Rotation invariant fast features for large-scale recognition

Gabriel Takacs; Vijay Chandrasekhar; Sam S. Tsai; David Chen; Radek Grzeszczuk; Bernd Girod

doi:10.1117/12.945968

ScienceGate Book Chapters

JOURNAL ARTICLE

Rotation invariant fast features for large-scale recognition

Gabriel Takacs Vijay Chandrasekhar Sam S. Tsai David Chen Radek Grzeszczuk Bernd Girod

Year: 2012 Journal: Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE Vol: 8499 Pages: 84991D-84991D Publisher: SPIE

DOI: 10.1117/12.945968

Get Full-Text PDF Get Analytical Report

Abstract

We present an end-to-end feature description pipeline which uses a novel interest point detector and Rotation- Invariant Fast Feature (RIFF) descriptors. The proposed RIFF algorithm is 15× faster than SURF¹ while producing large-scale retrieval results that are comparable to SIFT.²Such high-speed features benefit a range of applications from Mobile Augmented Reality (MAR) to web-scale image retrieval and analysis.

Keywords:

Scale-invariant feature transform Invariant (physics) Computer science Image retrieval Artificial intelligence Computer vision Rotation (mathematics) Scale invariance Pipeline (software) Pattern recognition (psychology) Detector Feature extraction Algorithm Mathematics Image (mathematics)

Metrics

Cited By

0.83

FWCI (Field Weighted Citation Impact)

Refs

0.74

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Image and Video Retrieval Techniques

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Robotics and Sensor-Based Localization

Physical Sciences → Engineering → Aerospace Engineering

Image Retrieval and Classification Techniques

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Rotation invariant fast features for large-scale recognition

Abstract

Metrics

Citation History

Topics

Related Documents

Rotation-invariant fast features for large-scale recognition and real-time tracking

Fast Features Invariant to Rotation and Scale of Texture

Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features

Large-scale point cloud place recognition method based on attention mechanism and rotation invariant features

Scale- And Rotation-Invariant Pattern Recognition