New Distance Transforms for Gray Level Image Compression

This thesis deals with distance transforms which are a fundamental issue in image processing and computer vision. In this thesis, two new distance transforms for gray level images are presented. As a new application for distance transforms, they are applied to gray level image compression. The new distance transforms are both new extensions of the well known distance transform algorithm developed by Rosenfeld, Pfaltz and Lay. With some modification their algorithm which calculates a distance transform on binary images with a chosen kernel has been made to calculate a chessboard like distance transform with integer numbers (DTOCS) and a real value distance transform (EDTOCS) on gray level images. Both distance transforms, the DTOCS and EDTOCS, require only two passes over the graylevel image and are extremely simple to implement. Only two image buffers are needed: The original gray level image and the binary image which defines the region(s) of calculation. No other image buffers are needed even if more than one iteration round is performed. For large neighborhoods and complicated images the two pass distance algorithm has to be applied to the image more than once, typically 3 10 times. Different types of kernels can be adopted. It is important to notice that no other existing transform calculates the same kind of distance map as the DTOCS. All the other gray weighted distance function, GRAYMAT etc. algorithms find the minimum path joining two points by the smallest sum of gray levels or weighting the distance values directly by the gray levels in some manner. The DTOCS does not weight them that way. The DTOCS gives a weighted version of the chessboard distance map. The weights are not constant, but gray value differences of the original image. The difference between the DTOCS map and other distance transforms for gray level images is shown. The difference between the DTOCS and EDTOCS is that the EDTOCS calculates these gray level differences in a different way. It propagates local Euclidean distances inside a kernel. Analytical derivations of some results concerning the DTOCS and the EDTOCS are presented. Commonly distance transforms are used for feature extraction in pattern recognition and learning. Their use in image compression is very rare. This thesis introduces a new application area for distance transforms. Three new image compression algorithms based on the DTOCS and one based on the EDTOCS are presented. Control points, i.e. points that are considered fundamental for the reconstruction of the image, are selected from the gray level image using the DTOCS and the EDTOCS. The first group of methods select the maximas of the distance image to new control points and the second group of methods compare the DTOCS distance to binary image chessboard distance. The effect of applying threshold masks of different sizes along the threshold boundaries is studied. The time complexity of the compression algorithms is analyzed both analytically and experimentally. It is shown that the time complexity of the algorithms is independent of the number of control points, i.e. the compression ratio. Also a new morphological image decompression scheme is presented, the 8 kernels' method. Several decompressed images are presented. The best results are obtained using the Delaunay triangulation. The obtained image quality equals that of the DCT images with a 4 x 4

Three-Dimensional (3D) Microarchitecture Correlations with 2D Projection Image Gray-Level Variations Assessed by Trabecular Bone Score Using High-Resolution Computed Tomographic Acquisitions: Effects of Resolution and Noise.

The aim of the present study is to determine the level of correlation between the 3-dimensional (3D) characteristics of trabecular bone microarchitecture, as evaluated using microcomputed tomography (μCT) reconstruction, and trabecular bone score (TBS), as evaluated using 2D projection images directly derived from 3D μCT reconstruction (TBSμCT). Moreover, we have evaluated the effects of image degradation (resolution and noise) and X-ray energy of projection on these correlations. Thirty human cadaveric vertebrae were acquired on a microscanner at an isotropic resolution of 93μm. The 3D microarchitecture parameters were obtained using MicroView (GE Healthcare, Wauwatosa, MI). The 2D projections of these 3D models were generated using the Beer-Lambert law at different X-ray energies. Degradation of image resolution was simulated (from 93 to 1488μm). Relationships between 3D microarchitecture parameters and TBSμCT at different resolutions were evaluated using linear regression analysis. Significant correlations were observed between TBSμCT and 3D microarchitecture parameters, regardless of the resolution. Correlations were detected that were strongly to intermediately positive for connectivity density (0.711≤r(2)≤0.752) and trabecular number (0.584≤r(2)≤0.648) and negative for trabecular space (-0.407 ≤r(2)≤-0.491), up to a pixel size of 1023μm. In addition, TBSμCT values were strongly correlated between each other (0.77≤r(2)≤0.96). Study results show that the correlations between TBSμCT at 93μm and 3D microarchitecture parameters are weakly impacted by the degradation of image resolution and the presence of noise.

Distance Transforms on Gray-Level Surfaces

This thesis studies gray-level distance transforms, particularly the Distance Transform on Curved Space (DTOCS). The transform is produced by calculating distances on a gray-level surface. The DTOCS is improved by definingmore accurate local distances, and developing a faster transformation algorithm. The Optimal DTOCS enhances the locally Euclidean Weighted DTOCS (WDTOCS) with local distance coefficients, which minimize the maximum error from the Euclideandistance in the image plane, and produce more accurate global distance values.Convergence properties of the traditional mask operation, or sequential localtransformation, and the ordered propagation approach are analyzed, and compared to the new efficient priority pixel queue algorithm. The Route DTOCS algorithmdeveloped in this work can be used to find and visualize shortest routes between two points, or two point sets, along a varying height surface. In a digital image, there can be several paths sharing the same minimal length, and the Route DTOCS visualizes them all. A single optimal path can be extracted from the route set using a simple backtracking algorithm. A new extension of the priority pixel queue algorithm produces the nearest neighbor transform, or Voronoi or Dirichlet tessellation, simultaneously with the distance map. The transformation divides the image into regions so that each pixel belongs to the region surrounding the reference point, which is nearest according to the distance definition used. Applications and application ideas for the DTOCS and its extensions are presented, including obstacle avoidance, image compression and surface roughness evaluation.

An entropy-based approach to automatic image segmentation of satellite images

An entropy-based image segmentation approach is introduced and applied to color images obtained from Google Earth. Segmentation refers to the process of partitioning a digital image in order to locate different objects and regions of interest. The application to satellite images paves the way to automated monitoring of ecological catastrophes, urban growth, agricultural activity, maritime pollution, climate changing and general surveillance. Regions representing aquatic, rural and urban areas are identified and the accuracy of the proposed segmentation methodology is evaluated. The comparison with gray level images revealed that the color information is fundamental to obtain an accurate segmentation. (C) 2010 Elsevier B.V. All rights reserved.

Human gait recognition using extraction and fusion of global motion features

This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. This work proposes to recover these different kinds of information to interpret the global motion of the human body based on four different segmented image models, using a fusion model to improve classification. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette-Edge-Binary model (SEW) captures motion based on edge information and the Silhouette Skeleton Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.

Kohinan poisto spektrikuvista epälineaaristen suodattimien avulla

Tietokoneiden vuosi vuodelta kasvanut prosessointikyky mahdollistaa spektrikuvien hyö- dyntämisen harmaasävy- ja RGB-värikuvien sijaan yhä useampien ongelmien ratkaisemi- sessa. Valitettavasti häiriöiden suodatuksen tutkimus on jäänyt jälkeen tästä kehityksestä. Useimmat menetelmät on testattu vain harmaasävy- tai RGB-värikuvien yhteydessä, mut- ta niiden toimivuutta ei ole testattu spektrikuvien suhteen. Tässä diplomityössä tutkitaan erilaisia menetelmiä bittivirheiden poistamisessa spektrikuvista. Uutena menetelmänä työssä käytetään kuutiomediaanisuodatinta ja monivaiheista kuutio- mediaanisuodatinta. Muita tutkittuja menetelmiä olivat vektorimediaanisuodatus, moni- vaiheinen vektorimediaanisuodatus, sekä rajattu keskiarvosuodatus. Kuutiosuodattimilla pyrittiin hyödyntämään spektrikuvien kaistojen välillä olevaa korrelaatiota ja niillä pääs- tiinkin kokonaisuuden kannalta parhaisiin tuloksiin. Kaikkien suodattimien toimintaa tutkittiin kahdella eri 224 komponenttisella spektriku- valla lisäämällä kuviin satunnaisia bittivirheitä.

Neural Network based studies on Spectroscopic Analysis and Image Processing

International School of Photonics, Cochin University of Science and Technology

A Study of Morphological Operators with Applications

The present work deals with the A study of morphological opertors with applications. Morphology is now a.necessary tool for engineers involved with imaging applications. Morphological operations have been viewed as filters the properties of which have been well studied (Heijmans, 1994). Another well-known class of non-linear filters is the class of rank order filters (Pitas and Venetsanopoulos, 1990). Soft morphological filters are a combination of morphological and weighted rank order filters (Koskinen, et al., 1991, Kuosmanen and Astola, 1995). They have been introduced to improve the behaviour of traditional morphological filters in noisy environments. The idea was to slightly relax the typical morphological definitions in such a way that a degree of robustness is achieved, while most of the desirable properties of typical morphological operations are maintained. Soft morphological filters are less sensitive to additive noise and to small variations in object shape than typical morphological filters. They can remove positive and negative impulse noise, preserving at the same time small details in images. Currently, Mathematical Morphology allows processing images to enhance fuzzy areas, segment objects, detect edges and analyze structures. The techniques developed for binary images are a major step forward in the application of this theory to gray level images. One of these techniques is based on fuzzy logic and on the theory of fuzzy sets.Fuzzy sets have proved to be strongly advantageous when representing in accuracies, not only regarding the spatial localization of objects in an image but also the membership of a certain pixel to a given class. Such inaccuracies are inherent to real images either because of the presence of indefinite limits between the structures or objects to be segmented within the image due to noisy acquisitions or directly because they are inherent to the image formation methods.

Limiarização contextual automática de imagens coloridas: aplicação na extração de sementes de rodovia

In this paper is a totally automatic strategy proposed to reduce the complexity of patterns ( vegetation, building, soils etc.) that interact with the object 'road' in color images, thus reducing the difficulty of the automatic extraction of this object. The proposed methodology consists of three sequential steps. In the first step the punctual operator is applied for artificiality index computation known as NandA ( Natural and Artificial). The result is an image whose the intensity attribute is the NandA response. The second step consists in automatically thresholding the image obtained in the previous step, resulting in a binary image. This image usually allows the separation between artificial and natural objects. The third step consists in applying a preexisting road seed extraction methodology to the previous generated binary image. Several experiments carried out with real images made the verification of the potential of the proposed methodology possible. The comparison of the obtained result to others obtained by a similar methodology for road seed extraction from gray level images, showed that the main benefit was the drastic reduction of the computational effort.

Detection of matchings in a sequence of underwater images through texture analysis

This paper presents an approach to ameliorate the reliability of the correspondence points relating two consecutive images of a sequence. The images are especially difficult to handle, since they have been acquired by a camera looking at the sea floor while carried by an underwater robot. Underwater images are usually difficult to process due to light absorption, changing image radiance and lack of well-defined features. A new approach based on gray-level region matching and selective texture analysis significantly improves the matching reliability

A Quantitative method for the characterization of lytic metastases of the bone from radiographic images

The aim of our study was to assess the diagnostic usefulness of the gray level parameters to distinguish osteolytic lesions using radiological images. Materials and Methods: A retrospective study was carried out. A total of 76 skeletal radiographs of osteolytic metastases and 67 radiographs of multiple myeloma were used. The cases were classified into nonflat (MM1 and OL1) and flat bones (MM2 and OL2). These radiological images were analyzed by using a computerized method. The parameters calculated were mean, standard deviation, and coefficient of variation (MGL, SDGL, and CVGL) based on gray level histogram analysis of a region-of-interest.Diagnostic utility was quantified bymeasurement of parameters on osteolyticmetastases andmultiplemyeloma, yielding quantification of area under the receiver operating characteristic (ROC) curve (AUC). Results: Flat bone groups (MM2 and OL2) showed significant differences in mean values of MGL ( = 0.048) and SDGL ( = 0.003). Their corresponding values of AUC were 0.758 for MGL and 0.883 for SDGL in flat bones. In nonflat bones these gray level parameters do not show diagnostic ability. Conclusion: The gray level parametersMGL and SDGL show a good discriminatory diagnostic ability to distinguish between multiple myeloma and lytic metastases in flat bones.

Texture analysis of computed tomography images of acute ischemic stroke patients

Computed tomography (CT) images are routinely used to assess ischemic brain stroke in the acute phase. They can provide important clues about whether to treat the patient by thrombolysis with tissue plasminogen activator. However, in the acute phase, the lesions may be difficult to detect in the images using standard visual analysis. The objective of the present study was to determine if texture analysis techniques applied to CT images of stroke patients could differentiate between normal tissue and affected areas that usually go unperceived under visual analysis. We performed a pilot study in which texture analysis, based on the gray level co-occurrence matrix, was applied to the CT brain images of 5 patients and of 5 control subjects and the results were compared by discriminant analysis. Thirteen regions of interest, regarding areas that may be potentially affected by ischemic stroke, were selected for calculation of texture parameters. All regions of interest for all subjects were classified as lesional or non-lesional tissue by an expert neuroradiologist. Visual assessment of the discriminant analysis graphs showed differences in the values of texture parameters between patients and controls, and also between texture parameters for lesional and non-lesional tissue of the patients. This suggests that texture analysis can indeed be a useful tool to help neurologists in the early assessment of ischemic stroke and quantification of the extent of the affected areas.

Fiabilité et changement minimal détectable de mesures obtenues à partir d'images enregistrées par ultrasonographie afin de caractériser l'intégrité du tendon d'Achille

Problématique : La quantification de l’intégrité du tendon d’Achille (TA) représente un défi en réadaptation. L’adoption de mesures quantitatives du TA, extraites à partir d’une image ultrasonographique (QUS), pourrait remédier à cette lacune. Objectifs : 1) Évaluer la fiabilité test-retest et la précision de mesures QUS du TA; 2) Déterminer le meilleur protocole de collecte de mesures QUS à employer en pratique clinique. Méthodologie : Un total de 23 TAs présentant des symptômes d’une tendinopathie achilléenne et 63 TAs asymptomatiques ont été évalués. Pour chaque TA, 8 images ont été enregistrées (2 visites * 2 évaluatrices * 2 images). Différents types de mesures QUS ont été prises : géométriques (épaisseur, largeur, aire), dérivées d’un histogramme des niveaux de gris et dérivées d’une matrice de co-occurrence. Une étude de généralisabilité a quantifié la fiabilité et la précision de chaque mesure QUS et une étude de décision a fait ressortir les meilleurs protocoles de prise de mesures. Résultats : Les mesures géométriques ont démontré une excellente fiabilité et précision. Les mesures dérivées de l’histogramme des niveaux de gris ont démontré une fiabilité et précision médiocres. Les mesures dérivées d’une matrice de co-occurrence ont démontré une fiabilité modérée à excellente et une précision variable. En pratique clinique, il est recommandé de moyenner les résultats de trois images collectées par un évaluateur lors d’une visite. Conclusion : L’utilisation des mesures QUS géométriques permet de quantifier l’intégrité du TA (clinique et recherche). Davantage d’études sur les mesures QUS dérivées d’une matrice de co-occurrence s’avèrent nécessaires.