Development of advanced evolutionary computation methods for complex structure and their applications to motion picture processing
复杂结构先进进化计算方法的发展及其在运动图像处理中的应用
基本信息
- 批准号:17300044
- 负责人:
- 金额:$ 4.54万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for Scientific Research (B)
- 财政年份:2005
- 资助国家:日本
- 起止时间:2005 至 2006
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
We studied to develop new evolutionary computation algorithms for complex structures including tree structures with several numerical parameters, network structures, graph structures and so on. Conventional evolutionary algorithms such as GA (Genetic Algorithm) and GP (Genetic Programming) cannot optimize such complex structures.We developed three kinds algorithms for them.First, we developed an algorithm named "GMA (Genetic Matrix Algorithm)" for optimization of tree structures with several numerical parameters and applied it to automatic construction of image processing methods.Second, we constructed GIN (Genetic Image Network) for optimization of network structures whose node is an image filter, and we showed that GIN can generate automatically complex image processing procedures.Third, we developed GRAPE (GRAph structured Program Evolution) for automatic programming. GRAPE can generate general programs based on machine learning of learning data. For instance, GRAPE can make sorting programs from examples of several original data and their correctly sorted data.We applied the above methods to automatic generation of image processing algorithms especially motion picture processing such as extraction of human and automobile regions form motion pictures. We can generate complex image processing algorithms very easily using the developed evolutionary algorithms. These methods can be applied to various kinds of fields.
本文研究了复杂结构的进化计算方法,包括多参数树结构、网络结构、图结构等,传统的进化算法如遗传算法、遗传算法等。(遗传算法)和GP遗传程序设计(Genetic Programming)无法对这样复杂的结构进行优化,为此我们开发了三种算法:我们开发了一种名为“GMA”的算法(遗传矩阵算法)”,并将其应用于图像处理方法的自动构建。我们构建了GIN(Genetic Image Network),并证明了GIN可以自动生成复杂的图像处理程序。第三,我们开发了GRAPE(GRAph结构化程序进化)用于自动编程。GRAPE可以基于学习数据的机器学习生成通用程序。例如,GRAPE可以根据几个原始数据及其正确排序后的数据的例子编写排序程序,我们将上述方法应用于图像处理算法的自动生成,特别是运动图像处理,如从运动图像中提取人体和汽车区域。我们可以生成复杂的图像处理算法非常容易地使用开发的进化算法。这些方法可以应用于各种领域。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Genetic Image Network (GIN): Automatically construction of image processing algorithm
遗传图像网络(GIN):自动构建图像处理算法
- DOI:
- 发表时间:2007
- 期刊:
- 影响因子:0
- 作者:Shinichi Shirakawa;Tomoharu Nagao
- 通讯作者:Tomoharu Nagao
Action Control of Autonomous Agents in Continuous Valued Space Using RFCN
使用 RFCN 连续值空间中自主代理的动作控制
- DOI:
- 发表时间:2007
- 期刊:
- 影响因子:0
- 作者:Shinichi Shirakawa;Tomoharu Nagao
- 通讯作者:Tomoharu Nagao
GPによる構造最適化とGAによる数値最適化を併用した画像処理自動生成法PT-ACTIT
PT-ACTIT,一种结合使用GP的结构优化和使用GA的数值优化的图像处理自动生成方法
- DOI:
- 发表时间:2005
- 期刊:
- 影响因子:0
- 作者:藤嶋 航;長尾智晴
- 通讯作者:長尾智晴
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
NAGAO Tomoharu其他文献
NAGAO Tomoharu的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('NAGAO Tomoharu', 18)}}的其他基金
A study on analysis and modeling of awake brain surgery
清醒脑手术分析与建模研究
- 批准号:
25540099 - 财政年份:2013
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Challenging Exploratory Research
A research on evolutionary automatic construction of image recognition procedure based on machine learning
基于机器学习的图像识别流程进化自动构建研究
- 批准号:
21300050 - 财政年份:2009
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
An evolutionary automatic programming method and its application to autonomous mobile robots
一种进化自动编程方法及其在自主移动机器人中的应用
- 批准号:
19300043 - 财政年份:2007
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
A research on optimization of cellular neural networks based on evolutionary computation
基于进化计算的细胞神经网络优化研究
- 批准号:
09680355 - 财政年份:1997
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
相似国自然基金
Scalable Learning and Optimization: High-dimensional Models and Online Decision-Making Strategies for Big Data Analysis
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:合作创新研究团队
供应链管理中的稳健型(Robust)策略分析和稳健型优化(Robust Optimization )方法研究
- 批准号:70601028
- 批准年份:2006
- 资助金额:7.0 万元
- 项目类别:青年科学基金项目
相似海外基金
Automatic optimization of deep learning models and reconstruction of training data for microscopic image processing
深度学习模型的自动优化和显微图像处理训练数据的重建
- 批准号:
22K12270 - 财政年份:2022
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Development and Optimization of Biomass Cleanliness Image Processing Algorithm
生物质清洁度图像处理算法开发与优化
- 批准号:
571121-2021 - 财政年份:2021
- 资助金额:
$ 4.54万 - 项目类别:
Applied Research and Development Grants - Level 2
Optimization-based hologram image processing framework
基于优化的全息图像处理框架
- 批准号:
19K20293 - 财政年份:2019
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Optimization of Image Processing Pipeline Algorithms for Digital Camera
数码相机图像处理流水线算法优化
- 批准号:
503277-2016 - 财政年份:2016
- 资助金额:
$ 4.54万 - 项目类别:
Experience Awards (previously Industrial Undergraduate Student Research Awards)
Low-level optimization of image processing algorithms for heterogeneous computing environments
异构计算环境下图像处理算法的底层优化
- 批准号:
481938-2015 - 财政年份:2015
- 资助金额:
$ 4.54万 - 项目类别:
Experience Awards (previously Industrial Undergraduate Student Research Awards)
Automatic Construction of Feature Extraction Process Based on Combinatorial Optimization of Image Processing Filters
基于图像处理滤波器组合优化的特征提取过程自动构建
- 批准号:
15K16029 - 财政年份:2015
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Young Scientists (B)
Stochastic Convex Optimization Algorithm for Image Processing and Transfer
用于图像处理和传输的随机凸优化算法
- 批准号:
15K06078 - 财政年份:2015
- 资助金额:
$ 4.54万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Collaborative Research: Proximity Algorithms for Optimization Problems Arising from Image Processing
协作研究:图像处理优化问题的邻近算法
- 批准号:
1115523 - 财政年份:2011
- 资助金额:
$ 4.54万 - 项目类别:
Continuing Grant
Collaborative Research: Proximity Algorithms for Optimization Problems Arising from Image Processing
协作研究:图像处理优化问题的邻近算法
- 批准号:
1115469 - 财政年份:2011
- 资助金额:
$ 4.54万 - 项目类别:
Continuing Grant
SBIR Phase I: Computer Generation and Optimization of Image Processing Functions
SBIR 第一阶段:图像处理功能的计算机生成和优化
- 批准号:
1013936 - 财政年份:2010
- 资助金额:
$ 4.54万 - 项目类别:
Standard Grant