The resolution of the inverse problem for iterated function systems (IFS) is a problem that has remained open, currently there is no general solution that requires no human interaction and provides optimal results. Here we present a novel approach to the resolution of the general inverse problem for IFS using segmentation of target images in conjuction with an Evolutionary Algorithm that is a Genetic Programming-Evolutionary Strategies hybrid.

3D models of millions of triangles invariably repeatedly use the same 12-byte unit normals. Several bit-wise compression algorithms exist for efficient storage and progressive transmission and visualization of normal vectors. However such methods often incur a reconstruction time penalty which, in the absence of dedicated hardware acceleration, make real-time rendering with such compression/reconstruction methods prohibitive. In particular, several methods use a subdivided octahedron to create look-up normals, where the bit length of normal indices varies according to the number of subdivisions used. Not much attention has been given to the error in the normals using such schemes. We show that different Platonic solids create different amounts of normals for each subdivision or bit length in bit-wise compression terms, with different distributions and associated errors. In particular we show that subdividing the icosahedron gives a smaller maximum and mean error than its counterparts Platonic solids. This result has led us to create an alternative to bit-wise compression of normal ids for real-time rendering, where we use a x5 subdivided icosahedron to create 2.5 times more normals than a x5 subdivided octahedron, with less error, and exploit the advantages of absolute normal indices that do not require reconstruction at run-time, whilst still having memory savings of over 83% when using 2-byte indices.We present results using 2-byte indices for a target max error of 1.3° degrees and 4-byte for a max error of <0.1°. We present two hierarchical encoding methods, a fast method which allows one to dynamically encode large sets of modified triangles, useful for task, and a slower but more accurate method that caters for symmetry present in the subdivision solid being used. Different levels of a database allow for different cartoon like shading effects. The advantages of these databases are that they can be re-used for any object, and have studied bounds on the maximum errors of normals for yet to be known geometry such as new objects to be added to a scene. This error bound is also independent of the size and normal distribution of the object that we wish to add. In order to visualize the colour coding distribution of the errors in the normals of large models a simple 1-byte color encoding algorithm was developed.

Predication of a pedestrian’s 3D pose using movie sequences is not straightforward because of the human body’s articulation and the complexity of biped locomotion. In this paper we show how temporal coherence can be employed to help the reconstruction of gait pose using corresponding silhouette moments of a video sequence from a monocular view. Virtual avatars were used to train the model for inferring the pose. The system was tested on a walking real person’s silhouettes and evaluated using different avatars that were not in the training set. 1

MOTIVATION: Converting the vast quantity of free-format text found in journals into a concise, structured format makes the researcher's quest for information easier. Recently, several information extraction systems have been developed that attempt to simplify the retrieval and analysis of biological and medical data. Most of this work has used the abstract alone, owing to the convenience of access and the quality of data. Abstracts are generally available through central collections with easy direct access (e.g. PubMed). The full-text papers contain more information, but are distributed across many locations (e.g. publishers' web sites, journal web sites and local repositories), making access more difficult. In this paper, we present BioRAT, a new information extraction (IE) tool, specifically designed to perform biomedical IE, and which is able to locate and analyse both abstracts and full-length papers. BioRAT is a Biological Research Assistant for Text mining, and incorporates a document search ability with domain-specific IE. RESULTS: We show first, that BioRAT performs as well as existing systems, when applied to abstracts; and second, that significantly more information is available to BioRAT through the full-length papers than via the abstracts alone. Typically, less than half of the available information is extracted from the abstract, with the majority coming from the body of each paper. Overall, BioRAT recalled 20.31% of the target facts from the abstracts with 55.07% precision, and achieved 43.6% recall with 51.25% precision on full-length papers.

UNLABELLED: Dynamically disordered regions appear to be relatively abundant in eukaryotic proteomes. The DISOPRED server allows users to submit a protein sequence, and returns a probability estimate of each residue in the sequence being disordered. The results are sent in both plain text and graphical formats, and the server can also supply predictions of secondary structure to provide further structural information. AVAILABILITY: The server can be accessed by non-commercial users at http://bioinf.cs.ucl.ac.uk/disopred/

Dense surface models can be used to register unseen surfaces, using an algorithm which is a hybrid of iterative closest-point (ICP) and active shape model (ASM) fitting. In this paper we give details of this procedure and show how it can be improved by sequentially extending the transform group over which it operates. We also evaluate it for robustness to the position of the target and to shape variation across a set of unseen examples. The fit was successful on all 21 examples in our test set, with an average RMS error of 3.0mm. An initial comparison of 3 people landmarking the same scans suggests that this is within the normal landmark reproducibility range for 3D face scans. 1

In silico screening of chemical libraries or virtual chemicals may reduce drug discovery and medicine optimisation lead times and increase the probability of success by directing search through chemical space. About a dozen intelligent pharmaceutical QSAR modelling techniques were used to predict IC50 concentration (three classes) of drug interaction with a cell wall enzyme (P450 CYC2D6). Genetic programming gave comprehensible cheminformatics models which generalised best. This was shown by a blind test on Glaxo Welcome molecules of machine learning knowledge nuggets mined from SmithKline Beecham compounds. Performance on similar chemicals (interpolation) and diverse chemicals (extrapolation) suggest generalisation is more difficult than avoiding over fitting. Two GP approaches, classification via regression using a multiobjective fitness measure and a direct winner takes all (WTA) or one versus all (OVA) classification, are described. Predictive rules were compressed by separate follow up GP runs seeded with the best program.

MOTIVATION: A new method that uses support vector machines (SVMs) to predict protein secondary structure is described and evaluated. The study is designed to develop a reliable prediction method using an alternative technique and to investigate the applicability of SVMs to this type of bioinformatics problem. METHODS: Binary SVMs are trained to discriminate between two structural classes. The binary classifiers are combined in several ways to predict multi-class secondary structure. RESULTS: The average three-state prediction accuracy per protein (Q(3)) is estimated by cross-validation to be 77.07 +/- 0.26% with a segment overlap (Sov) score of 73.32 +/- 0.39%. The SVM performs similarly to the 'state-of-the-art' PSIPRED prediction method on a non-homologous test set of 121 proteins despite being trained on substantially fewer examples. A simple consensus of the SVM, PSIPRED and PROFsec achieves significantly higher prediction accuracy than the individual methods.

In this paper, we show how a dense surface point distribution model of the human face can be computed and demonstrate the usefulness of the high-dimensional shape-space for expressing the shape changes associated with growth and aging. We show how average growth trajectories for the human face can be computed in the absence of longitudinal data by using kernel smoothing across a population. A training set of three-dimensional surface scans of 199 male and 201 female subjects of between 0 and 50 years of age is used to build the model.

Flexible Shape Models (FSMs), have been widely used for modelling shape variations of deformable objects [4]. A major limitation of this approach is that it assumes a near fronto-parallel view. Recently, representing images as a Linear Combination of Views (LCV) has become a popular approach for modelling 3D pose variations in a 2D image context (e.g. [7]). This technique, however, only works for images of rigid objects. Apart from explicit 3D model approaches, most previous models that can cope with both shape and pose variations have either used a relationship between pose and shape parameters (e.g. [3]) or modelled the pose variations as variations in shape (e.g. FSMs [4]). However, variations of an object’s pose and shape are extrinsic and intrinsic degrees of freedom, respectively. The two should, therefore, not be confounded since they are independent and, in general, not correlated. We have, therefore, developed an integrated approach that uses a coupled-view FSM [3] to represent the shape of the entire face as seen from two different view-points, and uses the LCV technique to deal with pose variations. A preliminary comparison is made to the conventional FSM [4]. 1

Kalman's optimum linear filter has proved to be immensely popular in the field of computer vision. A less often quoted contribution of Kalman's to the control theory literature is that of the concepts of controllability and observability which may be used to analyse the state transition and observation equations and give insights into the filter's viability. This paper aims to highlight the usefulness of these two ideas during the design stage of the filter and, as well as presenting the standard solutions for linear systems, uses a practical vision application (that of tracking plants for an autonomous crop protection vehicle) to illustrate a useful special case where these methods may be applied to a non-linear system. The application of tests for controllability and observability to the practical non-linear system give not only confirmation that the filter will be able to produce stable estimates, but also gives a lower bound on the number of features required from each image for it...

Three different statistical models of colour data for use in segmentation or tracking algorithms are proposed. The results of a performance comparison of a tracking algorithm, applied to two separate applications, using each of the three different types of underlying model of the data are presented. From these a comparison of the performance of the statistical colour models themselves is obtained.

Statistical colour models may be used to characterise regions of interest within images or sequences of images. In this work two types of model, one based on underlying Gaussian statistics and one using a Bingham distribution, are compared on both a theoretical and an experimental level. It is shown that when certain conditions hold, the Bingham model tends to have superior performance but that the performance of the Gaussian model degrades more slowly as these assumptions are relaxed.

This paper presents results from computer experiments with an algorithm to perform scene disposition and motion segmentation from visual motion or optic flow. The maximum a posteriori (MAP) criterion is used to formulate what the best segmentation or interpretation of the scene should be, where the scene is assumed to be made up of some fixed number of moving planar surface patches. The Bayesian approach requires, first, specification of prior expectations for the optic flow field, which here is modeled as spatial and temporal Markov random fields; and, secondly, a way of measuring how well the segmentation predicts the measured flow field. The Markov random fields incorporate the physical constraints that objects and their images are probably spatially continuous, and that their images are likely to move quite smoothly across the image plane. To compute the flow predicted by the segmentation, a recent method for reconstructing the motion and orientation of planar surface facets is used. The search for the globally optimal segmentation is performed using simulated annealing.