Sharif Digital Repository

Processing time and segmentation quality are two main factors in evaluation of image segmentation methods. Oversegmentation is one of the most challenging problems that significantly degrade the segmentation quality. This paper presents a framework for decreasing the oversegmentation rate and improving the processing time. Significant variations in both color and texture spaces are the main reasons that lead to oversegmentation. We exploit Affine Invariant Region Detectors to mark regions with high variations in both color and texture spaces. The results are then utilized to reduce the oversegmentation rate of image segmentation algorithms. The performance of the proposed framework is... 

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... 

Synthetic aperture radar (SAR) appropriate image processing in conjunction with noise reduction is crucial in proper image segmentation. The authors present a new algorithm, logarithmic adaptive soft morphological (LASM) filter, utilising collectivity and flexibility of order-statistic soft morphological filters. This method not only reduces the speckle noise of the single-look SAR imagery considerably, but it significantly enhances the segmentation results. To verify the performance, a simulated SAR image is first created by applying an imagery method to an original noiseless image. The resulting image has characteristics identical to a real SAR image. The LASM method, as well as several... 

Digital watermarking is an efficacious technique to protect the copyright and ownership of digital information. Traditional image watermarking algorithms embed a logo in the image that reduces its visual quality. A new approach in watermarking called zero watermarking doesn’t need to embed a logo in the image. In this algorithm we find a feature from the main image and combine it with a logo to obtain a key. This key is securely kept by a trusted authority. In this paper we show that we can increase the robustness of digital zero watermarking by a new counter detection method in comparison to Canny Edge detection and morphological dilatation that is mostly used by related works. Experimental... 

Progressive image transmission enables the receivers to reconstruct a transmitted image at various bit rates. Most of the works in this field are based on the conventional Shannon-Nyquist sampling theory. In the present work, progressive image transmission is investigated using sparse recovery of random samples. The sparse recovery methods such as Iterative Method with Adaptive Thresholding (IMAT) and Iterative IKMAX Thresholding (IKMAX) are exploited in this framework since they have the ability for successive reconstruction. The simulation results indicate that the proposed method performs well in progressive recovery. The IKMAX has better final reconstruction than IMAT at the cost of... 

Automatic cell segmentation has various applications in different parts of science. The development of automated methods for cell segmentation, remains challenging in situations where there are touching cells. In this paper we propose a new method for separating touching cells. As the first step, we use a combination of graph segmentation algorithm and thresholding for segmenting foreground objects and producing a binary image. Next, boundary points of separation zone are selected by using a corner detection algorithm. Finally, the marker controller watershed transform is applied to separate touching cells at selected points. © 2008 IEEE  

We present an attempt to improve the performance of multi-class image segmentation systems based on a multilevel description of segments. The multi-class image segmentation system used in this paper marks the segments in an image, describes the segments via multilevel feature vectors and passes the vectors to a multi-class object classifier. The focus of this paper is on the segment description section. We first propose a robust, scale-invariant texture feature set, named directional differences (DDs). This feature is designed by investigating the flaws of conventional texture features. The advantages of DDs are justified both analytically and experimentally. We have conducted several... 

Segmentation plays an important role in the machine vision field. Extraction of dominant segments with large number of pixels is essential for some applications such as object detection. In this paper, a new approach is proposed for color image segmentation which uses ideas behind the social science and complex networks to find dominant segments. At first, we extract the color and texture information for each pixel of input image. A network that consists of some nodes and edges is constructed based on the extracted information. The idea of community detection in social networks is used to partition a color image into disjoint segments. Community detection means partitioning vertices of a... 

Color image segmentation is a primitive operation in many image processing and computer vision applications. Accordingly, there exist numerous segmentation approaches in the literature, which might be misleading for a researcher who is looking for a practical algorithm. While many researchers are still using the tools which belong to the old color space paradigm, there is evidence in the research established in the eighties that a proper descriptor of color vectors should act locally in the color domain. In this paper, these results are used to propose a new color image segmentation method. The proposed method searches for the principal colors, defined as the intersections of the cylindrical... 

Chest computed tomography (CT) has played an essential diagnostic role in assessing patients with COVID-19 by showing disease-specific image features such as ground-glass opacity and consolidation. Image segmentation methods have proven to help quantify the disease and even help predict the outcome. The availability of longitudinal CT series may also result in an efficient and effective method to reliably assess the progression of COVID-19, monitor the healing process and the response to different therapeutic strategies. In this paper, we propose a new framework to identify infection at a voxel level (identification of healthy lung, consolidation, and ground-glass opacity) and visualize the... 

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... 

According to the WHO, two individuals die every hour from skin cancer and about 9500 people get skin cancer every day just in the United States. Various computer vision algorithms have been introduced for skin lesion detection, classification, and segmentation. This paper proposes a new segmentation-based algorithm in order to select target components using the persistence diagram of the input images. The results, in comparison with the existing seven different both clustering-and histogram-based segmentation methods using three metrics, show improved performance. Medical image segmentation is an essential task in computer-aided diagnosis. The main improvement of our method is to detect one... 

Breast cancer is regarded as one of the most frequent mortality causes among women. As early detection of breast cancer increases the survival chance, creation of a system to diagnose suspicious masses in mammograms is important. In this paper, two automated methods are presented to diagnose mass types of benign and malignant in mammograms. In the first proposed method, segmentation is done using an automated region growing whose threshold is obtained by a trained artificial neural network (ANN). In the second proposed method, segmentation is performed by a cellular neural network (CNN) whose parameters are determined by a genetic algorithm (GA). Intensity, textural, and shape features are... 

Teeth segmentation in computed tomography (CT) images is a major and challenging task for various computer assisted procedures. In this paper, we introduced a hybrid method for quantification of teeth in CT volumetric dataset inspired by our previous experiences and anatomical knowledge of teeth and jaws. In this regard, we propose a novel segmentation technique using an adaptive thresholding, morphological operations, panoramic re-sampling and variational level set algorithm. The proposed method consists of several steps as follows: first, we determine the operation region in CT slices. Second, the bony tissues are separated from other tissues by utilizing an adaptive thresholding technique... 

Recognition of cursive handwritings such as Persian script is a hard task as there is no fixed segmentation and simultaneous segmentation and recognition is required. This paper presents a novel comparison method for such tasks which is based on a Multiple States Machine to perform robust elastic comparison of small segments with high speed through generation and maintenance of a set of concurrent possible hypotheses, The approach is implemented on Persian (Farsi) language using a typical feature set and a specific tailored genetic algorithm and the recognition and computation time is compared with dynamic programming comparison approach. Copyright - World Automation Congress (WAC) 2006  

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  

Segmentation is a very important stage of Farsi/Arabie character recognition systems. A new segmentation algorithm -for multi font Farsi/Arabic texts- based on the conditional labeling of the up contour and down contour is presented. A pre-processing technique is used to adjust the local base line for each subword. This algorithm uses adaptive base line for each subword to improve the segmentation results. This segmentation algorithm, in addition to up and down contours, takes advantage of their curvatures also. The algorithm was tested on a data set of printed Farsi texts, containing 22236 characters, in 18 different fonts. 97% of characters were correctly segmented. © 2005 IEEE  

The goal of image segmentation is to find regions that represent objects or meaningful parts of objects. In this paper a new method is presented for color image segmentation which involves the ideas used for community detection in social networks. In the proposed method an initial segmentation is applied to partition input image into small homogeneous regions. Then a weighted network is constructed from the regions, and a community detection algorithm is applied to it. The detected communities represent segments of the image. A remarkable feature of the method is the ability to segments the image automatically by optimizing the modularity value in the constructed network. The performance of... 

Anatomical image segmentation is one of the foundations for medical planning. Recently, convolutional neural networks (CNN) have achieved much success in segmenting volumetric (3D) images when a large number of fully annotated 3D samples are available. However, rarely a volumetric medical image dataset containing a sufficient number of segmented 3D images is accessible since providing manual segmentation masks is monotonous and time-consuming. Thus, to alleviate the burden of manual annotation, we attempt to effectively train a 3D CNN using a sparse annotation where ground truth on just one 2D slice of the axial axis of each training 3D image is available. To tackle this problem, we propose... 

Fuzzy connectedness and fuzzy clustering are two well-known techniques for fuzzy image segmentation. The former considers the relation of pixels in the spatial space but does not inherently utilize their feature information. On the other hand, the latter does not consider the spatial relations among pixels. In this paper, a new segmentation algorithm is proposed in which these methods are combined via a notion called membership connectedness. In this algorithm, two kinds of local spatial attractions are considered in the functional form of membership connectedness and the required seeds can be selected automatically. The performance of the proposed method is evaluated using a developed...