The project introduces an application using computer vision for Hand gesture recognition. A camera records a live video stream, from which a snapshot is taken with the help of interface. The system is trained for each type of count hand gestures (one, two, three, four, and five) at least once. After that a test gesture is given to it and the system tries to recognize it.A research was carried out on a number of algorithms that could best differentiate a hand gesture. It was found that the diagonal sum algorithm gave the highest accuracy rate. In the preprocessing phase, a self-developed algorithm removes the background of each training gesture. After that the image is converted into a binary image and the sums of all diagonal elements of the picture are taken. This sum helps us in differentiating and classifying different hand gestures.Previous systems have used data gloves or markers for input in the system. I have no such constraints for using the system. The user can give hand gestures in view of the camera naturally. A completely robust hand gesture recognition system is still under heavy research and development; the implemented system serves as an extendible foundation for future work.

This master's thesis explores whether time-frequency techniques can be utilized in a ground penetrating radar system. The system studied is the HUMUS system which has been developed at FOI, and which is used for the detection and classification of buried land mines. The objective of this master's thesis is twofold. First of all it is supposed to give a theoretical introduction to the wavelet transform and wavelet packets, and also to introduce general time-frequency transformations. Secondly, the thesis presents and implements an adaptive method, which is used to perform the task of a feature extractor. The wavelet theory presented in this thesis gives a first introduction to the concept of time-frequency transformations. The wavelet transform and wavelet packets are studied in detail. The most important goal of this introduction is to define the theoretical background needed for the second objective of the thesis. However, some additional concepts will also be introduced, since they were deemed necessary to include in an introduction to wavelets. To illustrate the possibilities of wavelet techniques in the existing HUMUS system, one specific application has been chosen. The application chosen is feature extraction. The method for feature extraction described in this thesis uses wavelet packets to transform theoriginal radar signal into a form where the features of the signal are better revealed. One of the algorithms strengths is its ability to adapt itself to the kind of input radar signals expected. The algorithm will pick the "best" wavelet packet from a large number of possible wavelet packets. The method we use in this thesis emanates from a previously publicized dissertation. The method proposed in that dissertation has been modified to the specific environment of the HUMUS system. It has also been implemented in MATLAB, and tested using data obtained by the HUMUS system. The results are promising; even"weak"objects can be revealed using the method.

The human auditory perception system is much more noise-robust than any state-of the art automatic speech recognition (ASR) system. It is expected that the noise-robustness of speech feature can be improved by employing the human auditory based feature extraction procedure. In this thesis, we investigate modifying the commonly-used feature extraction process for automatic speech recognition systems. A novel frequency masking curve, which is based on modeling the basilar membrane as a cascade system of damped simple harmonic oscillators, is used to replace the critical-band masking curve to compute the masking threshold. We mathematically analyze the coupled motion of the oscillator system (basilar membrane) when they are driven by short-time stationary (speech) signals. Based on the analysis, we derive the relation between the amplitudes of neighboring oscillators, and accordingly insert a masking module in the front-end signal processing stage to modify the speech spectrum. We evaluate the proposed method on the Aurora 2.0 noisy-digit speech database. When combined with the commonly-used cepstral mean subtraction post-processing, the proposed auditory front-end module achieves a significant improvement. The method of correlational masking effect curve combine with CMS can achieves relative improvements of 25.9% over the baseline respectively. After applying the methods iteratively, the relative improvement improves from 25.9% to 30.3%.

Missile Detection System (MDS) is one of the main components of a self-protection system developed against the threat of guided missiles for airborne platforms. The requirements such as time critical operation and high accuracy in classification performance make the &lsquo / Pattern Recognition&rsquo / problem of an MDS a hard task. Problem can be defined in two main parts such as &lsquo / Feature Set Evaluation&rsquo / (FSE) and &lsquo / Classifier&rsquo / designs. The main goal of feature set evaluation is to employ a dimensionality reduction process for the input data set, while not disturbing the classification performance in the result. In this thesis study, FSE approaches are investigated for the pattern recognition problem of a generic MDS. First, synthetic data generation is carried out in software environment by employing generic models and assumptions in order to reflect the nature of a realistic problem environment. Then, data sets are evaluated in order to draw a baseline for further feature set evaluation approaches. Further, a theoretical background including the concepts of Class Separability, Feature Selection and Feature Extraction is given. Several widely used methods are assessed in terms of convenience for the problem by giving necessary justifications depending on the data set characteristics. Upon this background, software implementations are performed regarding several feature set evaluation techniques. Simulations are carried out in order to process dimensionality reduction. For the evaluation of the resulting data sets in terms of classification performance, software implementation of a classifier is realized. Resulting classification performances of the applied approaches are compared and evaluated.

In this thesis, a feature extraction algorithm based on 2D Local Discriminant Bases (LDB) search is developed for acoustic and hyperspectral data. The developed algorithm extracts the relevant features by both eliminating the irrelevant ones and/or by merging the ones that do not provide extra information on their own. It is implemented on real world data to separate aflatoxin contaminated or high risk hazelnuts from the sound ones by using impact acoustic and hyperspectral data. Impact acoustics data is used to sort cracked and intact shell hazelnuts with high classification accuracy. Hypespectral images of the shelled and roasted (SRT) hazelnuts are used for classification and the algorithm extracted the spectral and spatial-frequency features for that classification. Aflatoxin concentration of the SRT category hazelnuts is automatically decreased to 0.7 ppb from 608 ppb by eliminating the detected contaminated ones.

Electrocardiography (ECG) is the most important noninvasive tool used for diagnosing heart diseases. An ECG interpretation program can help the physician state the diagnosis correctly and take the corrective action. Detection of the QRS complexes from the ECG signal is usually the first step for an interpretation tool. The main goal in this thesis was to develop robust and high performance QRS detection algorithms, and using the results of the QRS detection step, to classify these beats according to their different pathologies. In order to evaluate the performances, these algorithms were tested and compared in Massachusetts Institute of Technology Beth Israel Hospital (MIT-BIH) database, which was developed for research in cardiac electrophysiology. In this thesis, four promising QRS detection methods were taken from literature and implemented: a derivative based method (Method I), a digital filter based method (Method II), Tompkin&rsquo / s method that utilizes the morphological features of the ECG signal (Method III) and a neural network based QRS detection method (Method IV). Overall sensitivity and positive predictivity values above 99% are achieved with each method, which are compatible with the results reported in literature. Method III has the best overall performance among the others with a sensitivity of 99.93% and a positive predictivity of 100.00%. Based on the detected QRS complexes, some features were extracted and classification of some beat types were performed. In order to classify the detected beats, three methods were taken from literature and implemented in this thesis: a Kth nearest neighbor rule based method (Method I), a neural network based method (Method II) and a rule based method (Method III). Overall results of Method I and Method II have sensitivity values above 92.96%. These findings are also compatible with those reported in the related literature. The classification made by the rule based approach, Method III, did not coincide well with the annotations provided in the MIT-BIH database. The best results were achieved by Method II with the overall sensitivity value of 95.24%.

A generic missile warner decision algorithm for airborne platforms with an emphasis on multiple classifier systems is proposed within the scope of this thesis. For developing the algorithm, simulation data are utilized. The simulation data are created in order to cover a wide range of real-life scenarios and for this purpose a scenario creation methodology is proposed. The scenarios are simulated by a generic missile warner simulator and tracked object data for each scenario are produced. Various feature extraction techniques are applied to the output data of the scenarios and feature sets are generated. Feature sets are examined by using various statistical methods. The performance of selected multiple classifier systems are evaluated for all feature sets and experimental results are presented.

Roads are significant objects of an infrastructure and the extraction of roads from aerial and satellite images are important for different applications such as automated map generation and change detection. Roads are also important to detect other structures such as buildings and urban areas. In this thesis, the road extraction approach is based on Active Contour Models for 1- meter resolution gray level images. Active Contour Models contains Snake Approach. During applications, the road structure was separated as salient-roads, non-salient roads and crossings and extraction of these is provided by using Ribbon Snake and Ziplock Snake methods. These methods are derived from traditional snake model. Finally, various experimental results were presented. Ribbon and Ziplock Snake methods were compared for both salient and non-salient roads. Also these methods were used to extract roads in an image. While Ribbon snake is described for extraction of salient roads in an image, Ziplock snake is applied for extraction of non-salient roads. Beside these, some constant variables in literature were redefined and expressed in a formula as depending on snake approach and a new approach for extraction of crossroads were described and tried.

Enzymes are proteins that play an important role in biochemical reactions as catalysts. They are classified based on the reaction they catalyzed, in a hierarchical scheme by International Enzyme Commission (EC). This hierarchical scheme is expressed as a four-level tree structure and a unique number is assigned to each enzyme class. There are six major classes at the top level according to the reaction they carried out and sub-classes at the lower levels are further specific reactions of these classes. The aim of this thesis is to build a three-level classification model based on the hierarchical structure of EC classes. ENZYME database is used to extract the information of EC classes and enzymes are assigned to these EC classes. Primary sequences of enzymes extracted from UniProtKB/Swiss-Prot database are used to extract features. A subsequence based feature extraction method, Subsequence Profile Map (SPMap) is used in this study. SPMap is a method that explicitly models the differences between positive and negative examples. SPMap pays attention to the conserved subsequences of protein sequences in the same class. SPMap generates the feature vector of each sample protein as a probability of fixed-length subsequences of this protein with respect to a probabilistic profile matrix calculated by clustering similar subsequences in the training dataset. In our case, positive and negative training datasets are prepared for each class, at each level of the tree structure. Subsequence Profile Map (SPMap) is used for feature extraction and Support Vector Machines (SVMs) are used for classification. Five-fold cross validation is used to test the performance of the system. The overall sensitivity, specificity and AUC values for the six major EC classes are 93.08%, 98.95% and 0.993, respectively. The results at the second- and third- levels are also promising.

Visual Attention is an interesting concept that constantly widens its application areas in the field of image processing and computer vision. The main idea of visual attention is to find the locations on the image that are visually attractive. In this thesis, the visually attractive regions are extracted and tracked in video sequences coming from the vision systems of mobile platforms. First, the salient regions are extracted in each frame and a feature vector is constructed for each one. Then Scale Invariant Feature Transform (SIFT) is applied only to the salient regions to extract more stable features. The tracking is achieved by matching the salient regions of consecutive frames by comparing their feature vectors. Then the SIFT points of salient regions are matched to calculate the shift values for the matched pairs. Limiting the SIFT application to only the salient regions results in significantly reduced computational cost. Moreover, the salient region detection procedure is also limited to the predetermined regions throughout the video sequence in order to increase the efficiency. In addition, the visual attention channels are limited to the most dominant features of the regions. Experimental results that compare the algorithm outputs with ground-truth data reveal that, the proposed algorithm has fine tracking performance together with acceptable computational cost. Promising results are obtained even with blurred video sequences typical of ground vehicles and robots and in an uncontrolled environment.