The large amounts of Synthetic Aperture Radar (SAR) data now being generated demand automatic tools for image interpretation. Where available, map data provides a valuable aid for visual interpretation and it should aid automatic interpretation. Automatic map based interpretation will be heavily dependent on methods for matching image and map features, both for defining the initial registration and for comparing image and map. This thesis investigates methods for carrying out this matching. Before beginning to develop image map matching methods, a full understanding of the nature of SAR data is first required. The general theory of SAR imaging, the effects of speckle and texture on image statistics, multi-look image statistics, and parameter estimation, are all discussed before addressing the main subject matter. Initially the feasibility of directly matching map features to SAR image features is investigated. Simulations based on a simple image model produce promising results. However, the results of matching features in real images are disappointing. This is due to the limitations of the image model on which matching is based. Possible extensions to include texture and correlation are considered to be computationally too expensive. Rather, it is concluded that pre-processing is needed to structure the image prior to matching. Structuring using edge detection and segmentation are investigated. Among operators for detecting edges in SAR an operator based on intensity ratios is identified as the most suitable. Its performance is fully analysed. Segmentation using an iterative edge detection/segment growing algorithm developed at the Royal Signals and Radar Establishment is investigated and various improvements are suggested. The output of segmentation is structured to a higher level than the output of edge detection. Thus the former is the more suitable candidate for map matching. Approaches to matching segmentations to map data are discussed.

This thesis is concerned with the development of an optimization based approach to solving labelling problems which involve the assignment of image entities into interpretation categories in computer vision. Attention is mainly focussed on the theoretical basis and computational aspect of continuous relaxation for solving a discrete labelling problem based on an optimization framework. First, a theoretical basis for continuous relaxation is presented which includes the formulation of a discrete labelling problem as a continuous minimization problem and an analysis of labelling unambiguity associated with continuous relaxation. The main advantage of the formulation over existing formulations is the embedding of relational measurements into the specification of a consistent labelling. The analysis provides a sufficient condition for a continuous labelling formulation to ensure that a consistent labelling is unambiguous. Second, a continuous relaxation labelling algorithm based on mean field theory is presented with the aim of approximating simulated annealing in a deterministic manner. The novelty of the algorithm lies in the utilization of mean field theory technique to avoid stochastic optimization for approximating the global optimum of a consistent labelling criterion. This is contrast to the conventional methods which find a local optimum near an initial estimate of labelling. A special three-frame discrete labelling problem of establishing trinocular stereo correspondence and a mixed labelling problem of interpreting image entities in terms of cylindrical objects and their locations are also addressed. For the former, two orientation based geometric constraints are suggested for matching lines among three viewpoints and a method is presented to find a consistent labelling using simulated annealing. For the latter, the image interpretation of 3D cylindrical objects and their 3D locations is achieved using three knowledge sources: edge map, region map and the ground plane constraint. The method differs from existing methods in that it exploits an integrated use of multiple image cues to simplify the interpretation task and improve the interpretation performance. Experimental results on both synthetic data and real images are provided to demonstrate the viability and the potential of the proposed methods throughout the thesis.

No / Background The role of radiographers with respect to image interpretation within clinical practice is well recognised. It is the expectation of the professional, regulatory and academic bodies that upon qualification, radiographers will possess image interpretation skills. Additionally, The College of Radiographers has asserted that its aspiration is for all radiographers to be able to provide an immediate written interpretation on skeletal trauma radiographs by 2010. This paper explores the readiness of radiography education programmes in the UK to deliver this expectation. Method A postal questionnaire was distributed to 25 Higher Education Institutions in the UK (including Northern Ireland) that provided pre-registration radiography education as identified from the Society & College of Radiographers register. Information was sought relating to the type of image interpretation education delivered at pre- and post-registration levels; the anatomical range of image interpretation education; and education delivery styles. Results A total of 19 responses (n=19/25; 76.0%) were received. Image interpretation education was included as part of all radiographer pre-registration programmes and offered at post-registration level at 12 academic centres (n=12/19; 63.2%). The anatomical areas and educational delivery methods varied across institutions. Conclusion Radiography education providers have embraced the need for image interpretation education within both pre- and post-registration radiography programmes. As a result, UK education programmes are able to meet the 2010 College of Radiographers aspiration.

Diss. Umeå : Umeå universitet, 2008.

This thesis describes a probabilistic approach to imagesegmentation and interpretation. The focus of the investigation is the development of a systematic way of combining color, brightness, texture and geometric features extracted from an image to arrive at a consistent interpretation for each pixel in the image. The contribution of this thesis is thus the presentation of a novel framework for the fusion of extracted image features producing a segmentation of an image into relevant regions. Further, a solution to the sub-pixel mixing problem is presented based on solving a probabilistic linear program. This work is specifically aimed at interpreting and digitizing multi-spectral aerial imagery of the Earth's surface. The features of interest for extraction are those of relevance to environmental management, monitoring and protection. The presented algorithms are suitable for use within a larger interpretive system. Some results are presented and contrasted with other techniques. The integration of these algorithms into a larger system is based firmly on a probabilistic methodology and the use of statistical decision theory to accomplish uncertain inference within the visual formalism of a graphical probability model.

This thesis describes a probabilistic approach to imagesegmentation and interpretation. The focus of the investigation is the development of a systematic way of combining color, brightness, texture and geometric features extracted from an image to arrive at a consistent interpretation for each pixel in the image. The contribution of this thesis is thus the presentation of a novel framework for the fusion of extracted image features producing a segmentation of an image into relevant regions. Further, a solution to the sub-pixel mixing problem is presented based on solving a probabilistic linear program. This work is specifically aimed at interpreting and digitizing multi-spectral aerial imagery of the Earth's surface. The features of interest for extraction are those of relevance to environmental management, monitoring and protection. The presented algorithms are suitable for use within a larger interpretive system. Some results are presented and contrasted with other techniques. The integration of these algorithms into a larger system is based firmly on a probabilistic methodology and the use of statistical decision theory to accomplish uncertain inference within the visual formalism of a graphical probability model.

Thesis (M.Eng.). / Written for the Dept. of Biomedical Engineering. Title from title page of PDF (viewed 2008/04/12). Includes bibliographical references.

Thesis (Ph. D.)--Cornell University, January, 2009. / Vita. Includes bibliographical references (leaves 143-155).

Assessment of image interpretation competency is commonly undertaken through review of a defined image test bank. Content of these image banks has been criticised for the high percentage of abnormal examinations which contrasts with lower reported incidences of abnormal radiographs in clinical practice. As a result, questions have been raised regarding the influence of prevalence bias on the accuracy of interpretive decision making. This article describes a new and novel approach to the design of musculoskeletal image test banks. Three manufactured image banks were compiled following a standard academic menu in keeping with previous studies. Three further image test banks were constructed to reflect local clinical workload within a single NHS Trust. Eighteen radiographers, blinded to the method of test bank composition, were randomly assigned 2 test banks to review (1 manufactured, 1 clinical workload). Comparison of interpretive accuracy was undertaken. Inter-rater agreement was moderate to good for all image banks (manufactured: range k = 0.45–0.68; clinical workload: k = 0.49–0.62). A significant difference in mean radiographer sensitivity was noted between test bank designs (manufactured 87.1%; clinical workload 78.5%; p = 0.040, 95% CI = 0.4–16.8; t = 2.223). Relative parity in radiographer specificity and overall accuracy was observed. This study confirms the findings of previous research that high abnormality prevalence image banks over-estimate the ability of observers to identify abnormalities. Assessment of interpretive competency using an image bank that reflects local clinical practice is a better approach to accurately establish interpretive competency and the learning development needs of individual practitioners.

This thesis explores the use of invariant features for learning sprites from image sequences, and for recognising object categories in images. A popular framework for the interpretation of image sequences is the layers or sprite model of e.g. Wang and Adelson (1994), Irani et al. (1994). Jojic and Frey (2001) provide a generative probabilistic model framework for this task, but their algorithm is slow as it needs to search over discretised transformations (e.g. translations, or affines) for each layer. We show that by using invariant features (e.g. Lowe’s SIFT features) and clustering their motions we can reduce or eliminate the search and thus learn the sprites much faster. The algorithm is demonstrated on example image sequences. We introduce the Generative Template of Features (GTF), a parts-based model for visual object category detection. The GTF consists of a number of parts, and for each part there is a corresponding spatial location distribution and a distribution over ‘visual words’ (clusters of invariant features). We evaluate the performance of the GTF model for object localisation as compared to other techniques, and show that such a relatively simple model can give state-of- the-art performance. We also discuss the connection of the GTF to Hough-transform-like methods for object localisation.