A SIFT Descriptor with Global Context

Mortensen, Eric N.; Deng, Hucheng; Shapiro, Linda G.

doi:10.1109/cvpr.2005.45

Cited by 190 publications

(132 citation statements)

References 18 publications

Supporting

Mentioning

129

Contrasting

Unclassified

Order By: Relevance

“…Edge-driven dual-bootstrap iterative closest point (ED-DB-ICP) [12] is a modi cation of GDB-ICP designed for the registration of multimodal Fluorescein angiogram (FA) sequences. The main di erences of ED-DB-ICP with respect to GDB-ICP are the use of gradient magnitude images instead of intensity images and extending the SIFT-descriptors with a shape context descriptor presented in detail in [6]. Publicly available implementations were used for all the methods.…”

Section: Methodsmentioning

confidence: 99%

Comparison of image registration methods for composing spectral retinal images

Laaksonen

Claridge

Fält

et al. 2014

Proceedings of the Ophthalmic Medical Image Analysis First International Workshop

View full text Add to dashboard Cite

Abstract. Spectral retinal images have signi cant potential for improving the early detection and visualization of subtle changes due to eye diseases and many systemic diseases. High resolution in both the spatial and the spectral domain can be achieved by capturing a set of narrowband channel images from which the spectral images are composed. With imaging techniques where the eye movement between the acquisition of the images is unavoidable, image registration is required. In this paper, the applicability of the state-of-the-art image registration methods for the composition of spectral retinal images is studied. The registration methods are quantitatively compared using synthetic channel image data of an eye phantom and semisynthetic set of retinal channel images subjected to known transformations. The experiments show that Generalized dual-bootstrap iterative closest point method outperforms the other evaluated methods in registration accuracy and the number of successful registrations.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparison of image registration methods for composing spectral retinal images

Laaksonen

Claridge

Fält

et al. 2014

Proceedings of the Ophthalmic Medical Image Analysis First International Workshop

View full text Add to dashboard Cite

show abstract

“…A variety of image features and representations have been used by other authors, such as Gabor filters (Nestares et al 1998), wavelets (Strang and Nguyen 1997), SIFT features (Mortensen et al 2005), etc. Many of these image features are used for purposes such as recognizing objects (Murphy et al 2003;Serre et al 2005), faces (Zhao et al 2003), facial expressions (Saxena et al 2004), grasps (Saxena et al 2006a); image segmentation (Konishi and Yuille 2000), computing the visual gist of a scene (Oliva and Torralba 2006) and computing sparse representations of natural images (Olshausen and Field 1997).…”

Section: Related Workmentioning

confidence: 99%

3-D Depth Reconstruction from a Single Still Image

2007

View full text Add to dashboard Cite

We consider the task of 3-d depth estimation from a single still image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which include forests, sidewalks, trees, buildings, etc.) and their corresponding ground-truth depthmaps. Then, we apply supervised learning to predict the value of the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a hierarchical, multiscale Markov Random Field (MRF) that incorporates multiscale local-and global-image features, and models the depths and the relation between depths at different points in the image. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps. We further propose a model that incorporates both monocular cues and stereo (triangulation) cues, to obtain significantly more accurate depth estimates than is possible using either monocular or stereo cues alone.

show abstract

“…E. N. Mortensen [12] introduced a SIFT descriptor with global context (called GSIFT), which adds a global texture vector to the basis of SIFT.…”

Section: Related Workmentioning

confidence: 99%

“…According to the statistics of references in Google Scholar, the article [7], which published the SIFT algorithm, has more than 12,000 references. Among its variants, the numbers of references of PCA-SIFT [11], GSIFT [12], CSIFT [13], SURF [14] and ASIFT [15] are relatively high. Thus, these algorithms are selected and investigated in this paper.…”

Section: Related Workmentioning

confidence: 99%

A Comparative Study of SIFT and its Variants

Wu¹,

Cui²,

Sheng³

et al. 2013

Measurement Science Review

154

View full text Add to dashboard Cite

SIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved algorithms that have drawn a lot of attention are PCA-SIFT, GSIFT, CSIFT, SURF and ASIFT. In this paper, we first systematically analyze SIFT and its variants. Then, we evaluate their performance in different situations: scale change, rotation change, blur change, illumination change, and affine change. The experimental results show that each has its own advantages. SIFT and CSIFT perform the best under scale and rotation change. CSIFT improves SIFT under blur change and affine change, but not illumination change. GSIFT performs the best under blur change and illumination change. ASIFT performs the best under affine change. PCA-SIFT is always the second in different situations. SURF performs the worst in different situations, but runs the fastest.

show abstract

A SIFT Descriptor with Global Context

Cited by 190 publications

References 18 publications

Comparison of image registration methods for composing spectral retinal images

Comparison of image registration methods for composing spectral retinal images

3-D Depth Reconstruction from a Single Still Image

A Comparative Study of SIFT and its Variants

Contact Info

Product

Resources

About