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
Diverse Non-Negative Matrix Factorization for Multiview Data Representation
TL;DR: A diverse NMF (DiNMF) approach is proposed, which enhances the diversity, reduces the redundancy among multiview representations with a novel defined diversity term and enables the learning process in linear execution time, and a locality preserved DiNMF (LP-Di NMF) for more accurate learning.
Journal ArticleDOI
Re-Weighted Discriminatively Embedded $K$ -Means for Multi-View Clustering
TL;DR: Compared with several state-of-the-art multi-view clustering methods, the proposed method substantially improves the accuracy of the clustering results on widely used benchmark data sets, which demonstrates the superiority of the proposed work.
Proceedings ArticleDOI
Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context
Gautam Singh,Jana Kosecka +1 more
TL;DR: This paper presents a nonparametric approach to semantic parsing using small patches and simple gradient, color and location features and examines the importance of the retrieval set used to compute the nearest neighbours using a novel semantic descriptor to retrieve better candidates.
Book ChapterDOI
Part-based feature synthesis for human detection
TL;DR: An empirical evaluation of the new approach for learning part-based object detection through feature synthesis suggests that the approach is on a par with the best current methods and advances the state-of-the-art on the Caltech pedestrian training dataset.
Proceedings ArticleDOI
Learning to Count Leaves in Rosette Plants
TL;DR: These findings suggest that it is possible to treat leaf counting as a regression problem, requiring as input only the total leaf count per training image, and relate image-based descriptors learned in an unsupervised fashion to leaf counts using a supervised regression model.
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.