We propose to use a compressed sensing recovery method called IMATCS for improving the resolution in microwave imaging applications. The electromagnetic inverse scattering problem is solved using the Distorted Born Iterative Method combined with the IMATCS algorithm. This method manages to recover small targets in cases where traditional DBIM approaches fail. Furthermore, by applying an L2-based approach to regularize the sparse recovery algorithm, we improve the algorithm's robustness and demonstrate its ability to image complex breast structures. Although our simulation scenarios do not fully represent experimental or clinical data, our results suggest that the proposed algorithm may be... 

Segmentation of a scene to the part made is a challenging work. In this paper a graphical model is used for this task. The methods based on geometrical derivatives such as curvature and normal often haven't good result in segmentation of geometrically-complex architecture and lead to over-segmentation and even failure. Proposed method for segmentation contains two steps. At first region growing based on curvature, normal and color is used for growing region. This segmented cloud is used for unary potential in graphical model. Fully connected graph for Conditional Random Field with Gaussian kernel for pair wise potentials is used for correcting this segmentation. Gaussian kernels are based on... 

3D scene understanding is an open challenge in the field of computer vision. Most of the focus is on 2D methods in which the semantic labeling of each RGB pixel is considered. But, in this paper, the 3D semantic labeling of RGB-D images is considered. In the proposed method, to extract some meaningful features, the superpixel generation algorithm is applied to the RGB image to segment it into a set of disjoint pixels. After that, the set of three powerful classifiers are utilized to semantically label each superpixel. In the proposed method, the probability outputs of these classifiers are concatenated as the novel feature vector for each superpixel. Consequently, to analyze the strengths... 

This paper presents a new segmentation method for color images. It relies on soft and hard segmentation processes. In the soft segmentation process, a cellular learning automata analyzes the input image and closes together the pixels that are enclosed in each region to generate a soft segmented image. Adjacency and texture information are encountered in the soft segmentation stage. Soft segmented image is then fed to the hard segmentation process to generate the final segmentation result. As the proposed method is based on CLA it can adapt to its environment after some iterations. This adaptive behavior leads to a semi content-based segmentation process that performs well even in presence of... 

In this paper, a content-aware medical image transmission scheme is investigated over a multiple-input single-output (MISO) channel in wireless healthcare systems. The multi-antenna-aided access point, as a source node, wishes to wirelessly send medical images of a patient to a trusted destination node, while multiple randomly-located totally passive and non-colluding eavesdroppers (Eves) try to wiretap the transmission. Considering the fact that not all regions of an image have the same importancy level from the security view-point, we first segment the image into two parts: the region of interest (RoI), which more likely contains important diagnostic information regarding the medical image... 

Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance of the state-of-the-art techniques for this task. However, their superior performance is highly reliant on the availability of a large-scale annotated dataset. In this letter, we propose a novel fully unsupervised semantic segmentation method, the so-called Information Maximization and Adversarial Regularization Segmentation (InMARS). Inspired by human perception which parses a scene into perceptual groups, rather than analyzing each pixel individually, our... 

Automatic image annotation is a challenging problem in the field of image retrieval. Dealing with large databases makes the annotation problem more difficult and therefore an effective approach is needed to manage such databases. In this work, an annotation system has been developed which considers images in separate categories and constructs a profiling model for each category. To describe an image, we propose a new feature extraction method based on color and texture information that describes image content using discrete distribution signatures. Image signatures of one category are partitioned using spectral clustering and a prototype is determined for each cluster by solving an... 

The grain-size distribution (GSD) of porous rocks is important in order to better understand their hydrodynamic behavior. Clear and precise GSD data can be used to computationally reconstruct rock structure for further analysis. In this study, three main algorithms for image analysis have been examined to estimate the GSD of clastic rocks. The main challenge in GSD determination from images is in detecting overlapping grains and measuring their size separately. In this study, three previously developed image processing algorithms are implemented on two-dimensional (2D) binary images of rocks in order to compare the obtained GSD from each of the methods, i.e., the mean intercept length... 

3D scene understanding is one of the most important problems in the field of computer vision. Although, in the past decades, considerable attention has been devoted on the 2D scene understanding problem, now with the development of the depth sensors (like Microsoft Kinect), the 3D scene understanding has become a very challenging task. Traditionally, the scene understanding problem was considered as the semantic labeling of each image pixel. Semantic labeling of RGB-D images has not attained a comparable success, as the RGB semantic labeling, due to the lack of a challenging dataset. With the introduction of an RGB-D dataset, called NYU-V2, it became possible to propose a novel method to... 

A novel method is proposed in the scope of image segmentation that solves this problem by breaking it into two main blocks. The first block's functionality is a method to anticipate the color basis of each segment in segmented images. One of the challenges of image segmentation is the inappropriate distribution of colors in the RGB color space. To determine the color of each segment, after mapping the input image onto the HSI color space, the image colors are classified into some clusters by exploiting the K-Means. Then, the list of cluster centers is winnowed down to a short list of colors based on a set of criteria. The second block of the proposed method defines how each pixel of the... 

Here we present an approach for processing neural cells images to analyze their growth process in culture environment. We have applied several image processing techniques for: 1- Environmental noise reduction, 2- Neural cells segmentation, 3- Neural cells classification based on their dendrites' growth conditions, and 4- neurons' features Extraction and measurement (e.g., like cell body area, number of dendrites, axon's length, and so on). Due to the large amount of noise in the images, we have used feed forward artificial neural networks to detect edges more precisely. © 2008 Springer-Verlag  

In the image segmentation field, traditional techniques do not completely meet the segmentation challenges mostly posed by inherently fuzzy images. Fuzzy connectedness and fuzzy clustering are considered as two well-known techniques for introducing fuzzy concepts to the problem of image segmentation. Fuzzy connectedness-based Segmentation methods consider spatial relation of image pixels by "hanging togetherness" a notion based on intensity homogeneity. But, they do not inherently utilize feature information of image pixels. On the other hand, as the segmentation domain of fuzzy clustering-based methods is the feature space they do not consider spatial relations among image pixels. Recently,...