In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.

This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF's strong performance.

/pdf/surf-speeded-up-robust-features-1fje09jteo.pdf

SURF: speeded up robust features

https://www.cs.jhu.edu/~misha/ReadingSeminar/Papers/Bay08.pdf

Speeded-Up Robust Features (SURF)

Advances in functional and structural MR image analysis and implementation as FSL.

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Anomaly detection is an important problem that has been researched within diverse research areas and application domains. Many anomaly detection techniques have been specifically developed for certain application domains, while others are more generic. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection. We have grouped existing techniques into different categories based on the underlying approach adopted by each technique. For each category we have identified key assumptions, which are used by the techniques to differentiate between normal and anomalous behavior. When applying a given technique to a particular domain, these assumptions can be used as guidelines to assess the effectiveness of the technique in that domain. For each category, we provide a basic anomaly detection technique, and then show how the different existing techniques in that category are variants of the basic technique. This template provides an easier and more succinct understanding of the techniques belonging to each category. Further, for each category, we identify the advantages and disadvantages of the techniques in that category. We also provide a discussion on the computational complexity of the techniques since it is an important issue in real application domains. We hope that this survey will provide a better understanding of the different directions in which research has been done on this topic, and how techniques developed in one area can be applied in domains for which they were not intended to begin with.

/pdf/anomaly-detection-a-survey-1x33g9m0a3.pdf

Anomaly detection: A survey

Improved optimization for the robust and accurate linear registration and motion correction of brain images

Many computer vision problems can be considered to consist of two main tasks: the extraction of image content descriptions and their subsequent matching. The appropriate choice of type and level of description is of course task dependent, yet it is generally accepted that the low-level or so called early vision layers in the Human Visual System are context independent.

This paper concentrates on the use of low-level approaches for solving computer vision problems and discusses three inter-related aspects of this: saliencys scale selection and content description. In contrast to many previous approaches which separate these tasks, we argue that these three aspects are intrinsically related. Based on this observation, a multiscale algorithm for the selection of salient regions of an image is introduced and its application to matching type problems such as tracking, object recognition and image retrieval is demonstrated.

/pdf/saliency-scale-and-image-description-19bs91yuos.pdf

Saliency, Scale and Image Description

For quantitative PET information, correction of tissue photon attenuation is mandatory. Generally in conventional PET, the attenuation map is obtained from a transmission scan, which uses a rotating radionuclide source, or from the CT scan in a combined PET/CT scanner. In the case of PET/MRI scanners currently under development, insufficient space for the rotating source exists; the attenuation map can be calculated from the MR image instead. This task is challenging because MR intensities correlate with proton densities and tissue-relaxation properties, rather than with attenuation-related mass density. Methods: We used a combination of local pattern recognition and atlas registration, which captures global variation of anatomy, to predict pseudo-CT images from a given MR image. These pseudo-CT images were then used for attenuation correction, as the process would be performed in a PET/CT scanner. Results: For human brain scans, we show on a database of 17 MR/CT image pairs that our method reliably enables estimation of a pseudo-CT image from the MR image alone. On additional datasets of MRI/PET/CT triplets of human brain scans, we compare MRI-based attenuation correction with CT-based correction. Our approach enables PET quantification with a mean error of 3.2% for predefined regions of interest, which we found to be clinically not significant. However, our method is not specific to brain imaging, and we show promising initial results on 1 whole-body animal dataset. Conclusion: This method allows reliable MRI-based attenuation correction for human brain scans. Further work is necessary to validate the method for whole-body imaging.

/pdf/mri-based-attenuation-correction-for-pet-mri-a-novel-2q82meeqmz.pdf

MRI-Based Attenuation Correction for PET/MRI: A Novel Approach Combining Pattern Recognition and Atlas Registration

The authors propose a modification of Wells et al. (ibid., vol. 15, no. 4, p. 429-42, 1996) technique for bias field estimation and segmentation of magnetic resonance (MR) images. They show that replacing the class other, which includes all tissue not modeled explicitly by Gaussians with small variance, by a uniform probability density, and amending the expectation-maximization (EM) algorithm appropriately, gives significantly better results. The authors next consider the estimation and filtering of high-frequency information in MR images, comprising noise, intertissue boundaries, and within tissue microstructures. The authors conclude that post-filtering is preferable to the prefiltering that has been proposed previously. The authors observe that the performance of any segmentation algorithm, in particular that of Wells et al. (and the authors' refinements of it) is affected substantially by the number and selection of the tissue classes that are modeled explicitly, the corresponding defining parameters and, critically, the spatial distribution of tissues in the image. The authors present an initial exploration to choose automatically the number of classes and the associated parameters that give the best output. This requires the authors to define what is meant by "best output" and for this they propose the application of minimum entropy. The methods developed have been implemented and are illustrated throughout on simulated and real data (brain and breast MR).

Estimating the bias field of MR images

Breast cancer is the major cause of death amongst women in the 35 to 55 age group. Mammography is the only feasible imaging modality for screening large numbers of women. With the present screening policy, there are three million mammograms to be analysed each year in the UK; there is therefore a need (as yet unmet) for an automated analysis system which could highlight areas of interest. In the first instance, the areas of interest might simply be any mass-like structures and this is indeed the approach reported on in this paper. Mammography is typical of many problems in medicine: the class of real interest is under-represented in the database of available examples and hence its prior probability will be very low. As a result of this, there are very few examples of abnormalities in any of the existing databases. If a neural network classifier is trained using the standard approach of minimising the mean-squared error (MSE) at the output, the under-represented class will be ignored. We have been exploring an alternative approach in which we attempt to learn a description of normality using the large number of available mammograms which do not show any evidence of mass-like structures. The idea is then to test for novelty against this description in order to try and identify candidate masses in previously unseen images analysis and interpretation and present a sample of the results which we have so far obtained on a standard database.

Michael Brady

Papers

Improved optimization for the robust and accurate linear registration and motion correction of brain images

Saliency, Scale and Image Description

MRI-Based Attenuation Correction for PET/MRI: A Novel Approach Combining Pattern Recognition and Atlas Registration

Estimating the bias field of MR images

Novelty detection for the identification of masses in mammograms