Sharif Digital Repository

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... 

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... 

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... 

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... 

Statistical learning plays a key role in many areas of science [38]. 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... 

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.... 

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... 

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,...