Distinctive Image Features from Scale-Invariant Keypoints
01 Jan 2011-
TL;DR: 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.
Citations
More filters
TL;DR: A novel fusion of different recognition approaches is proposed and described how it can contribute to more reliable noncooperative iris recognition by compensating for degraded images captured in less constrained acquisition setups and protocols under visible wavelengths and varying lighting conditions.
104 citations
Cites methods from "Distinctive Image Features from Sca..."
...To achieve those results, a publicly available SIFT implementation3 was used, and its parameters optimized based on tests performed on the training dataset....
[...]
...II - http://www.nice2.di.ubi.pt. dðu;vÞ ¼ ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiXn i¼1 ðui v iÞ2 vuut ð6Þ As for the features extracted by the SIFT, the distance-ratiobased matching scheme (Lowe, 2004) was applied....
[...]
...Differing from the previous method, where features were only extracted from the region closest to the eye, the Scale-Invariant Feature Transform (SIFT) (Lowe, 2004) was applied to all available data, here seeking salient regions (e....
[...]
...Differing from the previous method, where features were only extracted from the region closest to the eye, the Scale-Invariant Feature Transform (SIFT) (Lowe, 2004) was applied to all available data, here seeking salient regions (e.g., facial marks)....
[...]
...AUC LBP 0.99 31.87 0.76 SIFT 0.87 32.09 0.74 1-...
[...]
TL;DR: This paper proposes to parallelize the near duplicate visual search architecture to index millions of images over multiple servers, including the distribution of both visual vocabulary and the corresponding indexing structure, and validates the distributed vocabulary indexing scheme in a real world location search system over 10 million landmark images.
Abstract: In recent years, there is an ever-increasing research focus on Bag-of-Words based near duplicate visual search paradigm with inverted indexing. One fundamental yet unexploited challenge is how to maintain the large indexing structures within a single server subject to its memory constraint, which is extremely hard to scale up to millions or even billions of images. In this paper, we propose to parallelize the near duplicate visual search architecture to index millions of images over multiple servers, including the distribution of both visual vocabulary and the corresponding indexing structure. We optimize the distribution of vocabulary indexing from a machine learning perspective, which provides a “memory light” search paradigm that leverages the computational power across multiple servers to reduce the search latency. Especially, our solution addresses two essential issues: “What to distribute” and “How to distribute”. “What to distribute” is addressed by a “lossy” vocabulary Boosting, which discards both frequent and indiscriminating words prior to distribution. “How to distribute” is addressed by learning an optimal distribution function, which maximizes the uniformity of assigning the words of a given query to multiple servers. We validate the distributed vocabulary indexing scheme in a real world location search system over 10 million landmark images. Comparing to the state-of-the-art alternatives of single-server search [5], [6], [16] and distributed search [23], our scheme has yielded a significant gain of about 200% speedup at comparable precision by distributing only 5% words. We also report excellent robustness even when partial servers crash.
104 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...In general, state-of-the-art visual search systems are built based upon a visual vocabulary model with an inverted indexing structure [4]–[7], which quantizes local features [1], [2] of query and reference images into visual words....
[...]
...C OMING with the popularity of local feature representations [1]–[3], recent years have witnessed an ever-increasing research focus on near duplicate visual search, with numerous applications in mobile location search, mobile product...
[...]
...11 Parameter Setting and Storage Cost: We extract SIFT features [1] for each image in each reference dataset....
[...]
01 Jan 2013
TL;DR: This work proposes a seam-driven image stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, the goodness of a transform is evaluated based upon the resulting visual quality of the seam-cut.
Abstract: Image stitching computes geometric transforms to align images based on the best fit of feature correspondences between overlapping images. Seam-cutting is used afterwards to to hide misalignment artifacts. Interestingly it is often the seam-cutting step that is the most crucial for obtaining a perceptually seamless result. This motivates us to propose a seam-driven image stitching strategy where instead of estimating a geometric transform based on the best fit of feature correspondences, we evaluate the goodness of a transform based on the resulting visual quality of the seam-cut. We show that this new image stitching strategy can often produce better perceptual results than existing methods especially for challenging scenes.
104 citations
TL;DR: A novel, custom-designed multi-robot platform for research on AI, robotics, and especially human–robot interaction for service robots designed as a part of the Building-Wide Intelligence project at the University of Texas at Austin is introduced.
Abstract: Recent progress in both AI and robotics have enabled the development of general purpose robot platforms that are capable of executing a wide variety of complex, temporally extended service tasks in open environments. This article introduces a novel, custom-designed multi-robot platform for research on AI, robotics, and especially human–robot interaction for service robots. Called BWIBots, the robots were designed as a part of the Building-Wide Intelligence (BWI) project at the University of Texas at Austin. The article begins with a description of, and justification for, the hardware and software design decisions underlying the BWIBots, with the aim of informing the design of such platforms in the future. It then proceeds to present an overview of various research contributions that have enabled the BWIBots to better (a) execute action sequences to complete user requests, (b) efficiently ask questions to resolve user requests, (c) understand human commands given in natural language, and (d) understand hum...
104 citations
Cites methods from "Distinctive Image Features from Sca..."
...It has primarily been used for detecting objects using SIFT visual features (Lowe, 2004)....
[...]
...It has primarily been used for detecting objects using SIFT visual features (Lowe 2004)....
[...]
30 Oct 2009
TL;DR: This paper proposes to exploit SURF features in face recognition in this paper by exploiting the advantages of SURF, a scale and in-plane rotation invariant detector and descriptor with comparable or even better performance with SIFT.
Abstract: The Scale Invariant Feature Transform (SIFT) proposed by David G. Lowe has been used in face recognition and proved
to perform well. Recently, a new detector and descriptor, named Speed-Up Robust Features (SURF) suggested by
Herbert Bay, attracts people's attentions. SURF is a scale and in-plane rotation invariant detector and descriptor with
comparable or even better performance with SIFT. Because each of SURF feature has only 64 dimensions in general and
an indexing scheme is built by using the sign of the Laplacian, SURF is much faster than the 128-dimensional SIFT at
the matching step. Thus based on the above advantages of SURF, we propose to exploit SURF features in face
recognition in this paper.
104 citations
Cites methods from "Distinctive Image Features from Sca..."
...In this paper, based on point matching method suggest in [5][6], we introduce geometric constraints into point-matching based on SURF features to increase the matching speed and robustness....
[...]
...Lowe [5][6] has been widely used in object detection and recognition....
[...]
...In [4][3] they all used the point matching method mentioned in [5][6] as a part of their evaluation of matching....
[...]
References
More filters
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.
Abstract: 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.
46,906 citations
20 Sep 1999
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.
Abstract: 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.
16,989 citations
01 Jan 1988
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.
Abstract: The problem we 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. For example, we desire to obtain an understanding of natural scenes, containing roads, buildings, trees, bushes, etc., as typified by the two frames from a sequence illustrated in Figure 1. The solution to this problem that we are pursuing is to use a computer vision system based upon motion analysis of a monocular image sequence from a mobile camera. By extraction and tracking of image features, representations of the 3D analogues of these features can be constructed.
13,993 citations
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.
Abstract: In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
7,057 citations
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.
3,422 citations