Με την αλματώδη πρόοδο της τεχνολογίας τα τελευταία χρόνια, οι συσκευές πολυμέσων έχουν γίνει ακόμη περισσότερο «έξυπνες». Όλες αυτές οι συσκευές, απαιτούν επικοινωνία με τον χρήστη σε πραγματικό χρόνο. Ο τομέας της επικοινωνίας ανθρώπου – υπολογιστή (human – computer interaction - HCI) έχει προχωρήσει πια από την εποχή που τα μοναδικά εργαλεία ήταν το ποντίκι και το πληκτρολόγιο. Ένας από τους πιο ενδιαφέροντες και αναπτυσσόμενους τομείς είναι η χρήση χειρονομιών για αλληλεπίδραση με την έξυπνη συσκευή. Στη παρούσα εργασία προτείνεται ένα αυτόματο σύστημα όπου ο χρήστης θα επικοινωνεί με μία συσκευή πολυμέσων, για παράδειγμα μία τηλεόραση, βάση χειρονομιών σε πραγματικό χρόνο και σε πραγματικές συνθήκες. Θα παρουσιαστούν και θα δοκιμαστούν δημοφιλείς αλγόριθμοι της υπολογιστικής όρασης (computer vision) και της αναγνώρισης προτύπων (pattern recognition) και κάποιοι από αυτούς θα ενσωματωθούν στο σύστημά μας. Το προτεινόμενο σύστημα μπορεί να παρακολουθεί το χέρι ενός χρήστη και να αναγνωρίζει τη χειρονομία του. Η παρούσα εργασία παρουσιάζει μια υλοποίηση στο Matlab® (2014b) και αποτελεί προστάδιο υλοποίησης σε πραγματικό χρόνο. / The rapid advances of technology during the last years have enabled multimedia devices to become more and more «smart» requiring real time interaction with the user. The field of human-computer interaction (HCI) has to show many advances in this communication that is not restricted only to the use of mouse and keyboard that once used to be the only tools for communication with the computer. An area of great interest and improvements is the use of hand gestures in order to enable interaction with the smart device. In this master thesis, a novel automatic system that enables the communication of the user with a multimedia device, e.g. a television, in real time and under real circumstances is proposed. In this thesis, popular algorithms from the fields of computer vision and pattern recognition will be investigated in order to choose the ones that will be incorporated in the proposed system. This system has the ability to track the user’s hand, recognize his gesture and act properly. The current implementation was conducted with the use of Matlab® (2014b) and constitutes a first step of the final real time implementation.

The space of hand gesture recognition using radar and sonar is dominated mostly by radar applications. In addition, the machine learning algorithms used by these systems are typically based on convolutional neural networks with some applications exploring the use of long short term memory networks. The goal of this study was to build and design a Sonar system that can classify hand gestures using a machine learning approach. Secondly, the study aims to compare convolutional neural networks to long short term memory networks as a means to classify hand gestures using sonar. A Doppler Sonar system was designed and built to be able to sense hand gestures. The Sonar system is a multi-static system containing one transmitter and three receivers. The sonar system can measure the Doppler frequency shifts caused by dynamic hand gestures. Since the system uses three receivers, three different Doppler frequency channels are measured. Three additional differential frequency channels are formed by computing the differences between the frequency of each of the receivers. These six channels are used as inputs to the deep learning models. Two different deep learning algorithms were used to classify the hand gestures; a Doppler biLSTM network [1] and a CNN [2]. Six basic hand gestures, two in each x- y- and z-axis, and two rotational hand gestures are recorded using both left and right hand at different distances. The gestures were also recorded using both left and right hands. Ten-Fold cross-validation is used to evaluate the networks' performance and classification accuracy. The LSTM was able to classify the six basic gestures with an accuracy of at least 96% but with the addition of the two rotational gestures, the accuracy drops to 47%. This result is acceptable since the basic gestures are more commonly used gestures than rotational gestures. The CNN was able to classify all the gestures with an accuracy of at least 98%. Additionally, The LSTM network is also able to classify separate left and right-hand gestures with an accuracy of 80% and The CNN with an accuracy of 83%. The study shows that CNN is the most widely used algorithm for hand gesture recognition as it can consistently classify gestures with various degrees of complexity. The study also shows that the LSTM network can also classify hand gestures with a high degree of accuracy. More experimentation, however, needs to be done in order to increase the complexity of recognisable gestures.

A computer vision system consists of many stages, depending on its application. Feature extraction and segmentation are two key stages of a typical computer vision system and hence developments in feature extraction and segmentation are significant in improving the overall performance of a computer vision system. There are many inherent problems associated with feature extraction and segmentation processes of a computer vision system. In this thesis, I propose novel solutions to some of these problems in feature extraction and segmentation. First, I explore manifold learning, which is a non-linear dimensionality reduction technique for feature extraction in high dimensional data. The classical manifold learning techniques perform dimensionality reduction assuming that original data lie on a single low dimensional manifold. However, in reality, data sets often consist of data belonging to multiple classes, which lie on their own manifolds. Thus, I propose a multi-manifold learning technique to simultaneously learn multiple manifolds present in a data set, which cannot be achieved through classical single manifold learning techniques. Secondly, in image segmentation, when the number of segments of the image is not known, automatically determining the number of segments becomes a challenging problem. In this thesis, I propose an adaptive unsupervised image segmentation technique based on spatial and feature space Dirichlet tessellation as a solution to this problem. Skin segmentation is an important as well as a challenging problem in computer vision applications. Thus, thirdly, I propose a novel skin segmentation technique by combining the multi-manifold learning-based feature extraction and Vorono\"{i} region-based image segmentation. Finally, I explore hand gesture recognition, which is a prevalent topic in intelligent human computer interaction and demonstrate that the proposed improvements in the feature extraction and segmentation stages improve the overall recognition rates of the proposed hand gesture recognition framework. I use the proposed skin segmentation technique to segment the hand, the object of interest in hand gesture recognition and manifold learning for feature extraction to automatically extract the salient features. Furthermore, in this thesis, I show that different instances of the same dynamic hand gesture have similar underlying manifolds, which allows manifold-matching based hand gesture recognition. / February 2017

The performance of a classifier is affected by a number of factors including classifier type, the input features and the desired output. This thesis examines the impact of feature selection and classification problem division on classification accuracy and complexity. Proper feature selection can reduce classifier size and improve classifier performance by minimizing the impact of noisy, redundant and correlated features. Noisy features can cause false association between the features and the classifier output. Redundant and correlated features increase classifier complexity without adding additional information. Output selection or classification problem division describes the division of a large classification problem into a set of smaller problems. Problem division can improve accuracy by allocating more resources to more difficult class divisions and enabling the use of more specific feature sets for each sub-problem. The first part of this thesis presents two methods for creating feature-selected hierarchical classifiers. The feature-selected hierarchical classification method jointly optimizes the features and classification tree-design using genetic algorithms. The multi-modal binary tree (MBT) method performs the class division and feature selection sequentially and tolerates misclassifications in the higher nodes of the tree. This yields a piecewise separation for classes that cannot be fully separated with a single classifier. Experiments show that the accuracy of MBT is comparable to other multi-class extensions, but with lower test time. Furthermore, the accuracy of MBT is significantly higher on multi-modal data sets. The second part of this thesis focuses on input feature selection measures. A number of filter-based feature subset evaluation measures are evaluated with the goal of assessing their performance with respect to specific classifiers. Although there are many feature selection measures proposed in literature, it is unclear which feature selection measures are appropriate for use with different classifiers. Sixteen common filter-based measures are tested on 20 real and 20 artificial data sets, which are designed to probe for specific feature selection challenges. The strengths and weaknesses of each measure are discussed with respect to the specific feature selection challenges in the artificial data sets, correlation with classifier accuracy and their ability to identify known informative features. The results indicate that the best filter measure is classifier-specific. K-nearest neighbours classifiers work well with subset-based RELIEF, correlation feature selection or conditional mutual information maximization, whereas Fisher's interclass separability criterion and conditional mutual information maximization work better for support vector machines. Based on the results of the feature selection experiments, two new filter-based measures are proposed based on conditional mutual information maximization, which performs well but cannot identify dependent features in a set and does not include a check for correlated features. Both new measures explicitly check for dependent features and the second measure also includes a term to discount correlated features. Both measures correctly identify known informative features in the artificial data sets and correlate well with classifier accuracy. The final part of this thesis examines the use of feature selection for time-series data by using feature selection to determine important individual time windows or key frames in the series. Time-series feature selection is used with the MBT algorithm to create classification trees for time-series data. The feature selected MBT algorithm is tested on two human motion recognition tasks: full-body human motion recognition from joint angle data and hand gesture recognition from electromyography data. Results indicate that the feature selected MBT is able to achieve high classification accuracy on the time-series data while maintaining a short test time.

The topic of this thesis is Hand Gesture Recognition and Hand Tracking for user interface applications. 3 systems were produced, as well as datasets for recognition and tracking, along with UI applications to prove the concept of the technology. These represent significant contributions to resolving the hand recognition and tracking problems for 2d systems. The systems were designed to work in video only contexts, be computationally light, provide recognition and tracking of the user's hand, and operate without user driven fine tuning and calibration. Existing systems require user calibration, use depth sensors and do not work in video only contexts, or are computationally heavy requiring GPU to run in live situations. A 2-step static hand gesture recognition system was created which can recognize 3 different gestures in real-time. A detection step detects hand gestures using machine learning models. A validation step rejects false positives. The gesture recognition system was combined with hand tracking. It recognizes and then tracks a user's hand in video in an unconstrained setting. The tracking uses 2 collaborative strategies. A contour tracking strategy guides a minimization based template tracking strategy and makes it real-time, robust, and recoverable, while the template tracking provides stable input for UI applications. Lastly, an improved static gesture recognition system addresses the drawbacks due to stratified colour sampling of the detection boxes in the detection step. It uses the entire presented colour range and clusters it into constituent colour modes which are then used for segmentation, which improves the overall gesture recognition rates. One dataset was produced for static hand gesture recognition which allowed for the comparison of multiple different machine learning strategies, including deep learning. Another dataset was produced for hand tracking which provides a challenging series of user scenarios to test the gesture recognition and hand tracking system. Both datasets are significantly larger than other available datasets. The hand tracking algorithm was used to create a mouse cursor control application, a paint application for Android mobile devices, and a FPS video game controller. The latter in particular demonstrates how the collaborating hand tracking can fulfill the demanding nature of responsive aiming and movement controls.

Gesturing is a natural way of communication between people and is used in our everyday conversations. Hand gesture recognition systems are used in many applications in a wide variety of fields, such as mobile phone applications, smart TVs, video gaming, etc. With the advances in human-computer interaction technology, gesture recognition is becoming an active research area. There are two types of devices to detect gestures; contact based devices and contactless devices. Using ultrasonic waves for determining gestures is one of the ways that is employed in contactless devices. Hand gesture recognition utilizing ultrasonic waves will be the focus of this thesis work. This thesis presents a new method for detecting and classifying a predefined set of hand gestures using a single ultrasonic transmitter and a single ultrasonic receiver. This method uses a linear frequency modulated ultrasonic signal. The ultrasonic signal is designed to meet the project requirements such as the update rate, the range of detection, etc. Also, it needs to overcome hardware limitations such as the limited output power, transmitter, and receiver bandwidth, etc. The method can be adapted to other hardware setups. Gestures are identified based on two main features; range estimation of the moving hand and received signal strength (RSS). These two factors are estimated using two simple methods; channel impulse response (CIR) and cross correlation (CC) of the reflected ultrasonic signal from the gesturing hand. A customized simple hardware setup was used to classify a set of hand gestures with high accuracy. The detection and classification were done using methods of low computational cost. This makes the proposed method to have a great potential for the implementation in many devices including laptops and mobile phones. The predefined set of gestures can be used for many control applications.

With the growth of computer power, Digital Image Processing plays a more and more important role in the modern world, including the field of industry, medical, communications, spaceflight technology etc. As a sub-field, Interactive Image Processing emphasizes particularly on the communications between machine and human. The basic flowchart is definition of object, analysis and training phase, recognition and feedback. Generally speaking, the core issue is how we define the interesting object and track them more accurately in order to complete the interaction process successfully. This thesis proposes a novel dynamic simulation scheme for interactive image processing. The work consists of two main parts: Hand Motion Detection and Hand Gesture recognition. Within a hand motion detection processing, movement of hand will be identified and extracted. In a specific detection period, the current image is compared with the previous image in order to generate the difference between them. If the generated difference exceeds predefined threshold alarm, a typical hand motion movement is detected. Furthermore, in some particular situations, changes of hand gesture are also desired to be detected and classified. This task requires features extraction and feature comparison among each type of gestures. The essentials of hand gesture are including some low level features such as color, shape etc. Another important feature is orientation histogram. Each type of hand gestures has its particular representation in the domain of orientation histogram. Because Gaussian Mixture Model has great advantages to represent the object with essential feature elements and the Expectation-Maximization is the efficient procedure to compute the maximum likelihood between testing images and predefined standard sample of each different gesture, the comparability between testing image and samples of each type of gestures will be estimated by Expectation-Maximization algorithm in Gaussian Mixture Model. The performance of this approach in experiments shows the proposed method works well and accurately.

This thesis study presents a hand gesture recognition system, which replaces input devices like keyboard and mouse with static and dynamic hand gestures, for interactive computer applications. Despite the increase in the attention of such systems there are still certain limitations in literature. Most applications require different constraints like having distinct lightning conditions, usage of a specific camera, making the user wear a multi-colored glove or need lots of training data. The system mentioned in this study disables all these restrictions and provides an adaptive, effort free environment to the user. Study starts with an analysis of the different color space performances over skin color extraction. This analysis is independent of the working system and just performed to attain valuable information about the color spaces. Working system is based on two steps, namely hand detection and hand gesture recognition. In the hand detection process, normalized RGB color space skin locus is used to threshold the coarse skin pixels in the image. Then an adaptive skin locus, whose varying boundaries are estimated from coarse skin region pixels, segments the distinct skin color in the image for the current conditions. Since face has a distinct shape, face is detected among the connected group of skin pixels by using the shape analysis. Non-face connected group of skin pixels are determined as hands. Gesture of the hand is recognized by improved centroidal profile method, which is applied around the detected hand. A 3D flight war game, a boxing game and a media player, which are controlled remotely by just using static and dynamic hand gestures, were developed as human machine interface applications by using the theoretical background of this study. In the experiments, recorded videos were used to measure the performance of the system and a correct recognition rate of ~90% was acquired with nearly real time computation.

This masters thesis describes possibilities and principles of gesture-based computer interface. The work describes general approaches for gesture control.  It also deals with implementation of the selected detection method of the hands and fingers using depth maps loaded form Kinect sensor. The implementation also deals with gesture recognition using hidden Markov models. For demonstration purposes there is also described implementation of a simple photo viewer that uses developed gesture-based computer interface. The work also focuses on quality testing and accuracy evaluation for selected gesture recognizer.

The use of hand gestures provides an attractive alternative to cumbersome interface devices such as keyboard, mouse, joystick, etc. Hand tracking has a great potential as a tool for better human-computer interaction by means of communication in a more natural and articulate way. This has motivated a very active research area concerned with computer vision-based analysis and interpretation of hand gestures and hand tracking. In this study, a real-time hand tracking system is developed. Mainly, it is image-based hand tracking and based on 2D image information. For separation and identification of finger parts, coloured markers are used. In order to obtain 3D tracking, a stereo vision approach is used where third dimension is obtained by depth information. In order to see results in 3D, a 3D hand model is developed and Java 3D is used as the 3D environment. Tracking is tested on two different types of camera: a cheap USB web camera and Sony FCB-IX47AP camera, connected to the Matrox Meteor frame grabber with a standard Intel Pentium based personal computer. Coding is done by Borland C++ Builder 6.0 and Intel Image Processing and Open Source Computer Vision (OpenCV) library are used as well. For both camera types, tracking is found to be robust and efficient where hand tracking at ~8 fps could be achieved. Although the current progress is encouraging, further theoretical as well as computational advances are needed for this highly complex task of hand tracking.