Sharif Digital Repository

In this investigation, the idea of Visual Working Memory (VWM) mechanism modeling based on versatile fuzzy method; Active Learning method, is presented. Visual information process; retrieving and learning rely on the use of Ink Drop Spread (IDS) and Center of Gravity (COG) as spatial density convergence operators. IDS modeling is characterized by processing that uses intuitive pattern information instead of complex formulas, and it is capable of stable and fast convergence. Furthermore, because it approves that distortion in retrieving irrelative data is adaptive to avoid storing lots of repetitive external information in daily visualization. Subsequently, this distortion is analyzed via two... 

Along with the improvement of image watermarking techniques, the necessity for effectively and comprehensively evaluating various algorithms becomes imperative. In this paper, we first propose a new categorization that fits for most of the existing watermarking algorithms that work in the wavelet domain. Then an adaptive watermarking attack for evaluating the robustness of watermarking schemes that are based on the proposed categorization is presented. This attack determines the flat regions, edges, and textures of the watermarked image and based on known features of each region the proposed attack tries to destroy the watermark information. This is done by separately manipulating the... 

In this paper, we proposed a categorization for most of the existing watermarking algorithms that work in wavelet domain. Then an adaptive watermarking attack for digital images that is based on the proposed categorization is presented. This attack determines the flat regions, edges and textures of the watermarked image and based on known features of each region the proposed attack tries to destroy the watermark information by manipulating the wavelet coefficients of each region separately such that the least visual distortion will be imposed on the attacked image. We have tested the proposed method to attack two recent and robust watermarking methods and the results sound impressive. The... 

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced. However, since their introduction, hand-crafted and engineered features were used to learn increasingly complex models for the problem of relative attributes. This limits the applicability of those methods for more realistic cases. We introduce a deep neural network architecture for the task of relative attribute prediction. A convolutional neural network (ConvNet) is adopted to learn the features by including an... 

A novel method based on EEG nonlinear analysis and analysis of steady-state visual evoked potentials (SSVEPs) has been processed. The EEG phase space is reconstructed, and some new geometrical features are extracted. Statistical analysis is carried out based on ANOVA, and most significant features are selected and then fed into a multi-class support vector machine (MSVM). Both offline and online phases are considered to fully address SSVEP detection. In the offline mode, the whole design evaluation, feature selection, and classifier training are performed. In the online scenario, the proposed method is evaluated and the detection rate is reported for both phases. Subject-dependent and... 

This paper is focused on video event recognition based on frame level CNN descriptors. Using transfer learning, the image trained descriptors are applied to the video domain to make event recognition feasible in scenarios with limited computational resources. After fine-tuning of the existing Convolutional Neural Network (CNN) concept score extractors, pre-trained on ImageNet, the output descriptors of the different fully connected layers are employed as frame descriptors. The resulting descriptors are hierarchically post-processed and combined with novel and efficient pooling and normalization methods. As major contributions of this work to the video event recognition, we present a... 

This paper is focused on video event recognition based on frame level convolutional neural network (CNN) descriptors. Using transfer learning, the image trained descriptors are applied to the video domain to make event recognition feasible in scenarios with limited computational resources. After fine-tuning of the existing CNN concept score extractors, pretrained on ImageNet, the output descriptors of the different fully connected layers are employed as frame descriptors. The resulting descriptors are hierarchically postprocessed and combined with novel and efficient pooling and normalization methods. As major contributions of this paper to the video event recognition, we present a... 

This paper is focused on video event recognition based on frame level convolutional neural network (CNN) descriptors. Using transfer learning, the image trained descriptors are applied to the video domain to make event recognition feasible in scenarios with limited computational resources. After fine-tuning of the existing CNN concept score extractors, pretrained on ImageNet, the output descriptors of the different fully connected layers are employed as frame descriptors. The resulting descriptors are hierarchically postprocessed and combined with novel and efficient pooling and normalization methods. As major contributions of this paper to the video event recognition, we present a... 

An experimental study was carried out on an axisymmetric supersonic inlet with external compression. The scope of this study was to investigate the general characteristics of the inlet buzz under various design and off-design conditions. The model was equipped with accurate and high frequency pressure sensors and the tests were conducted at Mach numbers varying from 1.8 to 2.5, at various angles of attack, and at different mass flow rates. Shadowgraph flow visualization, together with a high speed camera, was used to capture the external shock structure in front of the inlet. Frequencies of buzz were obtained from both the shadowgraph pictures and analysis of the pressure data. The amplitude... 

An extensive wind tunnel test series were conducted on an axisymmetric supersonic inlet. The model was tested at Mach numbers from 1.8 to 2.2 and at different values of mass flow rate. Shadowgraph flow visualization was used to capture the external shock structure in front of the inlet. The goal of this study is to find out the general characteristics of the inlet buzz. Frequencies of the buzz have been achieved from the analysis of the pressure data as well as the shadowgraph pictures. The amplitude of the shock waves motion has been measured from the visualization pictures too. In the some large value of mass flow rate, the frequency of shock oscillation increased versus Mach number. Also... 

In recent years there has been a great effort to enhance the computer-aided diagnosis systems, since proven similar pathologies, in the past, plays an important role in diagnosis of the current cases, content based medical image retrieval has been emerged. In this work we have designed a decision making machine in which utilizes sparse representation technique to preserve semantic category relevance among the retrieved images and the query image, this machine comprises optimized wavelets (adapted using lifting scheme) to extract appropriate visual features in order to grasp visual content of the images, afterwards by using some classical methods, Raw data vectors become applicable for sparse... 

Since expertise elicited from past resolved cases plays an important role in medical application and images acquired from various cases have a great contribution to diagnosis of the abnormalities, Content based medical image retrieval has become an active research area for many scientists, In this article we proposed a new framework to retrieve visually similar images from a large database, in which visual relevance is regarded as much as the semantic category similarity, we used optimized wavelet transform as the multi-resolution analysis of the images and extracted various statistical SGLDM features from different resolutions then after reducing feature space we used error correcting codes... 

Low Salinity Waterflooding (LSWF) has become a popular tertiary injection EOR method recently. Both fluid-fluid and fluid-rock interactions are suggested as the contributing mechanisms on the effectiveness of LSWF. Considering the contradictory remarks in the literature, the dominating mechanisms and necessary conditions for Low Salinity Effect (LSE) varies for different crude oil-brine-rock (CBR) systems. The aim of the present study is to investigate LSE for an oil field in the Middle East that is composed of separate sandstone and limestone layers. Contact angles and Interfacial Tension (IFT) are measured to have more insight on the CBR under investigation. Visual experiments were... 

Low Salinity Waterflooding (LSWF) has become a popular tertiary injection EOR method recently. Both fluid-fluid and fluid-rock interactions are suggested as the contributing mechanisms on the effectiveness of LSWF. Considering the contradictory remarks in the literature, the dominating mechanisms and necessary conditions for Low Salinity Effect (LSE) varies for different crude oil-brine-rock (CBR) systems. The aim of the present study is to investigate LSE for an oil field in the Middle East that is composed of separate sandstone and limestone layers. Contact angles and Interfacial Tension (IFT) are measured to have more insight on the CBR under investigation. Visual experiments were... 

In this study, coupled Generative Adversarial and Auto-Encoder neural networks have been used to reconstruct realizations of three-dimensional porous media. The gradient-descent-based optimization method is used for training and stabilizing the neural networks. The multi-scale reconstruction has been conducted for both sandstone and carbonate samples from an Iranian oilfield. The sandstone contains inter and intra-grain porosity. The generative adversarial network predicts the inter-grain pores and the auto-encoder provides the generative adversarial network result with intra-grain pores (micro-porosity). Different matching criteria, including porosity, permeability, auto-correlation... 

In this study, a novel, simple and sensitive ratiometric fluorescence method is presented for the detection of very low quantities of the carbaryl in Iranian apple using cadmium telluride quantum dots (CdTe QDs) nanoprobe. The principle of the proposed strategy relies on the rapid hydrolysis of the carbaryl under an alkaline condition and production of the 1-naphthol with a blue emission at 470 nm. Besides, using the CdTe QDs with a yellow emission at 580 nm, as a reference, improves the visual tracking of carbaryl through changes in color tonality. The herein described methodology is applied for enzyme-free visual detection of carbaryl with satisfactory results in the presence of other... 

The detection and repair of the cracks in the road pavement is a very time consuming task which should be performed periodically in order to maintain the safety and quality of the road network. There are various types of road pavement cracks and each type requires different management and repair method and also each type indicates a different problem in that section of the road. In this paper, an autonomous machine learning based visual inspection system for detection and classification of the road pavement cracks is proposed. The proposed framework uses deep neural networks in order to detect and classify longitudinal, alligator and asphalt cracks. A dataset of images from different road... 

Knee osteoarthritis (KOA) is a common musculoskeletal disorder resulting in altered gait patterns. Uncontrolled manifold (UCM) analysis has been demonstrated as a useful approach for quantitative analysis of motor variability and synergies. The present study aimed to investigate the changes in the kinematic synergy, controlling the center of mass (COM) position while walking on normal and narrow paths in people with KOA compared to asymptomatic participants. In this cross-sectional study, twenty people with mild to moderate KOA and twenty asymptomatic individuals walked at their comfortable preferred speed across normal and narrow paths on a treadmill. The UCM analysis was performed... 

Medical images contain human body pictures and used widely in diagnosis and surgical purposes [1]. Compression is needed for medical images for some applications such as profiling patient's data or transmission systems Due to the importance of the information of medical images, lossless or visually lossless compression preferred. Lossless compression mainly consists of transformation and encoding steps. On the other hand, hardware implementation of lossless compression algorithm accelerates real time tasks such as online diagnosis and telemedicine. Lossless JPEG, JPEG-LS and lossless version of JPEG2000 are few well known methods for lossless compression. This paper is focused on the... 

In this paper, the problem of convolutive source separation via multimodal soft Nonnegative Matrix Co-Factorization (NMCF) is addressed. Different aspects of a phenomenon may be recorded by sensors of different types (e.g., audio and video of human speech), and each of these recorded signals is called a modality. Since the underlying phenomenon of the modalities is the same, they have some similarities. Especially, they usually have similar time changes. It means that changes in one of them usually correspond to changes in the other one. So their active or inactive periods are usually similar. Assuming this similarity, it is expected that the activation coefficient matrices of their...