This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

/pdf/distinctive-image-features-from-scale-invariant-keypoints-3waurjqzke.pdf

Distinctive Image Features from Scale-Invariant Keypoints

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

/pdf/object-recognition-from-local-scale-invariant-features-5887b1cgwf.pdf

Object recognition from local scale-invariant features

The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.

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)

A fundamental problem in brain imaging concerns how to define functional areas consisting of neurons that are activated together as populations. We propose that this issue can be ideally addressed by a computer vision tool referred to as the scale-space primal sketch. This concept has the attractive properties that it allows for automatic and simultaneous extraction of the spatial extent and the significance of regions with locally high activity. In addition, a hierarchical nested tree structure of activated regions and subregions is obtained. The subject in this article is to show how the scale-space primal sketch can be used for automatic determination of the spatial extent and the significance of rCBF changes. Experiments show the result of applying this approach to functional PET data, including a preliminary comparison with two more traditional clustering techniques. Compared to previous approaches, the method overcomes the limitations of performing the analysis at a single scale or assuming specific models of the data.

/pdf/analysis-of-brain-activation-patterns-using-a-3-d-scale-49a72gpvys.pdf

Analysis of brain activation patterns using a 3-D scale-space primal sketch.

This paper shows how the performance of feature trackers can be improved by building a view-based object representation consisting of qualitative relations between image structures at Different scales. The idea is to track all image features individually, and to use the qualitative feature relations for resolving ambiguous matches and for introducing feature hypotheses whenever image features are mismatched or lost. Compared to more traditional work on view-based object tracking, this methodology has the ability to handle semi-rigid objects and partial occlusions. Compared to trackers based on three-dimensional object models, this approach is much simpler and of a more generic nature. A hands-on example is presented showing how an integrated application system can be constructed from conceptually very simple operations.

/pdf/qualitative-multi-scale-feature-hierarchies-for-object-2bh8xv1yu4.pdf

Qualitative Multi-scale Feature Hierarchies for Object Tracking

The notion of multi-scale representation is essential to many aspects of early visual processing. This article deals with the axiomatic formulation of the special type of multi-scale representation known as scale-space representation. Specifically, this work is concerned with the problem of how different choices of basic assumptions (scale-space axioms) restrict the class of permissible smoothing operations.A scale-space formulation previously expressed for discrete signals is adapted to the continuous domain. The basic assumptions are that the scale-space family should be generated by convolution with a one-parameter family of rotationally symmetric smoothing kernels that satisfy a semi-group structure and obey a causality condition expressed as a non-enhancement requirement of local extrema. Under these assumptions, it is shown that the smoothing kernel is uniquely determined to be a Gaussian.Relations between this scale scale-space formulation and recent formulations based on scale invariance are explained in detail. Connections are also pointed out to approaches based on non-uniform smoothing.

/pdf/on-the-axiomatic-foundations-of-linear-scale-space-combining-3erqjc7rbp.pdf

On the axiomatic foundations of linear scale-space : Combining semi-group structure with causality vs. scale invariance

Qualitative Multiscale Feature Hierarchies for Object Tracking

This paper outlines a general framework for automatic selection in temporal scale-space representations, and shows how the suggested theory applies to motion detection and motion estimation.

/pdf/on-automatic-selection-of-temporal-scales-in-time-causal-3ewj9by88q.pdf

Tony Lindeberg

Papers

Analysis of brain activation patterns using a 3-D scale-space primal sketch.

Qualitative Multi-scale Feature Hierarchies for Object Tracking

On the axiomatic foundations of linear scale-space : Combining semi-group structure with causality vs. scale invariance

Qualitative Multiscale Feature Hierarchies for Object Tracking

On Automatic Selection of Temporal Scales in Time-Causal Scale-Space