Local Feature Detection Based on Image Block Discrete Scale Space

In the high-level operations of computer vision it is taken for granted that image features have been reliably detected. This paper addresses the problem of feature extraction by scale-space methods. There has been a strong development in scale-space theory and its applications to low-level vision in the last couple of years. Scale-space theory for continuous signals is on a firm theoretical basis. However, discrete scale-space theory is known to be quite tricky, particularly for low levels of scale-space smoothing. The paper is based on two key ideas: to investigate the stochastic properties of scale-space representations and to investigate the interplay between discrete and continuous images. These investigations are then used to predict the stochastic properties of sub-pixel feature detectors.The modeling of image acquisition, image interpolation and scale-space smoothing is discussed, with particular emphasis on the influence of random errors and the interplay between the discrete and continuous representations. In doing so, new results are given on the stochastic properties of discrete and continuous random fields. A new discrete scale-space theory is also developed. In practice this approach differs little from the traditional approach at coarser scales, but the new formulation is better suited for the stochastic analysis of sub-pixel feature detectors.The interpolated images can then be analysed independently of the position and spacing of the underlying discretisation grid. This leads to simpler analysis of sub-pixel feature detectors. The analysis is illustrated for edge detection and correlation. The stochastic model is validated both by simulations and by the analysis of real images.

Download Full-text

Local feature detection for digital surfaces

10.1117/12.251795 ◽

1996 ◽

Cited By ~ 3

Author(s):

Peter Veelaert

Keyword(s):

Feature Detection ◽

Local Feature

Download Full-text

A biologically inspired scale-space for illumination invariant feature detection

Measurement Science and Technology ◽

10.1088/0957-0233/24/7/074024 ◽

2013 ◽

Vol 24 (7) ◽

pp. 074024 ◽

Cited By ~ 23

Author(s):

Vasillios Vonikakis ◽

Dimitrios Chrysostomou ◽

Rigas Kouskouridas ◽

Antonios Gasteratos

Keyword(s):

Feature Detection ◽

Scale Space ◽

Biologically Inspired ◽

Illumination Invariant ◽

Invariant Feature

Download Full-text

An Improved Learning Framework for Covariant Local Feature Detection

Computer Vision – ACCV 2018 - Lecture Notes in Computer Science ◽

10.1007/978-3-030-20876-9_17 ◽

2019 ◽

pp. 262-276

Author(s):

Nehal Doiphode ◽

Rahul Mitra ◽

Shuaib Ahmed ◽

Arjun Jain

Keyword(s):

Feature Detection ◽

Local Feature ◽

Learning Framework ◽

Improved Learning

Download Full-text

α-shapes for local feature detection

Pattern Recognition ◽

10.1016/j.patcog.2015.08.016 ◽

2016 ◽

Vol 50 ◽

pp. 56-73 ◽

Cited By ~ 7

Author(s):

Christos Varytimidis ◽

Konstantinos Rapantzikos ◽

Yannis Avrithis ◽

Stefanos Kollias

Keyword(s):

Feature Detection ◽

Local Feature

Download Full-text

A Comparative Study of SIFT and its Variants

Measurement Science Review ◽

10.2478/msr-2013-0021 ◽

2013 ◽

Vol 13 (3) ◽

pp. 122-131 ◽

Cited By ~ 71

Author(s):

Jian Wu ◽

Zhiming Cui ◽

Victor S. Sheng ◽

Pengpeng Zhao ◽

Dongliang Su ◽

...

Keyword(s):

Machine Vision ◽

Comparative Study ◽

Image Retrieval ◽

Scale Space ◽

Local Feature ◽

Experimental Results ◽

Image Stitching ◽

Illumination Change ◽

Feature Description ◽

Scale Change

SIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved algorithms that have drawn a lot of attention are PCA-SIFT, GSIFT, CSIFT, SURF and ASIFT. In this paper, we first systematically analyze SIFT and its variants. Then, we evaluate their performance in different situations: scale change, rotation change, blur change, illumination change, and affine change. The experimental results show that each has its own advantages. SIFT and CSIFT perform the best under scale and rotation change. CSIFT improves SIFT under blur change and affine change, but not illumination change. GSIFT performs the best under blur change and illumination change. ASIFT performs the best under affine change. PCA-SIFT is always the second in different situations. SURF performs the worst in different situations, but runs the fastest.

Download Full-text