prototype shape that is maximally similar to that in the image. Results are presented for silhouettes, trademarks, handwritten digits and the COIL dataset.

Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ 2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on four texture and five object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate the influence of background correlations on recognition performance via extensive tests on the PASCAL database, for which ground-truth object localization information is available. Our experiments demonstrate that image representations based on distributions of local features are surprisingly effective for classification of texture and object images under challenging real-world conditions, including significant intra-class variations and substantial background clutter.

The purpose of this chapter is to present a survey of recent publications concerning medical image registration techniques. These publications will be classified according to a model based on nine salient criteria, the main dichotomy of which is extrinsic versus intrinsic methods The statistics of the classification show definite trends in the evolving registration techniques, which will be discussed. At this moment, the bulk of interesting intrinsic methods is either based on segmented points or surfaces, or on techniques endeavoring to use the full information content of the images involved. Keywords: registration, matching Received May 25, 1997

Motivation: Protein homology detection and sequence alignment are at the basis of protein structure prediction, function prediction, and evolution. Results: We have generalized the alignment of protein se-quences with a profile hidden Markov model (HMM) to the case of pairwise alignment of profile HMMs. We present a method for detecting distant homologous relationships between proteins based on this approach. The method (HHsearch) is benchmarked together with BLAST, PSI-BLAST, HMMER, and the profile-profile comparison tools PROF_SIM and COMPASS, in an all-against-all compari-son of a database of 3691 protein domains from SCOP 1.63 with pairwise sequence identities below 20%. Sensitivity: When predicted secondary structure is included in the HMMs, HHsearch is able to detect between 2.7 and 4.2 times more homologs than PSI-BLAST or HMMER and between 1.44 and 1.9 times more than COMPASS or PROF_SIM for a rate of false positives of 10%. Approxi-mately half of the improvement over the profile–profile com-parison methods is attributable to the use of profile HMMs in place of simple profiles. Alignment quality: Higher sensitivity is mirrored by an in-creased alignment quality. HHsearch produced 1.2, 1.7, and 3.3 times more good alignments (“balanced ” score> 0.3) than the next best method (COMPASS), and 1.6, 2.9, and 9.4 times more than PSI-BLAST, at the family, super-family, and fold level. Speed: HHsearch scans a query of 200 residues against 3691 domains in 33s on an AMD64 3GHz PC. This is 10 times faster than PROF_SIM and 17 times faster than

Receiver Operating Characteristics (ROC) graphs are a useful technique for organizing classifiers and visualizing their performance. ROC graphs are commonly used in medical decision making, and in recent years have been increasingly adopted in the machine learning and data mining research communities. Although ROC graphs are apparently simple, there are some common misconceptions and pitfalls when using them in practice. This article serves both as a tutorial introduction to ROC graphs and as a practical guide for using them in research.

Datasets are an integral part of contemporary object recognition research. They have been the chief reason for the considerable progress in the field, not just as source of large amounts of training data, but also as means of measuring and comparing performance of competing algorithms. At the same

In the past, nearest neighbor algorithms for learning from examples have worked best in domains in which all features had numeric values. In such domains, the examples can be treated as points and distance metrics can use standard definitions. In symbolic domains, a more sophisticated treatment of the feature space is required. We introduce a nearest neighbor algorithm for learning in domains with symbolic features. Our algorithm calculates distance tables that allow it to produce real-valued distances between instances, and attaches weights to the instances to further modify the structure of feature space. We show that this technique produces excellent classification accuracy on three problems that have been studied by machine learning researchers: predicting protein secondary structure, identifying DNA promoter sequences, and pronouncing English text. Direct experimental comparisons with the other learning algorithms show that our nearest neighbor algorithm is comparable or superior ...

The Universal Protein Resource (UniProt) provides a central resource on protein sequences and functional annotation with three database components, each addressing a key need in protein bioinformatics. The UniProt Knowledgebase (UniProtKB), compris-ing the manually annotated UniProtKB/Swiss-Prot section and the automatically annotated UniProtKB/ TrEMBL section, is the preeminent storehouse of pro-tein annotation. The extensive cross-references, functional and feature annotations and literature-based evidence attribution enable scientists to anal-yse proteins and query across databases. The UniProt Reference Clusters (UniRef) speed similarity searches via sequence space compression by merg-ing sequences that are 100 % (UniRef100), 90% (UniRef90) or 50 % (UniRef50) identical. Finally, the UniProt Archive (UniParc) stores all publicly available protein sequences, containing the history of sequence data with links to the source databases. UniProt databases continue to grow in size and in availability of information. Recent and upcoming changes to database contents, formats, controlled vocabularies and services are described. New down-load availability includes all major releases of UniProtKB, sequence collections by taxonomic divi-sion and complete proteomes. A bibliography map-ping service has been added, and an ID mapping service will be available soon. UniProt databases can be accessed online at

Pfam is a widely used database of protein families, currently containing more than 13 000 manually curated protein families as of release 26.0. Pfam is available via servers in the UK

ReCoil- an algorithm for compression of