AI Chat

Resolving Implementation Ambiguity and Improving SURF

02/02/2012

∙

by Peter Abeles, et al.

∙

∙

Speeded Up Robust Features (SURF) has emerged as one of the more popular feature descriptors and detectors in recent years. Performance and algorithmic details vary widely between implementations due to SURF's complexity and ambiguities found in its description. To resolve these ambiguities, a set of general techniques for feature stability is defined based on the smoothness rule. Additional improvements to SURF are proposed for speed and stability. To illustrate the importance of these implementation details, a performance study of popular SURF implementations is done. By utilizing all the suggested improvements, it is possible to create a SURF implementation that is several times faster and more stable.

page 3

page 5

∙ 08/03/2021

Fast Estimation Method for the Stability of Ensemble Feature Selectors

It is preferred that feature selectors be stable for better interpretabi...

0 Rina Onda, et al. ∙

∙ 02/21/2011

SHREC 2011: robust feature detection and description benchmark

Feature-based approaches have recently become very popular in computer v...

0 E. Boyer, et al. ∙

∙ 11/04/2021

Optimised Playout Implementations for the Ludii General Game System

This paper describes three different optimised implementations of playou...

0 Dennis J. N. J. Soemers, et al. ∙

∙ 12/08/2020

Performance Analysis of Keypoint Detectors and Binary Descriptors Under Varying Degrees of Photometric and Geometric Transformations

Detecting image correspondences by feature matching forms the basis of n...

0 Shuvo Kumar Paul, et al. ∙

∙ 04/30/2019

FastContext: an efficient and scalable implementation of the ConText algorithm

Objective: To develop and evaluate FastContext, an efficient, scalable i...

0 Jianlin Shi, et al. ∙

∙ 03/31/2021

Identifying Co-Adaptation of Algorithmic and Implementational Innovations in Deep Reinforcement Learning: A Taxonomy and Case Study of Inference-based Algorithms

Recently many algorithms were devised for reinforcement learning (RL) wi...

7 Hiroki Furuta, et al. ∙

∙ 02/12/2020

Eigenvector Component Calculation Speedup over NumPy for High-Performance Computing

Applications related to artificial intelligence, machine learning, and s...

0 Shrey Dabhi, et al. ∙