Pattern-based segmentation of digital documents: model and implementation

This thesis proposes a new document model, according to which any document can be segmented in some independent components and transformed in a pattern-based projection, that only uses a very small set of objects and composition rules. The point is that such a normalized document expresses the same fundamental information of the original one, in a simple, clear and unambiguous way. The central part of my work consists of discussing that model, investigating how a digital document can be segmented, and how a segmented version can be used to implement advanced tools of conversion. I present seven patterns which are versatile enough to capture the most relevant documents’ structures, and whose minimality and rigour make that implementation possible. The abstract model is then instantiated into an actual markup language, called IML. IML is a general and extensible language, which basically adopts an XHTML syntax, able to capture a posteriori the only content of a digital document. It is compared with other languages and proposals, in order to clarify its role and objectives. Finally, I present some systems built upon these ideas. These applications are evaluated in terms of users’ advantages, workflow improvements and impact over the overall quality of the output. In particular, they cover heterogeneous content management processes: from web editing to collaboration (IsaWiki and WikiFactory), from e-learning (IsaLearning) to professional printing (IsaPress).

Atlas-Based Segmentation of Brain Tumor Images Using a Markov Random Field-Based Tumor Growth Model and Non-Rigid Registration

We propose a new and clinically oriented approach to perform atlas-based segmentation of brain tumor images. A mesh-free method is used to model tumor-induced soft tissue deformations in a healthy brain atlas image with subsequent registration of the modified atlas to a pathologic patient image. The atlas is seeded with a tumor position prior and tumor growth simulating the tumor mass effect is performed with the aim of improving the registration accuracy in case of patients with space-occupying lesions. We perform tests on 2D axial slices of five different patient data sets and show that the approach gives good results for the segmentation of white matter, grey matter, cerebrospinal fluid and the tumor.

Statistical model-based segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs.

PURPOSE    Segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs is required to create a three-dimensional model of the hip joint for use in planning and treatment. However, manually extracting the femoral contour is tedious and prone to subjective bias, while automatic segmentation must accommodate poor image quality, anatomical structure overlap, and femur deformity. A new method was developed for femur segmentation in AP pelvic radiographs. METHODS    Using manual annotations on 100 AP pelvic radiographs, a statistical shape model (SSM) and a statistical appearance model (SAM) of the femur contour were constructed. The SSM and SAM were used to segment new AP pelvic radiographs with a three-stage approach. At initialization, the mean SSM model is coarsely registered to the femur in the AP radiograph through a scaled rigid registration. Mahalanobis distance defined on the SAM is employed as the search criteria for each annotated suggested landmark location. Dynamic programming was used to eliminate ambiguities. After all landmarks are assigned, a regularized non-rigid registration method deforms the current mean shape of SSM to produce a new segmentation of proximal femur. The second and third stages are iteratively executed to convergence. RESULTS    A set of 100 clinical AP pelvic radiographs (not used for training) were evaluated. The mean segmentation error was [Formula: see text], requiring [Formula: see text] s per case when implemented with Matlab. The influence of the initialization on segmentation results was tested by six clinicians, demonstrating no significance difference. CONCLUSIONS    A fast, robust and accurate method for femur segmentation in digital AP pelvic radiographs was developed by combining SSM and SAM with dynamic programming. This method can be extended to segmentation of other bony structures such as the pelvis.

True four-dimensional analysis of thoracic aortic displacement and distension using model-based segmentation of computed tomography angiography.

Previous analyses of aortic displacement and distension using computed tomography angiography (CTA) were performed on double-oblique multi-planar reformations and did not consider through-plane motion. The aim of this study was to overcome this limitation by using a novel computational approach for the assessment of thoracic aortic displacement and distension in their true four-dimensional extent. Vessel segmentation with landmark tracking was executed on CTA of 24 patients without evidence of aortic disease. Distension magnitudes and maximum displacement vectors (MDV) including their direction were analyzed at 5 aortic locations: left coronary artery (COR), mid-ascending aorta (ASC), brachiocephalic trunk (BCT), left subclavian artery (LSA), descending aorta (DES). Distension was highest for COR (2.3 ± 1.2 mm) and BCT (1.7 ± 1.1 mm) compared with ASC, LSA, and DES (p < 0.005). MDV decreased from COR to LSA (p < 0.005) and was highest for COR (6.2 ± 2.0 mm) and ASC (3.8 ± 1.9 mm). Displacement was directed towards left and anterior at COR and ASC. Craniocaudal displacement at COR and ASC was 1.3 ± 0.8 and 0.3 ± 0.3 mm. At BCT, LSA, and DES no predominant displacement direction was observable. Vessel displacement and wall distension are highest in the ascending aorta, and ascending aortic displacement is primarily directed towards left and anterior. Craniocaudal displacement remains low even close to the left cardiac ventricle.

Atlas-based Segmentation of Tumor-bearing Brain Images

In diagnostic neuroradiology as well as in radiation oncology and neurosurgery, there is an increasing demand for accurate segmentation of tumor-bearing brain images. Atlas-based segmentation is an appealing automatic technique thanks to its robustness and versatility. However, atlas-based segmentation of tumor-bearing brain images is challenging due to the confounding effects of the tumor in the patient image. In this article, we provide a brief background on brain tumor imaging and introduce the clinical perspective, before we categorize and review the state of the art in the current literature on atlas-based segmentation for tumor-bearing brain images. We also present selected methods and results from our own research in more detail. Finally, we conclude with a short summary and look at new developments in the field, including requirements for future routine clinical use.

Probabilistic Atlas Based Segmentation Using Affine Moment Descriptors and Graph-Cuts

We show a procedure for constructing a probabilistic atlas based on affine moment descriptors. It uses a normalization procedure over the labeled atlas. The proposed linear registration is defined by closed-form expressions involving only geometric moments. This procedure applies both to atlas construction as atlas-based segmentation. We model the likelihood term for each voxel and each label using parametric or nonparametric distributions and the prior term is determined by applying the vote-rule. The probabilistic atlas is built with the variability of our linear registration. We have two segmentation strategy: a) it applies the proposed affine registration to bring the target image into the coordinate frame of the atlas or b) the probabilistic atlas is non-rigidly aligning with the target image, where the probabilistic atlas is previously aligned to the target image with our affine registration. Finally, we adopt a graph cut - Bayesian framework for implementing the atlas-based segmentation.

Psychophysical evidence for fast region-based segmentation processes in motion and color.

Theories of image segmentation suggest that the human visual system may use two distinct processes to segregate figure from background: a local process that uses local feature contrasts to mark borders of coherent regions and a global process that groups similar features over a larger spatial scale. We performed psychophysical experiments to determine whether and to what extent the global similarity process contributes to image segmentation by motion and color. Our results show that for color, as well as for motion, segmentation occurs first by an integrative process on a coarse spatial scale, demonstrating that for both modalities the global process is faster than one based on local feature contrasts. Segmentation by motion builds up over time, whereas segmentation by color does not, indicating a fundamental difference between the modalities. Our data suggest that segmentation by motion proceeds first via a cooperative linking over space of local motion signals, generating almost immediate perceptual coherence even of physically incoherent signals. This global segmentation process occurs faster than the detection of absolute motion, providing further evidence for the existence of two motion processes with distinct dynamic properties.

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Response-based segmentation using Finite Mixture Partial Least Squares: theoretical foundations and an application to American Customer Satisfaction Index Data

When applying multivariate analysis techniques in information systems and social science disciplines, such as management information systems (MIS) and marketing, the assumption that the empirical data originate from a single homogeneous population is often unrealistic. When applying a causal modeling approach, such as partial least squares (PLS) path modeling, segmentation is a key issue in coping with the problem of heterogeneity in estimated cause-and-effect relationships. This chapter presents a new PLS path modeling approach which classifies units on the basis of the heterogeneity of the estimates in the inner model. If unobserved heterogeneity significantly affects the estimated path model relationships on the aggregate data level, the methodology will allow homogenous groups of observations to be created that exhibit distinctive path model estimates. The approach will, thus, provide differentiated analytical outcomes that permit more precise interpretations of each segment formed. An application on a large data set in an example of the American customer satisfaction index (ACSI) substantiates the methodology’s effectiveness in evaluating PLS path modeling results.

The mosaic test:benchmarking colour-based image retrieval systems using image mosaics

Evaluation and benchmarking in content-based image retrieval has always been a somewhat neglected research area, making it difficult to judge the efficacy of many presented approaches. In this paper we investigate the issue of benchmarking for colour-based image retrieval systems, which enable users to retrieve images from a database based on lowlevel colour content alone. We argue that current image retrieval evaluation methods are not suited to benchmarking colour-based image retrieval systems, due in main to not allowing users to reflect upon the suitability of retrieved images within the context of a creative project and their reliance on highly subjective ground-truths. As a solution to these issues, the research presented here introduces the Mosaic Test for evaluating colour-based image retrieval systems, in which test-users are asked to create an image mosaic of a predetermined target image, using the colour-based image retrieval system that is being evaluated. We report on our findings from a user study which suggests that the Mosaic Test overcomes the major drawbacks associated with existing image retrieval evaluation methods, by enabling users to reflect upon image selections and automatically measuring image relevance in a way that correlates with the perception of many human assessors. We therefore propose that the Mosaic Test be adopted as a standardised benchmark for evaluating and comparing colour-based image retrieval systems.

Exploring the effectiveness of similarity-based visualisations for colour-based image retrieval

In April 2009, Google Images added a filter for narrowing search results by colour. Several other systems for searching image databases by colour were also released around this time. These colour-based image retrieval systems enable users to search image databases either by selecting colours from a graphical palette (i.e., query-by-colour), by drawing a representation of the colour layout sought (i.e., query-by-sketch), or both. It was comments left by readers of online articles describing these colour-based image retrieval systems that provided us with the inspiration for this research. We were surprised to learn that the underlying query-based technology used in colour-based image retrieval systems today remains remarkably similar to that of systems developed nearly two decades ago. Discovering this ageing retrieval approach, as well as uncovering a large user demographic requiring image search by colour, made us eager to research more effective approaches for colour-based image retrieval. In this thesis, we detail two user studies designed to compare the effectiveness of systems adopting similarity-based visualisations, query-based approaches, or a combination of both, for colour-based image retrieval. In contrast to query-based approaches, similarity-based visualisations display and arrange database images so that images with similar content are located closer together on screen than images with dissimilar content. This removes the need for queries, as users can instead visually explore the database using interactive navigation tools to retrieve images from the database. As we found existing evaluation approaches to be unreliable, we describe how we assessed and compared systems adopting similarity-based visualisations, query-based approaches, or both, meaningfully and systematically using our Mosaic Test - a user-based evaluation approach in which evaluation study participants complete an image mosaic of a predetermined target image using the colour-based image retrieval system under evaluation.

The mosaic test:measuring the effectiveness of colour-based image retrieval

A variety of content-based image retrieval systems exist which enable users to perform image retrieval based on colour content - i.e., colour-based image retrieval. For the production of media for use in television and film, colour-based image retrieval is useful for retrieving specifically coloured animations, graphics or videos from large databases (by comparing user queries to the colour content of extracted key frames). It is also useful to graphic artists creating realistic computer-generated imagery (CGI). Unfortunately, current methods for evaluating colour-based image retrieval systems have 2 major drawbacks. Firstly, the relevance of images retrieved during the task cannot be measured reliably. Secondly, existing methods do not account for the creative design activity known as reflection-in-action. Consequently, the development and application of novel and potentially more effective colour-based image retrieval approaches, better supporting the large number of users creating media for use in television and film productions, is not possible as their efficacy cannot be reliably measured and compared to existing technologies. As a solution to the problem, this paper introduces the Mosaic Test. The Mosaic Test is a user-based evaluation approach in which participants complete an image mosaic of a predetermined target image, using the colour-based image retrieval system that is being evaluated. In this paper, we introduce the Mosaic Test and report on a user evaluation. The findings of the study reveal that the Mosaic Test overcomes the 2 major drawbacks associated with existing evaluation methods and does not require expert participants. © 2012 Springer Science+Business Media, LLC.

Extruded colour-based plastic film for the measurement of dissolved CO2

Dissolved CO2 measurements are usually made using a Severinghaus electrode, which is bulky and can suffer from electrical interference. In contrast, optical sensors for gaseous CO2, whilst not suffering these problems, are mainly used for making gaseous (not dissolved) CO2 measurements, due to dye leaching and protonation, especially at high ionic strengths (>0.01 M) and acidity (<pH 4). This is usually prevented by coating the sensor with a gas-permeable, but ion-impermeable, membrane (GPM). Herein, we introduce a highly sensitive, colourimetric-based, plastic film sensor for the measurement of both gaseous and dissolved CO2, in which a pH-sensitive dye, thymol blue (TB) is coated onto particles of hydrophilic silica to create a CO2-sensitive, TB-based pigment, which is then extruded into low density polyethylene (LDPE) to create a GPM-free, i.e. naked, TB plastic sensor film for gaseous and dissolved CO2 measurements. When used for making dissolved CO2 measurements, the hydrophobic nature of the LDPE renders the film: (i) indifferent to ionic strength, (ii) highly resistant to acid attack and (iii) stable when stored under ambient (dark) conditions for >8 months, with no loss of colour or function. Here, the performance of the TB plastic film is primarily assessed as a dissolved CO2 sensor in highly saline (3.5 wt%) water. The TB film is blue in the absence of CO2 and yellow in its presence, exhibiting 50% transition in its colour at ca. 0.18% CO2. This new type of CO2 sensor has great potential in the monitoring of CO2 levels in the hydrosphere, as well as elsewhere, e.g. food packaging and possibly patient monitoring.

Effects of camera aperture correction on keying and compositing of broadcast video

This contribution discusses the effects of camera aperture correction in broadcast video on colour-based keying. The aperture correction is used to ’sharpen’ an image and is one element that distinguishes the ’TV-look’ from ’film-look’. ’If a very high level of sharpening is applied, as is the case in many TV productions then this significantly shifts the colours around object boundaries with hight contrast. This paper discusses these effects and their impact on keying and describes a simple low-pass filter to compensate for them. Tests with colour-based segmentation algorithms show that the proposed compensation is an effective way of decreasing the keying artefacts on object boundaries.