Proceedings ArticleDOI
Object recognition from local scale-invariant features
David G. Lowe
- Vol. 2, pp 1150-1157
TLDR
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.read more
Citations
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
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Distinctive Image Features from Scale-Invariant Keypoints
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.
Journal ArticleDOI
Deep learning in neural networks
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Book ChapterDOI
SURF: speeded up robust features
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
References
More filters
Journal ArticleDOI
Localizing Overlapping Parts by Searching the Interpretation Tree
TL;DR: The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on distances between faces, angles between face normals, and angles of vectors between sensed points.
Journal ArticleDOI
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus-of-attention
TL;DR: In this article, a multiscale representation of grey-level shape called the scale-space primal sketch is presented, which makes explicit both features in scale space and the relations between structures at different scales, and a methodology for extracting significant blob-like image structures from this representation.
Journal ArticleDOI
Size and position invariance of neuronal responses in monkey inferotemporal cortex
TL;DR: The size-specific responses observed in 43% of the cells are consistent with recent psychophysical data that suggest that images of objects are stored in a size- specific manner in the long-term memory, and both size-dependent and -independent processing of images may occur in anterior IT.
Journal ArticleDOI
A Representation for Shape Based on Peaks and Ridges in the Difference of Low-Pass Transform
James L. Crowley,Alice C. Parker +1 more
TL;DR: A multiple resolution representation for the two-dimensional gray-scale shapes in an image is defined by detecting peaks and ridges in the difference of lowpass (DOLP) transform and the principles for determining the correspondence between symbols in pairs of such descriptions are described.
Book ChapterDOI
Object Recognition Using Multidimensional Receptive Field Histograms
Bernt Schiele,James L. Crowley +1 more
TL;DR: The mathematical foundations of the technique are described and the results of experiments which compare robustness and recognition rates for different local neighborhood operators and histogram similarity measurements are presented.