What Do Features Tell about Images?

Nielsen, Mads; Lillholm, Martin

doi:10.1007/3-540-47778-0_4

Cited by 33 publications

(45 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The γ-normalization with scale invariance is discussed in detail by Florack and Kuijper [4]. Blobs can be ordered in strength by the magnitude of the response of their respective filters [27,20].…”

Section: Scale Space Interest Pointsmentioning

confidence: 99%

“…It is known that from a sufficiently rich set of scale space interest points, a visually attractive reconstruction of the original image can be created [27,20,13,14]. Such a reconstruction can for example be used for image understanding or image editing.…”

Section: Introductionmentioning

confidence: 99%

“…These points are usually ordered by their strength [27,20] or by the differential (quadratic) TV norm [29,14] in the corresponding points. Lillholm and Nielsen showed that a combination of different types of interest points can improve the reconstruction quality substantially [27,20]. It is however not clear how exactly these points should be selected.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Kanters

Denton

Shokoufandeh

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Scale space interest points capture important photometric and deep structure information of an image. The information content of such points can be made explicit using image reconstruction. In this paper we will consider the problem of combining multiple types of interest points used for image reconstruction. It is shown that ordering the complete set of points by differential (quadratic) TV-norm (which works for single feature types) does not yield optimal results for combined point sets. The paper presents a method to solve this problem using canonical sets of scale space features. Qualitative and quantitative analysis show improved performance over simple ordering of points using the TV-norm.

show abstract

Section: Scale Space Interest Pointsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Kanters

Denton

Shokoufandeh

et al. 2007

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Reconstruction from differential structure of scale space interest points, first introduced by Nielsen and Lillholm (2001), is an interesting instance of the reconstruction problem, since the samples are non-uniformly distributed over the image they were obtained from and the filter responses of the filters do not necessarily coincide. Several linear and non-linear methods (Nielsen and Lillholm 2001;Janssen et al 2006;Lillholm et al 2003) appeared in literature which all search for an image that (1) is indistinguishable from its original when observed through the filters the features were extracted with, and (2) simultaneously minimizes a certain prior.…”

Section: Introductionmentioning

confidence: 99%

“…Several linear and non-linear methods (Nielsen and Lillholm 2001;Janssen et al 2006;Lillholm et al 2003) appeared in literature which all search for an image that (1) is indistinguishable from its original when observed through the filters the features were extracted with, and (2) simultaneously minimizes a certain prior. If such a prior is a norm of Sobolev type on the unbounded domain one can obtain visually attractive reconstructions while retaining linearity, as we have shown in earlier work (Janssen et al 2006;Duits 2005).…”

Section: Introductionmentioning

confidence: 99%

Linear Image Reconstruction by Sobolev Norms on the Bounded Domain

Janssen

Duits

2008

Int J Comput Vis

View full text Add to dashboard Cite

The reconstruction problem is usually formulated as a variational problem in which one searches for that image that minimizes a so called prior (image model) while insisting on certain image features to be preserved. When the prior can be described by a norm induced by some inner product on a Hilbert space, the exact solution to the variational problem can be found by orthogonal projection. In previous work we considered the image as compactly supported in L 2 (R 2 ) and we used Sobolev norms on the unbounded domain including a smoothing parameter γ > 0 to tune the smoothness of the reconstructed image. Due to the assumption of compact support of the original image, components of the reconstructed image near the image boundary are too much penalized. Therefore, in this work we minimize Sobolev norms only on the actual image domain, yielding much better reconstructions (especially for γ 0). As an example we apply our method to the reconstruction of singular points that are present in the scale space representation of an image.

show abstract

On Image Reconstruction from Multiscale Top Points

Kanters

Lillholm

Duits

et al. 2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Image reconstruction from a fiducial collection of scale space interest points and attributes (e.g. in terms of image derivatives) can be used to make the amount of information contained in them explicit. Previous work by various authors includes both linear and non-linear image reconstruction schemes. In this paper, the authors present new results on image reconstruction using a top point representation of an image.A hierarchical ordering of top points based on a stability measure is presented, comparable to feature strength presented in various other works. By taking this into account our results show improved reconstructions from top points compared to previous work. The proposed top point representation is compared with previously proposed representations based on alternative feature sets, such as blobs using two reconstruction schemes (one linear, one non-linear). The stability of the reconstruction from the proposed top point representation under noise is also considered.

show abstract

What Do Features Tell about Images?

Cited by 33 publications

References 8 publications

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Combining Different Types of Scale Space Interest Points Using Canonical Sets

Linear Image Reconstruction by Sobolev Norms on the Bounded Domain

On Image Reconstruction from Multiscale Top Points

Contact Info

Product

Resources

About