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)

/pdf/on-the-handling-of-spatial-and-temporal-scales-in-feature-3l0mlckcjz.pdf

On the Handling of Spatial and Temporal Scales in Feature Tracking

Scale selection methods based on local extrema over scale of scale-normalized derivatives have been primarily developed to be applied sparsely --- at image points where the magnitude of a scale-normalized differential expression additionally assumes local extrema over the domain where the data are defined. This paper presents a methodology for performing dense scale selection, so that hypotheses about local characteristic scales in images, temporal signals and video can be computed at every image point and every time moment. 
A critical problem when designing mechanisms for dense scale selection is that the scale at which scale-normalized differential entities assume local extrema over scale can be strongly dependent on the local order of the locally dominant differential structure. To address this problem, we propose a methodology where local extrema over scale are detected of a quasi quadrature measure involving scale-space derivatives up to order two and propose two independent mechanisms to reduce the phase dependency of the local scale estimates by: (i) introducing a second layer of post-smoothing prior to the detection of local extrema over scale and (ii) performing local phase compensation based on a model of the phase dependency of the local scale estimates depending on the relative strengths between first- vs. second-order differential structure. 
This general methodology is applied over three types of domains: (i) spatial images, (ii) temporal signals and (iii) spatio-temporal video. Experiments show that the proposed methodology leads to intuitively reasonable results with local scale estimates that reflect variations in the characteristic scales of locally dominant structures over space and time.

Dense scale selection over space, time and space-time

This paper presents a set of image operators for detecting regions in space-time where interesting events occur. To define such regions of interest, we compute a spatio-temporal secondmoment matrix from a spatio-temporal scale-space representation, and diagonalize this matrix locally, using a local Galilean transformation in space-time, optionally combined with a spatial rotation, so as to make the Galilean invariant degrees of freedom explicit. From the Galilean-diagonalized descriptor so obtained, we then formulate different types of space-time interest operators, and illustrate their properties on different types of image sequences.

/pdf/galilean-corrected-spatio-temporal-interest-operators-5wm42yh4qt.pdf

Galilean-corrected spatio-temporal interest operators

This article presents a theory for constructing hierarchical networks in such a way that the networks are guaranteed to be provably scale covariant. We first present a general sufficiency argument for obtaining scale covariance, which holds for a wide class of networks defined from linear and nonlinear differential expressions expressed in terms of scale-normalized scale-space derivatives. Then, we present a more detailed development of one example of such a network constructed from a combination of mathematically derived models of receptive fields and biologically inspired computations. Based on a functional model of complex cells in terms of an oriented quasi quadrature combination of first- and second-order directional Gaussian derivatives, we couple such primitive computations in cascade over combinatorial expansions over image orientations. Scale-space properties of the computational primitives are analysed, and we give explicit proofs of how the resulting representation allows for scale and rotation covariance. A prototype application to texture analysis is developed, and it is demonstrated that a simplified mean-reduced representation of the resulting QuasiQuadNet leads to promising experimental results on three texture datasets.

/pdf/provably-scale-covariant-continuous-hierarchical-networks-45dyktxdzb.pdf

Provably Scale-Covariant Continuous Hierarchical Networks Based on Scale-Normalized Differential Expressions Coupled in Cascade

We show how the axiomatic structure of scale-space theory can be applied to the auditory domain and be used for deriving idealized models of auditory receptive fields via scale-space principles. For defining a time-frequency transformation of a purely temporal signal, it is shown that the scale-space framework allows for a new way of deriving the Gabor and Gammatone filters as well as a novel family of generalized Gammatone filters with additional degrees of freedom to obtain different trade-offs between the spectral selectivity and the temporal delay of time-causal window functions. Applied to the definition of a second layer of receptive fields from the spectrogram, it is shown that the scale-space framework leads to two canonical families of spectro-temporal receptive fields, using a combination of Gaussian filters over the logspectral domain with either Gaussian filters or a cascade of first-order integrators over the temporal domain. These spectro-temporal receptive fields can be either separable over the time-frequency domain or be adapted to local glissando transformations that represent variations in logarithmic frequencies over time. Such idealized models of auditory receptive fields respect auditory invariances, can be used for computing basic auditory features for audio processing and lead to predictions about auditory receptive fields with good qualitative similarity to biological receptive fields in the inferior colliculus (ICC) and the primary auditory cortex (A1).

/pdf/scale-space-theory-for-auditory-signals-4m6i8ypy0w.pdf

Tony Lindeberg

Papers

On the Handling of Spatial and Temporal Scales in Feature Tracking

Dense scale selection over space, time and space-time

Galilean-corrected spatio-temporal interest operators

Provably Scale-Covariant Continuous Hierarchical Networks Based on Scale-Normalized Differential Expressions Coupled in Cascade

Scale-Space Theory for Auditory Signals