Open Access
Distinctive Image Features from Scale-Invariant Keypoints
TLDR
The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images that can then be used to reliably match objects in diering images.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Interactive Multimodal Visual Search on Mobile Device
TL;DR: The proposed JIGSAW${+}$ is able to achieve 5% gain in terms of search performance and is ten times faster.
Journal ArticleDOI
Remote Sensing Image Registration Using Multiple Image Features
TL;DR: A multi-viewpoint remote sensing image registration method which contains a geometric constraint term introduced into the L2E-based energy function for better behaving the non-rigid transformation and compared with five state-of-the-art methods.
Journal ArticleDOI
Empowering Visual Categorization With the GPU
TL;DR: This paper analyzed the bag-of-words model for visual categorization in terms of computational cost and identified two major bottlenecks: the quantization step and the classification step and proposes two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model.
Journal ArticleDOI
Automatic Image Annotation and Retrieval Using Group Sparsity
TL;DR: A group-sparsity-based feature selection algorithm is introduced to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task, and keyword similarity is modeled in the annotation framework.
Proceedings ArticleDOI
Transform coding of image feature descriptors
TL;DR: It is shown that image and feature matching algorithms are robust to significantly compressed features, and a strong correlation between MSE and matching error for feature points and images is established.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: 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 and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Proceedings ArticleDOI
A Combined Corner and Edge Detector
Chris Harris,Mike Stephens +1 more
TL;DR: The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
Journal ArticleDOI
A performance evaluation of local descriptors
TL;DR: It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Journal ArticleDOI
Robust wide-baseline stereo from maximally stable extremal regions
TL;DR: The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.