Sharif Digital Repository

The first step of any face processing system is detecting the location in images where faces are present. In this paper we present an upright frontal face detection system based on the multi-resolution analysis of the face. In this method firstly, skin-color information is used to detect skin pixels in color images; then, the skin-region blocks are decomposed into frequency sub-bands using contourlet transform. Features extracted from sub-bands are used to detect face in each block. A multi-layer perceptrone (MLP) neural network was trained to do this classification. To decrease false positive detection we use eyes and lips template matching. These templates achieved by averaging... 

In this paper, an efficient approach for ultrasonic object segmentation with special application for left ventricle segmentation in echocardiography images is proposed. At first, an efficient hybrid trend for ultrasonic image edge detection is suggested. Then, a modified level set approach is introduced based on the extracted edges and the computed probabilistic map as the stopping criteria for the contour evolution. Both synthetic and clinical images are utilized as validation measures with respect to the prior techniques which indicate outperform results quantitatively and qualitatively. Left ventricle segmentation using proposed method illustrates expert-approved performance, providing a... 

Android is a major target of attackers for malicious purposes due to its popularity. Despite obvious malicious functionality of Android malware, its analysis is a challenging task. Extracting and using features that discriminate malicious and benign behaviors in applications is essential for malware classification in using machine learning methods. In this paper, we propose a new feature in Android malware classification process which in combination with other proposed features, can discriminate malicious and benign behaviors with a good accuracy. Using components such as activities and services in Android applications' source code will lead to different flows on invoking between... 

Early diagnosis of lung cancer is very important in improving patients life expectancies. Due to the high number of Computed Tomography (CT) images, fast and accurate diagnosis is difficult for radiologists. Therefore, there is an increasing demand for Computer-Aid Diagnosis (CAD) lung cancer. The core of all lung cancer detection systems is the distinction between cancer and non-cancerous tissues. This operation is performed in the false positive reduction phase, which is one of the most critical part of the lung cancer detection systems. The primary objective of this paper is to present a new method based on 3D Convolutional Neural Networks (CNN) that can reduce the false positives rate... 

One of the most important practices of cybercrime investigations is to search a network traffic history for an excerpt of traffic, such as the disclosed information of an organization or a worm's signature. In post-mortem investigations, criminals and targets are detected by attributing the excerpt to payloads of traffic flows. Since it is impossible to store the high volume of data related to long-term traffic history, payload attribution systems (PASs) based on storing a compact digest of traffic using Bloom filters have been presented in the literature. In these systems, querying the stored digest for an excerpt results in a low number of suspects instead of certain criminals. In this... 

Payload attribution systems (PAS) are one of the most important tools of network forensics for detecting an offender after the occurrence of a cybercrime. A PAS stores the network traffic history in order to detect the source and destination pair of a certain data stream in case a malicious activity occurs on the network. The huge volume of information that is daily transferred in the network means that the data stored by a PAS must be as compact and concise as possible. Moreover, the investigation of this large volume of data for a malicious data stream must be handled within a reasonable time. For this purpose, several techniques based on storing a digest of traffic using Bloom filters... 

Disease prediction is a well-known classification problem in medical applications. Graph Convolutional Networks (GCNs) provide a powerful tool for analyzing the patients’ features relative to each other. This can be achieved by modeling the problem as a graph node classification task, where each node is a patient. Due to the nature of such medical datasets, class imbalance is a prevalent issue in the field of disease prediction, where the distribution of classes is skewed. When the class imbalance is present in the data, the existing graph-based classifiers tend to be biased towards the major class(es) and neglect the samples in the minor class(es). On the other hand, the correct diagnosis... 

A combined texture- and color-based skin detection is proposed in this paper. Nonsubsampled contourlet transform is used to represent texture of the whole image. Local neighbor contourlet coefficients of a pixel are used as feature vectors to classify each pixel. Dimensionality reduction is addressed through principal component analysis (PCA) to remedy the curse of dimensionality in the training phase. Before texture classification, the pixel is tested to determine whether it is skin-colored. Therefore, the classifier is learned to discriminate skin and non-skin texture for skin colored regions. A multi-layer perceptron is then trained using the feature vectors in the PCA reduced space. The... 

Detection of skin pixels in arbitrary images is addressed in this paper. We have combined texture and color information to segment skin regions. First, a pixel-based boosted skin detection method is used to locate skin pixels. To further improve the detect performance, skin region texture features are employed using the nonsubsampled contourlet coefficients. For the candidate skin pixels, the set of 8×8 patches around that pixel in all subimages are selected and the feature vector of each patch is extracted. Multilayer perceptron is then utilized to learn features and classify any given input sample. The proposed algorithm has achieved true positive rate of about 82.8% and false positive... 

Due to the growing complexity of today's digital circuits, the speed of fault simulation has become increasingly important. Although critical path tracing (CPT) is faster than conventional methods, it is not fast enough for fault simulation of complex circuits with a large number of faults and tests. Exact stem analysis is the most important obstacle in accelerating the CPT method. The simplification of stem analysis eliminates time-consuming computations and makes the CPT method more parallelizable. An approximate and bit-parallel CPT algorithm is proposed for ultrafast fault simulation for both stuck-at-fault (SAF) and transition delay fault (TDF) models. Time linearity, speedup, and... 

Labeling vertebral discs from MRI scans is important for the proper diagnosis of spinal related diseases, including multiple sclerosis, amyotrophic lateral sclerosis, degenerative cervical myelopathy and cancer. Automatic labeling of the vertebral discs in MRI data is a difficult task because of the similarity between discs and bone area, the variability in the geometry of the spine and surrounding tissues across individuals, and the variability across scans (manufacturers, pulse sequence, image contrast, resolution and artefacts). In previous studies, vertebral disc labeling is often done after a disc detection step and mostly fails when the localization algorithm misses discs or has false... 

Botnets (networks of compromised computers) are often used for malicious activities such as spam, click fraud, identity theft, phishing, and distributed denial of service (DDoS) attacks. Most of previous researches have introduced fully or partially signature-based botnet detection approaches. In this paper, we propose a fully anomaly-based approach that requires no a priori knowledge of bot signatures, botnet C&C protocols, and C&C server addresses. We start from inherent characteristics of botnets. Bots connect to the C&C channel and execute the received commands. Bots belonging to the same botnet receive the same commands that causes them having similar netflows characteristics and... 

In this paper, we propose a novel algorithm that combines color and texture information of skin with cellular learning automata to segment skin-like regions in color images. First, the presence of skin colors in an image is detected, using a committee structure, to make decision from several explicit boundary skin models. Detected skin-color regions are then fed to a color texture extractor that extracts the texture features of skin regions via their color statistical properties and maps them to a skin probability map. Cellular learning automatons use this map to make decision on skin-like regions. The proposed algorithm has demonstrated true positive rate of about 83.4% and false positive... 

Skin detection is a difficult and primary task in many image processing applications. Because of the diversity of various image processing tasks, there exists no optimum method that can perform properly for all applications. In this paper, we have proposed a novel skin detection algorithm that combines color and texture information of skin with cellular learning automata to detect skin-like regions in color images. Skin color regions are first detected, by using a committee structure, from among several explicit boundary skin models. Detected skin-color regions are then fed to a texture analyzer which extracts texture features via their color statistical properties and maps them to a skin...