Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by
Explore this paper's citation graph
Summary
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.
- Type
- article
- Published
- 2011-01-01
- Cited by
- 11,835
- References
- 23
- OpenAlex
- https://openalex.org/W2184229386
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:130535382
Keywords
Scale-invariant feature transform, Artificial intelligence, Computer vision, Invariant (physics), Scale invariance
References
- Complex cells and Object Recognition
- Geometry from visual motion
- Probabilistic Models of Appearance for 3-D Object Recognition
- A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry
- Invariant Features from Interest Point Groups
- The structure of images
- Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention
- Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales
- Shape recognition with edge-based features
- Recognition without Correspondence using Multidimensional Receptive Field Histograms
- Large-scale tests of a keyed, appearance-based 3-D object recognition system.
- A Combined Corner and Edge Detector
- Local Grayvalue Invariants for Image Retrieval
- Object recognition from local scale-invariant features
- Robust wide-baseline stereo from maximally stable extremal regions
- Distinctive Image Features from Scale-Invariant Keypoints
- Notes on the OpenSURF Library
- A comparison of SIFT, PCA-SIFT and SURF
- Phase-Based Local Features
- A Comparison of SIFT, PCA-SIFT and SURF
Cited by
- Real-time Road Scene Classification using Infrared Images
- Detecting Multilingual Lines of Text with Fusion Moves
- Towards Automated Crop Yield Estimation - Detection and 3D Reconstruction of Pineapples in Video Sequences
- Real-Time Scale Invariant Object Recognition Using an Artificial Neural Network
- Retrieval of 3D medical images via their texture features
- Experimental Comparison of Wide Baseline Correspondence Algorithms for Multi Camera Calibration
- Reconhecimento Automático de Calorias numa Refeição
- Developing a person guidance module for hospital robots
- Edge cross-section profile for colonoscopic object detection
- Système de vision hybride à fovéation pour la vidéo-surveillance et la navigation robotique
- A hybrid method for indoor user localisation
- Hybrid human-machine vision systems: image annotation using crowds, experts and machines
- Functional Principal Component Analysis and Randomized Sparse Clustering Algorithm for Medical Image Analysis
- Robust Visual Robot Localization Across Seasons Using Network Flows
- Real-time geometry-aware augmented reality in minimally invasive surgery
- Development of a topographical imaging device for the near-planar surfaces of paintings
- Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian
- Motion estimation of planar curves and their alignment using visual servoing
- Image Representations for Ranking and Classification. (Représentations d'images pour la recherche et la classification d'images)
- Internal visuomotor models for cognitive simulation processes
Related papers
- Research on target feature detecting and extracting technologies based on SIFT algorithm
- Efficient heterogeneous face recognition using Scale Invariant Feature Transform
- Improved SIFT-Features Matching for Object Recognition
- Local Feature based Descriptors and their Applications
- Performance Evaluation of Scale Invariant Feature Transform
- Selection of distinctive sift feature based on its distribution on feature space and local classifier for face recognition