已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Scale-space theory: a basic tool for analyzing structures at different scales

缩放空间 平滑的 代表(政治) 比例(比率) 计算机科学 特征(语言学) 核(代数) 计算 空格(标点符号) 公理 财产(哲学) 算法 高斯分布 多样性(控制论) 模式识别(心理学) 人工智能 理论计算机科学 数学 图像处理 计算机视觉 图像(数学) 几何学 纯数学 哲学 物理 操作系统 认识论 法学 政治 量子力学 语言学 政治学
作者
Tony Lindeberg
出处
期刊:Journal of Applied Statistics [Taylor & Francis]
卷期号:21 (1-2): 225-270 被引量:1451
标识
DOI:10.1080/757582976
摘要

An inherent property of objects in the world is that they only exist as meaningful entities over certain ranges of scale. If one aims to describe the structure of unknown real-world signals, then a multi-scale representation of data is of crucial importance. This paper gives a tutorial review of a special type of multi-scale representation—linear scale-space representation—which has been developed by the computer vision community to handle image structures at different scales in a consistent manner. The basic idea is to embed the original signal into a one-parameter family of gradually smoothed signals in which the fine-scale details are successively suppressed. Under rather general conditions on the type of computations that are to be performed at the first stages of visual processing, in what can be termed ‘the visual front-end’, it can be shown that the Gaussian kernel and its derivatives are singled out as the only possible smoothing kernels. The conditions that specify the Gaussian kernel are, basically, linearity and shift invariance, combined with different ways of formalizing the notion that structures at coarse scales should correspond to simplifications of corresponding structures at fine scales-they should not be accidental phenomena created by the smoothing method. Notably, several different ways of choosing scale-space axioms give rise to the same conclusion. The output from the scale-space representation can be used for a variety of early visual tasks; operations such as feature detection, feature classification and shape computation can be expressed directly in terms of (possibly non-linear) combinations of Gaussian derivatives at multiple scales. In this sense the scale-space representation canserve as a basis for early vision. During the last few decades, a number of other approaches to multiscale representations have been developed, which are more or less related to scale-space theory, notably the theories of pyramids, wavelets and multi grid methods.Despite their qualitative differences, the increasing propularity of each of these approaches indicates that the crucial notion of scale is increasingly appreciated by the computer.vision community and by researchers in other related fields. An interesting similarity to biological vision is that the scale-space operators closely resemble receptive field profiles registered in neurophysiological studies of the mam- malian retina and visual cortex.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
朴素雪碧完成签到,获得积分10
刚刚
zzz完成签到 ,获得积分10
1秒前
妞妞完成签到 ,获得积分10
1秒前
科研通AI6.2的应助被Panda采纳,获得10
2秒前
2秒前
2秒前
红细胞发布了新的文献求助10
3秒前
乐乐的应助被光风霁月采纳,获得10
3秒前
Docsiwen发布了新的文献求助10
4秒前
高挑的小虾米完成签到,获得积分10
5秒前
6秒前
笨笨摇伽完成签到,获得积分10
6秒前
6秒前
6秒前
6秒前
dcx完成签到,获得积分10
6秒前
molihuakai的应助被长情靖雁采纳,获得10
6秒前
自信夏寒完成签到,获得积分10
6秒前
NexusExplorer的应助被长情靖雁采纳,获得10
6秒前
7秒前
bkagyin的应助被年轻的寻桃采纳,获得10
7秒前
Rina发布了新的文献求助10
7秒前
jing完成签到,获得积分10
8秒前
8秒前
伶俐一曲完成签到,获得积分10
8秒前
科研通AI65的应助被Qiao采纳,获得10
9秒前
鹰隼游发布了新的文献求助10
9秒前
闪闪翼发布了新的文献求助10
9秒前
LL发布了新的文献求助10
11秒前
NexusExplorer的应助被Rina采纳,获得30
11秒前
11秒前
林场发布了新的文献求助20
11秒前
sci发布了新的文献求助30
12秒前
12秒前
12秒前
12秒前
betterlouse发布了新的文献求助10
12秒前
13秒前
寤念发布了新的文献求助10
13秒前
橘子完成签到 ,获得积分10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8194529
求助须知:如何正确求助?哪些是违规求助? 9580304
关于积分的说明 21870538
捐赠科研通 7794101
什么是DOI,文献DOI怎么找? 3437711
关于科研通互助平台的介绍 2560986
邀请新用户注册赠送积分活动 2484393