Browsing by Subject "feature extraction"

Now showing 1 - 5 of 5

Open Access
A comparison of different approaches to target differentiation with sonar
(2001) Ayrulu (Erdem), Birsel
This study compares the performances of di erent classication schemes and fusion techniques for target di erentiation and localization of commonly encountered features in indoor robot environments using sonar sensing Di erentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identication map building navigation obstacle avoidance and target tracking The classication schemes employed include the target di erentiation algorithm developed by Ayrulu and Barshan statistical pattern recognition techniques fuzzy c means clustering algorithm and articial neural networks The fusion techniques used are Dempster Shafer evidential reasoning and di erent voting schemes To solve the consistency problem arising in simple ma jority voting di erent voting schemes including preference ordering and reliability measures are proposed and veried experimentally To improve the performance of neural network classiers di erent input signal representations two di erent training algorithms and both modular and non modular network structures are considered The best classication and localization scheme is found to be the neural network classier trained with the wavelet transform of the sonar signals This method is applied to map building in mobile robot environments Physically di erent sensors such as infrared sensors and structured light systems besides sonar sensors are also considered to improve the performance in target classication and localization.
Open Access
Comparison of multi-scale directional feature extraction methods for image processing
(2013) Bozkurt, Alican
Almost all images that are presented in classification problems regardless of area of application, have directional information embedded into its texture. Although there are many algorithms developed to extract this information, there is no ‘golden’ method that works the best every image. In order to evaluate performance of these developed algorithms, we consider 7 different multi-scale directional feature extraction algorithms along with our own multi-scale directional filtering framework. We perform tests on several problems from diverse areas of application such as font/style recognition on English, Arabic, Farsi, Chinese, and Ottoman texts, grading of follicular lymphoma images, and stratum corneum thickness calculation. We present performance metrics such as k-fold cross validation accuracies and times to extract feature from one sample, and compare with the respective state of art on each problem. Our multi-resolution computationally efficient directional approach provides results on a par with the state of the art directional feature extraction methods.
Open Access
Methods fro automatic target classification in radar
(2009) Eryıldırım, Abdülkadir
Automatic target recognition (ATR) using radar is an active research area. In this thesis, we develop new automatic radar target classification methods. We focus on two specific problems: (i) Synthetic Aperture Radar (SAR) target classification and (ii)Pulse-doppler radar (PDR) target classification. SAR and PDR target classification are extensively used for ground and battlefield surveillance tasks. In the first part of the thesis, a novel descriptive feature parameter extraction method from Synthetic Aperture Radar (SAR) images is proposed. Feature extraction and classification methods which were developed to handle optical images are usually inappropriate for SAR images because of the multiplicative nature of the severe speckle noise and imaging defects. In addition, SAR images of the same object taken at different aspect angles show great differences, which makes it hard to obtain satisfactory results. Consequently, feature parameter extraction method based on two-dimensional cepstrum is proposed and its object recognition results are compared with principal component analysis (PCA) and independent component analysis (ICA) methods. The extracted feature parameters are classified using Support Vector Machines (SVMs). Experimental results are presented. In the second part of the thesis, the automatic classification experiments over ground surveillance Pulse-doppler radar echo signal are investigated in order to overcome the limitations of human operators and improve the classification accuracy. Covariance method approach is introduced for PDR echo signal classification. To the best our knowledge, the use of covariance method-based classification is not investigated in radar automatic target classification problems. Furthermore, different approaches which involves SVMs are developed. As feature parameters, cepstrum and MFCCs are used. Performances of these two approaches are compared with the Gaussian Mixture Models (GMM) based classification scheme. Experimental results and conclusions are presented.
Open Access
Novel methods for microscopic image processing, analysis, classification and compression
(2013) Suhre, Alexander
Microscopic images are frequently used in medicine and molecular biology. Many interesting image processing problems arise after the initial data acquisition step, since image modalities are manifold. In this thesis, we developed several algorithms in order to handle the critical pipeline of microscopic image storage/ compression and analysis/classification more efficiently. The first step in our processing pipeline is image compression. Microscopic images are large in size (e.g. 100K-by-100K pixels), therefore finding efficient ways of compressing such data is necessary for efficient transmission, storage and evaluation. We propose an image compression scheme that uses the color content of a given image, by applying a block-adaptive color transform. Microscopic images of tissues have a very specific color palette due to the staining process they undergo before data acquisition. The proposed color transform takes advantage of this fact and can be incorporated into widely-used compression algorithms such as JPEG and JPEG 2000 without creating any overhead at the receiver due to its DPCM-like structure. We obtained peak signal-to-noise ratio gains up to 0.5 dB when comparing our method with standard JPEG. The next step in our processing pipeline is image analysis. Microscopic image processing techniques can assist in making grading and diagnosis of images reproducible and by providing useful quantitative measures for computer-aided diagnosis. To this end, we developed several novel techniques for efficient feature extraction and classification of microscopic images. We use region co-difference matrices as inputs for the classifier, which have the main advantage of yielding multiplication-free computationally efficient algorithms. The merit of the co-difference framework for performing some important tasks in signal processing is discussed. We also introduce several methods that estimate underlying probability density functions from data. We use sparsity criteria in the Fourier domain to arrive at efficient estimates. The proposed methods can be used for classification in Bayesian frameworks. We evaluated the performance of our algorithms for two image classification problems: Discriminating between different grades of follicular lymphoma, a medical condition of the lymph system, as well as differentiating several cancer cell lines from each another. Classification accuracies over two large data sets (270 images for follicular lymphoma and 280 images for cancer cell lines) were above 98%.
Open Access
Recognition and classification of human activities using wearable sensors
(2012) Yurtman, Aras
We address the problem of detecting and classifying human activities using two different types of wearable sensors. In the first part of the thesis, a comparative study on the different techniques of classifying human activities using tag-based radio-frequency (RF) localization is provided. Position data of multiple RF tags worn on the human body are acquired asynchronously and non-uniformly. Curves fitted to the data are re-sampled uniformly and then segmented. The effect of varying the relevant system parameters on the system accuracy is investigated. Various curve-fitting, segmentation, and classification techniques are compared and the combination resulting in the best performance is presented. The classifiers are validated through the use of two different cross-validation methods. For the complete classification problem with 11 classes, the proposed system demonstrates an average classification error of 8.67% and 21.30% for 5-fold and subject-based leave-one-out (L1O) cross validation, respectively. When the number of classes is reduced to five by omitting the transition classes, these errors become 1.12% and 6.52%. The system demonstrates acceptable classification performance despite that tag-based RF localization does not provide very accurate position measurements. In the second part, data acquired from five sensory units worn on the human body, each containing a tri-axial accelerometer, a gyroscope, and a magnetometer, during 19 different human activities are used to calculate inter-subject and interactivity variations in the data with different methods. Absolute, Euclidean, and dynamic time-warping (DTW) distances are used to assess the similarity of the signals. The comparisons are made using time-domain data and feature vectors. Different normalization methods are used and compared. The “best” subject is defined and identified according to his/her average distance to the other subjects.Based on one of the similarity criteria proposed here, an autonomous system that detects and evaluates physical therapy exercises using inertial sensors and magnetometers is developed. An algorithm that detects all the occurrences of one or more template signals (exercise movements) in a long signal (physical therapy session) while allowing some distortion is proposed based on DTW. The algorithm classifies the executions in one of the exercises and evaluates them as correct/incorrect, identifying the error type if there is any. To evaluate the performance of the algorithm in physical therapy, a dataset consisting of one template execution and ten test executions of each of the three execution types of eight exercise movements performed by five subjects is recorded, having totally 120 and 1,200 exercise executions in the training and test sets, respectively, as well as many idle time intervals in the test signals. The proposed algorithm detects 1,125 executions in the whole test set. 8.58% of the executions are missed and 4.91% of the idle intervals are incorrectly detected as an execution. The accuracy is 93.46% for exercise classification and 88.65% for both exercise and execution type classification. The proposed system may be used to both estimate the intensity of the physical therapy session and evaluate the executions to provide feedback to the patient and the specialist.