Browsing by Subject "Image processing."
Now showing 1 - 20 of 26
Results Per Page
Sort Options
Item Open Access 3-dimensional median-based algorithms in image sequence processing(Bilkent University, 1990) Alp, Münire BilgeThis thesis introduces new 3-dimensional median-based algorithms to be used in two of the main research areas in image sequence proc(',ssi,ng; image sequence enhancement and image sequence coding. Two new nonlinear filters are developed in the field of image sequence enhancement. The motion performances and the output statistics of these filters are evaluated. The simulations show that the filters improve the image quality to a large extent compared to other examples from the literature. The second field addressed is image sequence coding. A new 3-dimensional median-based coding and decoding method is developed for stationary images with the aim of good slow motion performance. All the algorithms developed are simulated on real image sequences using a video sequencer.Item Open Access 3D reconstruction of point clouds using multi-view orthographic projections(Bilkent University, 2006) Topçu, OsmanA method to reconstruct 3D point clouds using multi-view orthographic projections is examined. Point clouds are generated by means of a stochastic process. This stochastic process is designed to generate point clouds that mimic microcalcification formation in breast tissue. Point clouds are generated using a Gibbs sampler algorithm. Orthographic projections of point clouds from any desired orientation are generated. Volumetric intersection method is employed to perform the reconstruction from these orthographic projections. The reconstruction may yield erroneous reconstructed points. The types of these erroneous points are analyzed along with their causes and a performance measure based on linear combination is devised. Experiments have been designed to investigate the effect of the number of projections and the number of points to the performance of reconstruction. Increasing the number of projections and decreasing the number of points resulted in better reconstructions that are more similar to the original point clouds. However, it is observed that reconstructions do not improve considerably upon increasing the number of projections after some number. This method of reconstruction serves well to find locations of original points.Item Open Access Activity analysis for assistive systems(Bilkent University, 2014) İşcen, AhmetAlthough understanding and analyzing human actions is a popular research topic in computer vision, most of the research has focused on recognizing ”ordinary” actions, such as walking and jumping. Extending these methods for more specific domains, such as assistive technologies, is not a trivial task. In most cases, these applications contain more fine-grained activities with low inter-class variance and high intra-class variance. In this thesis, we propose to use motion information from snippets, or small video intervals, in order to recognize actions from daily activities. Proposed method encodes the motion by considering the motion statistics, such as the variance and the length of trajectories. It also encodes the position information by using a spatial grid. We show that such approach is especially helpful for the domain of medical device usage, which contains actions with fast movements Another contribution that we propose is to model the sequential information of actions by the order in which they occur. This is especially useful for fine-grained activities, such as cooking activities, where the visual information may not be enough to distinguish between different actions. As for the visual perspective of the problem, we propose to combine multiple visual descriptors by weighing their confidence values. Our experiments show that, temporal sequence model and the fusion of multiple descriptors significantly improve the performance when used together.Item Open Access Animated mesh simplification based on saliency metrics(Bilkent University, 2008) Tolgay, AhmetMesh saliency identifies the visually important parts of a mesh. Mesh simplification algorithms using mesh saliency as simplification criterion preserve the salient features of a static 3D model. In this thesis, we propose a saliency measure that will be used to simplify animated 3D models. This saliency measure uses the acceleration and deceleration information about a dynamic 3D mesh in addition to the saliency information for static meshes. This provides the preservation of sharp features and visually important cues during animation. Since oscillating motions are also important in determining saliency, we propose a technique to detect oscillating motions and incorporate it into the saliency based animated model simplification algorithm. The proposed technique is experimented on animated models making oscillating motions and promising visual results are obtained.Item Open Access An Automated rule based visual printed circuit board inspection system which uses mathematical morphological image processing algorithms(Bilkent University, 1990) Oğuz, Seyfullah HalitIn this thesis, the design and implementation of an automated rule based visual printed circuit board (PCB) inspection system are presented. The developed system makes use of mathematical morphology based image processing algorithms. This system is designed for the detection of the PCB defects related to the conducting structures on the PCBs. For this purpose, four new algorithms, three of which are defect detection algorithms, are designed, and an already existing algorithm is modified for its implementation in our system. The designed defect detection algorithms respectively verify the minimum conductor trace width, minimum land width, and the minimum conductor trace spacing requirements on digital binary PCB images. The implementation of a prototype system is made in our image processing laboratory and the necessary computer programs are developed. These programs control the image processor and apply the defect detection algorithms to discrete binary PCB test images.Item Open Access Cepstral methods for image feature extraction(Bilkent University, 2010) Çakır, SerdarImage feature extraction is one of the most vital tasks in computer vision and pattern recognition applications due to its importance in the preparation of data extracted from images. In this thesis, 2D cepstrum based methods (2D mel- and Mellin-cepstrum) are proposed for image feature extraction. The proposed feature extraction schemes are used in face recognition and target detection applications. The cepstral features are invariant to amplitude and translation changes. In addition, the features extracted using 2D Mellin-cepstrum method are rotation invariant. Due to these merits, the proposed techniques can be used in various feature extraction problems. The feature matrices extracted using the cepstral methods are classified by Common Matrix Approach (CMA) and multi-class Support Vector Machine (SVM). Experimental results show that the success rates obtained using cepstral feature extraction algorithms are higher than the rates obtained using standard baselines (PCA, Fourier-Mellin Transform, Fourier LDA approach). Moreover, it is observed that the features extracted by cepstral methods are computationally more efficient than the standard baselines. In target detection task, the proposed feature extraction methods are used in the detection and discrimination stages of a typical Automatic Target Recognition (ATR) system. The feature matrices obtained from the cepstral techniques are applied to the SVM classifier. The simulation results show that 2D cepstral feature extraction techniques can be used in the target detection in SAR images.Item Open Access Comparison of multi-scale directional feature extraction methods for image processing(Bilkent University, 2013) Bozkurt, AlicanAlmost 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.Item Open Access Design and implementation of a radiological image viewing tool(Bilkent University, 1993) Keskin, GürhanRecent developments in Picture Archiving and Communication Systems (PACS) in clinical environment allow physicians and radiologists to access and assess radiographic images directly through imaging workstations. In this thesis, an imaging workstation called RADVIEW^ has been designed and implemented for using in a PACS environment in radiology departments of large hospitals. The main function of RADVIEVV is the archiving of and access to radiological images by maintaining user friendly interactive environment to radiologists. The system can provide rapid access to any or all radiological information associated with a patient.Item Open Access Dynamic texture analysis in video with application to flame, smoke and volatile organic compound vapor detection(Bilkent University, 2009) Günay, OsmanDynamic textures are moving image sequences that exhibit stationary characteristics in time such as fire, smoke, volatile organic compound (VOC) plumes, waves, etc. Most surveillance applications already have motion detection and recognition capability, but dynamic texture detection algorithms are not integral part of these applications. In this thesis, image processing based algorithms for detection of specific dynamic textures are developed. Our methods can be developed in practical surveillance applications to detect VOC leaks, fire and smoke. The method developed for VOC emission detection in infrared videos uses a change detection algorithm to find the rising VOC plume. The rising characteristic of the plume is detected using a hidden Markov model (HMM). The dark regions that are formed on the leaking equipment are found using a background subtraction algorithm. Another method is developed based on an active learning algorithm that is used to detect wild fires at night and close range flames. The active learning algorithm is based on the Least-Mean-Square (LMS) method. Decisions from the sub-algorithms, each of which characterize a certain property of the texture to be detected, are combined using the LMS algorithm to reach a final decision. Another image processing method is developed to detect fire and smoke from moving camera video sequences. The global motion of the camera is compensated by finding an affine transformation between the frames using optical flow and RANSAC. Three frame change detection methods with motion compensation are used for fire detection with a moving camera. A background subtraction algorithm with global motion estimation is developed for smoke detection.Item Open Access Hardware acceleration of similarity queries using graphic processor units(Bilkent University, 2009) Genç, AtillaA Graphic Processing Unit (GPU) is primarily designed for real-time rendering. In contrast to a Central Processing Unit (CPU) that have complex instructions and a limited number of pipelines, a GPU has simpler instructions and many execution pipelines to process vector data in a massively parallel fashion. In addition to its regular tasks, GPU instruction set can be used for performing other types of general-purpose computations as well. Several frameworks like Brook+, ATI CAL, OpenCL, and Nvidia Cuda have been proposed to utilize computational power of the GPU in general computing. This has provided interest and opportunities for accelerating different types of applications. This thesis explores ways of taking advantage of the GPU in the field of metric space-based similarity searching. The KVP index structure has a simple organization that lends itself to be easily processed in parallel, in contrast to tree-based structures that requires frequent ”pointer chasing” operations. Several implementations using the general purpose GPU programming frameworks (Brook+, ATI CAL and OpenCL) based on the ATI platform are provided. Experimental results of these implementations show that the GPU versions presented in this work are several times faster than the CPU versions.Item Open Access Image processing methods for computer-aided interpretation of microscopic images(Bilkent University, 2012) Keskin, Musa FurkanImage processing algorithms for automated analysis of microscopic images have become increasingly popular in the last decade with the remarkable growth in computational power. The advent of high-throughput scanning devices allows for computer-assisted evaluation of microscopic images, resulting in a quick and unbiased image interpretation that will facilitate the clinical decision-making process. In this thesis, new methods are proposed to provide solution to two image analysis problems in biology and histopathology. The first problem is the classification of human carcinoma cell line images. Cancer cell lines are widely used for research purposes in laboratories all over the world. In molecular biology studies, researchers deal with a large number of specimens whose identity have to be checked at various points in time. A novel computerized method is presented for cancer cell line image classification. Microscopic images containing irregular carcinoma cell patterns are represented by subwindows which correspond to foreground pixels. For each subwindow, a covariance descriptor utilizing the dual-tree complex wavelet transform (DTCWT) coefficients as pixel features is computed. A Support Vector Machine (SVM) classifier with radial basis function (RBF) kernel is employed for final classification. For 14 different classes, we achieve an overall accuracy of 98%, which outperforms the classical covariance based methods. Histopathological image analysis problem is related to the grading of follicular lymphoma (FL) disease. FL is one of the commonly encountered cancer types in the lymph system. FL grading is based on histological examination of hematoxilin and eosin (H&E) stained tissue sections by pathologists who make clinical decisions by manually counting the malignant centroblast (CB) cells. This grading method is subject to substantial inter- and intra-reader variability and sampling bias. A computer-assisted method is presented for detection of CB cells in H&Estained FL tissue samples. The proposed algorithm takes advantage of the scalespace representation of FL images to detect blob-like cell regions which reside in the scale-space extrema of the difference-of-Gaussian images. Multi-stage false positive elimination strategy is employed with some statistical region properties and textural features such as gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM) and Scale Invariant Feature Transform (SIFT). The algorithm is evaluated on 30 images and 90% CB detection accuracy is obtained, which outperforms the average accuracy of expert hematopathologists.Item Open Access Naming faces on the web(Bilkent University, 2010) Zitouni, HilalIn this study, we introduce a method to name less-frequently appearing people on the web via naming frequently appearing ones first. Current image search engines are widely used for querying a person, however; retrievals are based on textual content; therefore, the results are not satisfactory. On the other hand, although; face recognition is a long standing problem; it is tested for limited sizes and successful results are acquired just for face images captured under controlled environments. Faces on the web, contrarily are huge in amount and vary in pose, illumination, occlusion and facial attributes. Recent researches on the area, suggest not to use simply the visual or textual content alone, but to combine them both. With this approach, face recognition problem is simplified to a face-name association problem. Following these approaches, in our method textual and visual information is combined to name faces. We divide the problem into two sub problems, first the more frequently appearing faces, then the less-frequently appearing faces on the web images are named. A supervised algorithm is used for naming a specified number of categories belonging to more frequently appearing faces. The faces that are not matched with any category are then considered to be the less-frequently appearing faces and labeled using the textual content. We extracted all the names from textual contents, and then eliminate the ones used to label frequentlyappearing faces before. The remaining names are the candidate categories for lessfrequently appearing faces. Each detected less-frequently appearing face finally matched to the names extracted from their corresponding textual content. In order to prune the irrelevant face images, finally, the most similar faces among this collection are found to be matched with their corresponding category. In our experiments, the method is applied on two different datasets. Bothdatasets are constructed from the images captured in realistic environments, varying in pose, illumination, facial expressions, occlusions and etc. The results of the experiments proved that the combination of textual and visual contents on realistic face images outperforms the methods that use either one of them. Besides, handling the face recognition problem as a face-name association, improves the results for the face images collected from uncontrolled environments.Item Open Access Novel methods for microscopic image processing, analysis, classification and compression(Bilkent University, 2013) Suhre, AlexanderMicroscopic 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%.Item Open Access Perceptual watersheds for cell segmentation in fluorescence microscopy images(Bilkent University, 2012) Arslan, SalimHigh content screening aims to analyze complex biological systems and collect quantitative data via automated microscopy imaging to improve the quality of molecular cellular biology research in means of speed and accuracy. More rapid and accurate high-throughput screening becomes possible with advances in automated microscopy image analysis, for which cell segmentation commonly constitutes the core step. Since the performance of cell segmentation directly a ects the output of the system, it is of great importance to develop e ective segmentation algorithms. Although there exist several promising methods for segmenting monolayer isolated and less con uent cells, it still remains an open problem to segment more con uent cells that grow in aggregates on layers. In order to address this problem, we propose a new marker-controlled watershed algorithm that incorporates human perception into segmentation. This incorporation is in the form of how a human locates a cell by identifying its correct boundaries and piecing these boundaries together to form the cell. For this purpose, our proposed watershed algorithm de nes four di erent types of primitives to represent di erent types of boundaries (left, right, top, and bottom) and constructs an attributed relational graph on these primitives to represent their spatial relations. Then, it reduces the marker identi cation problem to the problem of nding prede ned structural patterns in the constructed graph. Moreover, it makes use of the boundary primitives to guide the ooding process in the watershed algorithm. Working with uorescence microscopy images, our experiments demonstrate that the proposed algorithm results in locating better markers and obtaining better cell boundaries for both less and more con uent cells, compared to previous cell segmentation algorithms.Item Open Access Regularized motion estimation techniques and their applications to video coding(Bilkent University, 1996) Kıranyaz, SerkanNovel regularized motion estimation techniques and their possible applications to video coding are presented. A block matching motion estimation algorithm which extracts better block motion field by forming and ininimizing a suitable energy function is introduced. Based on ciri ¿idciptive structure onto block sizes, cui cidvcinced block matching ¿ilgorithm is presented. The block sizes are adaptively ¿idjusted according to the motion. Blockwise coarse to fine segmentation based motion estimation algorithm is introduced for further reduction on the number of bits that are spent lor the coding of the block motion vectors. Motion estiiricition algorithms which can be used lor ¿iverage motion determination and artificial frame generation by fractional motion compensation are ¿ilso developed. Finallj^, an alternative motion estimation cind compensation technique which defines feciture based motion vectors on the ob ject boundciries and reconstructs the decoded frame from the interpolation of the compensated object boundaries is presented. All the algorithms developed in this thesis are simulated on recil or synthetic images cind their performance is demonstrcited.Item Open Access Scene classification using bag-of-regions representation(Bilkent University, 2007) Gökalp, DemirSignificant growth of multimedia data creates the need for more complicated approaches in image understanding, classification and retrieval. Semantic scene classification is a popular research area which categorizes images into semantic categories for applications like content based image retrieval. In the near future, content based image retrieval will be much more important especially for the next generation internet technologies so new approaches are very welcomed in this subject. Research has showed that classifying images using components like regions, pixels or objects is a challenging work because of the ambiguity of the visual data. The main idea about image classification is to find similarities between these components to get information about the content of the image. This thesis describes our work on classification of outdoor scenes. As the first step, regions are extracted using one-class classification and patch-based clustering algorithms. The components (pixels, regions and objects) in outdoor images have particular spatial and geometric interactions so dividing images into meaningfully clustered regions has important benefits for a detailed content analysis. For region clustering, features from different levels make specific contributions but to avoid the ambiguity, we need to use low level information and more global information together for the clustering step. Also, using spatial relationships between clustered regions, we can make inference about the detailed content of outdoor images from specific to general. Therefore, after rough segmentation, scene representations are constructed with and without spatial information. At the final step Bayesian classification approach is used with the two different scene representations. The developed methods were tested on the MIT LabelMe dataset, and the results showed that using regions and their spatial relationships improved the classification accuracy.Item Open Access Segmentation and classification of cervical cell images(Bilkent University, 2010) Kale, AslıCervical cancer can be prevented if it is detected and treated early. Pap smear test is a manual screening procedure used to detect cervical cancer and precancerous changes in an uterine cervix. However, this procedure is costly and it may result in inaccurate diagnoses due to human error like intra- and interobserver variability. Therefore, a computer-assisted screening system will be very bene cial to prevent cervical cancer if it increases the reliability of diagnoses. In this thesis, we propose a computer-assisted diagnosis system which helps cyto-technicians by sorting cells in a Pap smear slide according to their abnormality degree. There are three main components of such a system. Firstly, cells along with their nuclei are located using a segmentation procedure on an image taken using a microscope. Then, features describing these segmented cells are extracted. Finally, the cells are sorted according to their abnormality degree based on the extracted features. Di erent from the related studies that require images of a single cervical cell, we propose a non-parametric generic segmentation algorithm that can also handle images of overlapping cells. We use thresholding as the rst phase to extract background regions for obtaining remaining cell regions. The second phase consists of segmenting the cell regions by a non-parametric hierarchical segmentation algorithm that uses the spectral and shape information as well as the gradient information. The last phase aims to partition the cell region into true structures of each nucleus and the whole cytoplasm area by classifying the nal segments as nucleus or cytoplasm region. We evaluate our segmentation method both quantitatively and qualitatively using two data sets.By proposing an unsupervised screening system, we aim to approach the problem in a di erent way when compared to the related studies that concentrate on classi cation. In order to rank the cells in a Pap slide, we rst perform hierarchical clustering on 14 di erent cell features. The initial ordering of the cells is determined as the leaf ordering of the constructed hierarchical tree. Then, this initial ordering is improved by applying an optimal leaf ordering algorithm. The experiments with ground truth data show the e ectiveness of the proposed approach under di erent experimental settings.Item Open Access Semantic scene classification for content-based image retrieval(Bilkent University, 2008) Çavuş, ÖzgeContent-based image indexing and retrieval have become important research problems with the use of large databases in a wide range of areas. Because of the constantly increasing complexity of the image content, low-level features are no longer sufficient for image content representation. In this study, a content-based image retrieval framework that is based on scene classification for image indexing is proposed. First, the images are segmented into regions by using their color and line structure information. By using the line structures of the images the regions that do not consist of uniform colors such as man made structures are captured. After all regions are clustered, each image is represented with the histogram of the region types it contains. Both multi-class and one-class classification models are used with these histograms to obtain the probability of observing different semantic classes in each image. Since a single class with the highest probability is not sufficient to model image content in an unconstrained data set with a large number of semantically overlapping classes, the obtained probability values are used as a new representation of the images and retrieval is performed on these new representations. In order to minimize the semantic gap, a relevance feedback approach that is based on the support vector data description is also incorporated. Experiments are performed on both Corel and TRECVID datasets and successful results are obtained.Item Open Access Semi-automatic video object segmentation(Bilkent University, 2000) Esen, ErsinContent-based iunetionalities form the core of the future multimedia applications. The new multimedia standard MPEG-4 provides a new form of interactivity with coded audio-visual data. The emerging standard MPEG-7 specifies a common description of various types of multimedia information to index the data for storage and retrieval. However, none of these standards specifies how to extract the content of the multimedia data. Video object segmentation addresses this task and tries to extract semantic objects from a scene. Two tyj)es of video object segmentation can be identified: unsupervised and supervised. In unsupervised méthods the user is not involved in any step of the process. In supervised methods the user is requested to supply additional information to increase the quality of the segmentation. The proposed weakly supervised still image segmentation asks the user to draw a scribble over what he defines as an object. These scribbles inititate the iterative method. .A.t each iteration the most similar regions are merged until the desired numljer of regions is reached. The proposed .segmentation method is inserted into the unsupervised COST211ter .A-ualysis Model (.A.M) for video object segmentation. The AM is modified to handh' the sujiervision. The new semi-automatic AM requires the user intei actimi for onl>· first frame of the video, then segmentation and object tracking is doin' automatically. The results indicate that the new semi-automatic AM constituK's a good tool for video oliject segmentation.Item Open Access Smart markers for watershed-based cell segmentation(Bilkent University, 2012) Koyuncu, Can FahrettinAutomated cell imaging systems facilitate fast and reliable analysis of biological events at the cellular level. In these systems, the first step is usually cell segmentation that greatly affects the success of the subsequent system steps. On the other hand, similar to other image segmentation problems, cell segmentation is an ill-posed problem that typically necessitates the use of domain specific knowledge to obtain successful segmentations even by human subjects. The approaches that can incorporate this knowledge into their segmentation algorithms have a potential to greatly improve the segmentation results. In this study, we propose a new approach for the effective segmentation of live cells from phase-contrast microscopy. This approach introduces a new set of “smart markers” for a marker-controlled watershed algorithm, for which the identification of its markers is critical. The proposed approach relies on using domain specific knowledge, in the form of visual characteristics of the cells, to define the markers. We evaluate our approach on a total of 1954 cells. The experimental results demonstrate that the proposed approach is quite effective in identifying better markers compared to its counterparts. This will in turn be effective in improving the segmentation performance of a marker-controlled watershed algorithm.