Sharif Digital Repository

Graph Matching (GM) plays an essential role in computer vision and machine learning. The ability of using pairwise agreement in GM makes it a powerful approach in feature matching. In this paper, a new formulation is proposed which is more robust when it faces with outlier points. We add weights to the one-to-one constraints, and modify them in the process of optimization in order to diminish the effect of outlier points in the matching procedure. We execute our proposed method on different real and synthetic databases to show both robustness and accuracy in contrast to several conventional GM methods  

Rolling element bearing fault diagnosis is a very important part of condition-based maintenance. In this article, a new method for detection of rolling element bearing defects is proposed. The method is based on the concept of the cyclostationarity of the vibration signal to find periodicity in statistical features of the vibration signal. Various statistical features are examined to find the best choice. Several case studies including inner race, outer race, and rolling element defects are investigated in this article. Comparison with the envelope analysis showed that the proposed method benefits from clearer defect frequency identification  

In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We... 

Steganalysis of least significant bit (LSB) embedded images in spatial domain has been investigated extensively over the past decade and most well-known LSB steganography methods have been shown to be detectable. However, according to the latest findings in the area, two major issues of very low-rate (VLR) embedding and content-adaptive steganography have remained hard to resolve. The problem of VLR embedding is indeed a generic problem to any steganalyser, while the issue of adaptive embedding specifically depends on the hiding algorithm employed. The latter challenge has recently been brought up again to the area of LSB steganalysis by highly undetectable stego image steganography that... 

With the advent of new positioning services, one can reach more satellites these days to find his position. Using a combination of satellites which belong to different constellations needs some considerations like addressing biases between their time references. Each constellation has progressed to the point that they have enough satellites to provide accurate position separately. According to this fact, we propose to find the position in each constellation and fusion their results in a way that final position has the minimum possible variance instead of combining the constellations in a satellite level and dealing with inter system biases. Experimental studies are conducted based on IGS... 

An advantage of steganography, as opposed to other information hiding techniques, is that the embedder can select a cover image that results in the least detectable stego image. In a previously proposed method, a technique based on block texture similarity was introduced where blocks of cover image were replaced with the similar secret image blocks; then indices of secret image blocks were stored in cover image. In this method, the blocks of secret image are compared with blocks of a set of cover images and the image with most similar blocks to those of the secret image is selected as the best candidate to carry the secret image. Using appropriate features for comparing image blocks,... 

Tool Condition Monitoring (TCM) is a vital demand of advanced manufacturing in order to develop automated unmanned production. Continuing the machining operation with a worn or damaged tool will result in damages to the workpiece. This problem becomes more important in supplementary machining processes like drilling which the workpiece usually has passed a lot of machining processes and any damage to workpiece at this stage results in high production losses. In this research features of sound pressure and vibration signals in drilling process are recorded and analyzed in order to detect tool wear. Signal statistical features are extracted in time domain, and the features trends as the tool... 

Multi-dimensional spatial analysis of image pixels have not been much investigated for the steganalysis of the LSB Steganographic methods. Pixel distribution based steganalysis methods could be thwarted by intelligently compensating statistical characteristics of image pixels, as reported in several papers. Simple LSB replacement methods have been improved by introducing smarter LSB embedding approaches, e.g. LSB matching and LSB+ methods, but they are basically the same in the sense of the LSB alteration. A new analytical method to detect LSB stego images is proposed in this paper. Our approach is based on the relative locations of image pixels that are essentially changed in an LSB... 

Acute hypotension episodes are one of the hemodynamic instabilities with high mortality rate that is frequent among many groups of patients. Prediction of acute hypotension episodes can help clinicians to diagnose the cause of this physiological disorder and select proper treatment based on this diagnosis. In this study new physiological time series are generated based on heart rate, systolic blood pressure, diastolic blood pressure and mean blood pressure time series. Statistical features of these time series are extracted and patients whom are exposed to acute hypotension episodes in future 1 hour time interval and whom are not, are classified based on these features and with the aid of... 

Pain level estimation from videos of face has many benefits for clinical applications. Most of the previous works focused only on pain detection task. However, pain level estimation of video sequences has been discussed fewer. In this work, we have proposed a new regression-based approach to estimate the pain level of video sequences. As the first step, facial expression-related features were extracted from each frame, this task was done by reducing identity-related features using the robust principal component analysis decomposition. Then, we used the minimum, maximum, and mean of the features of frames in a sequence to represent that sequence by a fixed-length feature vector. After this,... 

The quality assessment is a vital routine in videorelated industries such as broadcast service providers. Due to the duration and the excessive number of the video files, case by case assessment of the files by operators is no longer feasible. Therefore, a computer-based video quality assessment mechanism is the only solution. While it is common to measure the quality of a video file at the compression stage by comparing it against the raw data, at later stages no reference video is available for comparison. Therefore, a no-reference (Blind) video quality assessment (NR-VQA) technique is essential. The common NRVQA methods learn a quality metric based on a number of features extracted from... 

Identification of modulation and space-time block code (STBC) is an important task of receivers in applications such as military, civilian, and commercial communications. Here, we consider multiple-input multiple-output (MIMO) systems. We propose two methods for STBC identification when the modulation is known. We also introduce a method for joint identification of code and modulation. Additionally, we present an enhanced zero-forcing (ZF) equaliser to improve the separation between the features of different classes. Higher order cumulants are used as the statistical features. In the first method of STBC identification, after the proposed equalisation, received data samples are segmented,... 

Abnormal operating conditions for the timing belt can lead to cracks, fatigue, sudden rupture and damage to engines. In this study, an intelligent system was developed to detect and classify high-load operating conditions and high-temperature operating conditions for timing belts. To achieve this, vibration signals in normal operating conditions, high-load operating conditions and high-temperature operating conditions were collected. Time-domain signals were transformed to the frequency domain and the time-frequency domain using the fast Fourier transform method and the wavelet transform method respectively. In the data-mining stage, 25 statistical features were extracted from different...