Search for: feature-extraction
Total 234 records
Ph.D. Dissertation Sharif University of Technology ; Manzuri Shalmani, Mohammad Taghi
Feature extraction in subspace domain for face recognition has attracted growing attention in recent years. Face image shown by a long vector usually belongs to a manifold of intrinsically low dimension. Researchers in face recognition field try to extract these manifolds using algebraic and statistical tools. Recently, the use of multilinear algebra and multidimensional data in various stages of feature extraction and recognition is considered. This approach reduces small sample size problem and computational cost by considering the spatial information in the image. Although these successes, the performance of the methods based of this idea in term of recognition rate in the applications...
Article 2012 6th International Symposium on Telecommunications, IST 2012 ; 2012 , Pages 1147-1150 ; 9781467320733 (ISBN) ; Tabandeh, M ; Fatemizadeh, E ; Sharif University of Technology
Finger-Knuckle-Print (FKP) is one of the newest biometrics. In this paper, a novel approach has been proposed to segment the Region of Interest (ROI) of a FKP image using the global intensity. This method upgrades the speed and accuracy of segmentation stage, as well as the pace of other steps of the procedure. This has been achieved by employing the area with maximum intensity in ROI extraction, instead of using the creases of the knuckle image. To confirm this improvement, lots of experiments have been performed and the method has been compared with the only existing schemes for ROI extraction suggested by Zhang and Kekre. At the end, the captured ROI images obtained by three methods have...
Article 2006 IEEE GCC Conference, GCC 2006, Manama, 20 March 2006 through 22 March 2006 ; 2006 ; 9780780395909 (ISBN) ; Kasaei, S ; Sharif University of Technology
This work presents a method to increase the face recognition accuracy using a combination of Wavelet, PCA, and Neural Networks. Preprocessing, feature extraction and classification rules are three crucial issues for face recognition. This paper presents a hybrid approach to employ these issues. For preprocessing and feature extraction steps, we apply a combination of wavelet transform and PCA. During the classification stage, the Neural Network (MLP) is explored to achieve a robust decision in presence of wide facial variations. The computational load of the proposed method is greatly reduced as comparing with the original PCA based method on the Yale and ORL face databases. Moreover, the...
M.Sc. Thesis Sharif University of Technology ; Shabany, Mahdi ; Mohammadzadeh, Hoda
Make a connection between brain and computer, or Brain Computer Interface (BCI) for broad applications in areas such as medical and gamming has caused the subject to one of the most important and attractive issues in recent decades. From the perspective of pattern recognition, BCI is a classification issue that should receive signals that relate to the certain decisions of the brain and then after processing, it is concluded that the person has thought to what decision. Decisions that taken by individual, is sent from the brain to the body by signals, which is called Electroencephalogram (EEG). The number of these decisions is further, classified it also becomes more difficult. That is why...
M.Sc. Thesis Sharif University of Technology ; Vosughi Vahdat, Bijan
Face recognition is one of the best biometrics in computer vision. Although researchers introduced this method many years ago, the most important improvement has occurred in the biometrics last decade. Face recognition was employed in areas such as passport checking, security issues and identification. It facilitates our daily life as we use it in our mobile phones and computers for unlocking our devices. Many approaches were employed in the face recognition applications. Some of them were single-modal like PCA, ICA and LDA and some others were multimodal like Visual + 3D or 3D + IR. Still, most of Face recognition methods suffer from environment changes like variations in illumination and...
M.Sc. Thesis Sharif University of Technology ; Shamsollahi, Mohammad Bagher
BCI is an interface between brain and machine, particularly computer which translates brain signals into understandable instructions for machine. BCI records signals and determines what the subject is doing or thinking. BCI in the point of view of pattern recognition is a classification problem. For this aim, different tasks are referred to different classes. The more number of classes, the higher complexity we encounter in classification so surveying of different kinds of features, feature selection and reduction methods have highly importance. In this project we want to design a 4-class classification that each class is referred to a direction of wrist movement. During the time that the...
Article Computing and Informatics ; Volume 30, Issue 5 , 2011 , Pages 965-986 ; 13359150 (ISSN) ; Manzuri Shalmani, M. T ; Sharif University of Technology
One limitation of vector-based LDA and its matrix-based extension is that they cannot deal with heteroscedastic data. In this paper, we present a novel two-dimensional feature extraction technique for face recognition which is capable of handling the heteroscedastic data in the dataset. The technique is a general form of two-dimensional linear discriminant analysis. It generalizes the interclass scatter matrix of two-dimensional LDA by applying the Chernoff distance as a measure of separation of every pair of clusters with the same index in different classes. By employing the new distance, our method can capture the discriminatory information presented in the difference of covariance...
Article 2010 5th International Symposium on Telecommunications, IST 2010, 4 December 2010 through 6 December 2010, Tehran ; 2010 , Pages 755-759 ; 9781424481835 (ISBN) ; Sameti, H ; Ghaemmaghami, M. P ; BabaAli, B ; Sharif University of Technology
This paper focuses on enhancing MFCC features using a set of MLP NN in order to improve phoneme recognition accuracy under different noise types and SNRs. A NN can be used in different domains (between any pair of MFCC feature extraction blocks). It includes FFT, MEL, LOG, DCT and DELTA domains. Various domains have different complexities and achieve different degrees. A comparative study is done in this paper in order to find the best domain. Furthermore, a set of MLP NNs, instead of one NN, is used to enhance various noise types with different levels of SNRs. In this case, each NN is trained with a special noise type and SNR. The database used in the simulations is created by artificially...
Article 9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007, London, 7 July 2007 through 11 July 2007 ; 2007 , Pages 1515- ; 1595936971 (ISBN); 9781595936974 (ISBN) ; Bagheri Shouraki, S ; Jafari Jashmi B ; Jalali Heravi, M ; Sharif University of Technology
Recombination in the Genetic Algorithm (GA) is supposed to extract the component characteristics from two parents and reassemble them in different combinations hopefully producing an offspring that has the good characteristics of both parents. Symbiotic Combination is formerly introduced as an alternative for sexual recombination operator to overcome the need of explicit design of recombination operators in GA all. This paper presents an optimization algorithm based on using this operator in Tabu Search. The algorithm is benchmarked on two problem sets and is compared with standard genetic algorithm and symbiotic evolutionary adaptation model, showing success rates higher than both cited...
Article IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings ; 2013 , Pages 102-107 ; 1555-5798 (ISSN) ; 9781479915019 (ISBN) ; Fanian, A ; Saleh, F. S ; Gulliver, T. A ; Sharif University of Technology
Internet traffic classification is important in many aspects of network management such as data exploitation detection, malicious user identification, and restricting application traffic. Previously, features such as port and protocol numbers have been used to classify traffic, but these features can now be changed easily, making their use in traffic classification inadequate. Consequently, traffic classification based on machine learning (ML) is now employed. The number of features used in an ML algorithm has a significant impact on performance, in particular accuracy. In this paper, a minimum best feature set is chosen using a supervised method to obtain uncorrelated features. Outlier...
Article Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012 ; 2012 , Pages 9-16 ; 9780769549255 (ISBN) ; Hosseini, M. J ; Sani, Z. A ; Ghandeharioun, A ; Boghrati, R ; Sharif University of Technology
One of the main causes of death the world over are cardiovascular diseases, of which coronary artery disease (CAD) is a major type. This disease occurs when the diameter narrowing of one of the left anterior descending, left circumflex, or right coronary arteries is equal to or greater than 50 percent. Angiography is the principal diagnostic modality for the stenosis of heart vessels; however, because of its complications and costs, researchers are looking for alternative methods such as data mining. This study conducts data mining algorithms on the Z-Alizadeh Sani dataset which has been collected from 303 random visitors to Tehran's Shaheed Rajaei Cardiovascular, Medical and Research...
Article 2011 7th Iranian Conference on Machine Vision and Image Processing, MVIP 2011 - Proceedings ; 2011 ; 9781457715358 (ISBN) ; Fatemizadeh, E ; Sharif University of Technology
In feature-based image registration, feature selection and reduction methods play an important role in decreasing computational burden of these operations. In this paper, a new approach is introduced to reduce the dimension of extracted feature vectors of MR images. This approach is based on the selection of the maximum and minimum responses of the alpha stable filter for the MR images over the extracted features with different orientation in frequency domain. This algorithm selects the rotation invariant features which are suitable for image registration purposes. It has been shown that these features could efficiently describe the image elements. The discriminating ability of the features...
Article Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS ; 2011 , Pages 5100-5103 ; 1557170X (ISSN) ; 9781424441211 (ISBN) ; Razavian, S. M. J ; Vaziri, R ; Vosoughi Vahdat, B ; Sharif University of Technology
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...
Three-dimensional modular discriminant analysis (3DMDA): A new feature extraction approach for face recognition, Article Computers and Electrical Engineering ; Volume 37, Issue 5 , 2011 , Pages 811-823 ; 00457906 (ISSN) ; Manzuri Shalmani, M. T ; Sharif University of Technology
In this paper, we present a novel multilinear algebra based feature extraction approach for face recognition which preserves some implicit structural or locally-spatial information among elements of the original images. We call this method three-dimensional modular discriminant analysis (3DMDA). Our approach uses a new data model called third-order tensor model (3TM) for representing the face images. In this model, each image is partitioned into the several equal size local blocks, and the local blocks are combined to represent the image as a third-order tensor. Then, a new optimization algorithm called direct mode (d-mode) is introduced for learning three optimal projection axes. Extensive...
Feature extraction using gabor-filter and recursive fisher linear discriminant with application in fingerprint identification, Article Proceedings of the 7th International Conference on Advances in Pattern Recognition, ICAPR 2009, 4 February 2009 through 6 February 2009, Kolkata ; 2009 , Pages 217-220 ; 9780769535203 (ISBN) ; Roshani Tabrizi, P ; Fatemizadeh, E ; Soltanian Zadeh, H ; Sharif University of Technology
Fingerprint is widely used in identification and verification systems. In this paper, we present a novel feature extraction method based on Gabor filter and Recursive Fisher Linear Discriminate (RFLD) algorithm, which is used for fingerprint identification. Our proposed method is assessed on images from the biolab database. Experimental results show that applying RFLD to a Gabor filter in four orientations, in comparison with Gabor filter and PCA transform, increases the identification accuracy from 85.2% to 95.2% by nearest cluster center point classifier with Leave-One-Out method. Also, it has shown that applying RFLD to a Gabor filter in four orientations, in comparison with Gabor filter...
An empirical centre assignment in RBF network for quantification of anaesthesia using wavelet-domain features, Article 2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09, Antalya, 29 April 2009 through 2 May 2009 ; 2009 , Pages 510-513 ; 9781424420735 (ISBN) ; Rabiee, H. R ; Shakouri Ganjavi, H ; National Institutes of Health, NIH; National Institute of Neurological Disorders and Stroke, NINDS; National Science Foundation, NSF ; Sharif University of Technology
The assessment of the hypnotic state of the brain is crucial to the process of an operation under general anaesthesia. A noninvasive method of quantifying depth of anaesthesia is through analysis of electroencephalogram (EEG). Among number of works done in the field, no single algorithm has been found exhibiting a precise measure in all of the hypnotic states. One can categorise algorithms as either a state-quantifier or a trend measure. State-quantifier algorithms can discriminate between different hypnotic states such as awake, light sedation, deep anaesthesia, etc. On the other hand, trend measure algorithms are employed to specify the short-term changes in hypnotic brain conditions,...
M.Sc. Thesis Sharif University of Technology ; Babaie-zadeh, Massoud ; Ghorshi, Alireza
Statistical learning plays a key role in many areas of science . An example of learning problems is image matching, image matching plays an important role in many aspects of computer vision.Computers can be used in intelligent tasks, which are followed by logical inference, for example, visual scenes (images or videos) or speech (audios). For humans visual system of such task are performed hundreds of times every day so easily sometimes without any awareness. In this thesis we focus on the image matching phase which is the first phase of the classification process. One of the popular image matching methods is Scale Invariant Feature Transform (SIFT) which our proposed method is based on...
M.Sc. Thesis Sharif University of Technology ; Bahrani, Mohammad ; Khosravi Zadeh, Parvaneh
Author identification using statistical methods is a branch of authorship attribution which is one of important problems in natural language processing. Using different statistical methods, an anonymous text is attributed to an author. One of the primary parts of the task is to choose the appropriate stylistic features of the text in order to study the significances of style. These features must be quantitatively studied and could be extracted in lexical level, character level, and syntactic or semantic levels. The next step is text classification in which different machine learning methods such as decision tree, Artificial Neural Networks, Naïve Bayes and other methods could be used....
M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein
Measuring emotions of music is one of the methods to determine music content. Music emotion detection is applicable in music retrieval, recognition of music genre and also music data management softwares. Music emotion is considered in different sciences such as physiology, psychology, musicology and engineering. First, we collected a database of different types of music with various emotions. These data have been labeled according to their emotions. In this project, four emotions (Angry, happy, relax and sad) have been used as labels based on Thayer’s two dimension emotion model. There are two basic steps for music emotion recognition similar to other recognition systems: Feature extraction...
M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh ; Rabiei, Hamidreza
Reinforcement learning is a field of machine learning which is more similar to human training procedures.It uses reward signals to train an agent designed to act in that environment. Deep neural networks enhance the agent’s ability to determine and act better in its complex environment. Most previous works have addressed model-free agents, which ignore modeling details of the environment that in turn can be used to achieve better results. On the other hand, humans utilize a model-based approach in their decision-making process. They use their knowledge to predict the future and choose the action that leads them to a better state. To combine the benefits of model-based and model-free designs,...