Shape extraction from gray-valued images by concept construction networks

通过概念构建网络从灰度图像中提取形状

• 批准号: 03452166
• 负责人: AGUI Takeshi
• 金额: $ 3.9万
• 依托单位: Tokyo Institute of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (B)
• 财政年份: 1991
• 资助国家: 日本
• 起止时间: 1991 至 1992
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-03452166/
• 关键词: Concept generation; Neural network; Feature extraction; Shape extraction; 概念形成; ニュ-ラルネットワ-ク

The purpose of this research is to make a neural network system which can extract various two dimensional and three dimensional objects from gray-valued images. This research consists of following three steps;1.to develop pattern recognition methods for extraction of 2D and 3D objects from block and white images. In this step, rather simple shapes such as straight lines, circles and characters are considered.2.to develop neural networks which can extract complex 2D and 3D objects from gray- valued images by the use of the result obtained in the first step. For example, face regions are extracted from monochromatic photographs.3.to make a shape extraction neural network system which can extract various kind of 2D and 3D objects from images.This research can be applied to recognition and understanding of images in the field of computer vision.

本研究的目的是建立一个能够从灰度图像中提取各种二维和三维目标的神经网络系统。本研究包括以下三个步骤：1.发展从块状图像和白色图像中提取2D和3D对象的模式识别方法。在这一步中，考虑了直线、圆和字符等较为简单的形状。2.利用第一步得到的结果，开发了能够从灰度值图像中提取复杂2D和3D目标的神经网络。例如，从单色照片中提取人脸区域。3.制作了一个形状提取神经网络系统，该系统可以从图像中提取各种2D和3D对象，该研究可以应用于计算机视觉领域的图像识别和理解。

项目成果

Tomoharu NAGAO: "Automatic construction of image transformation processes using feature selection network" the proceeding of the first KOREAーJAPAN joint conference on Computer Vision. 1. 119-125 (1991)

Tomoharu NAGAO：“使用特征选择网络自动构建图像转换过程”，第一届韩国-日本计算机视觉联合会议的记录。1. 119-125 (1991)。

Hiroshi NAGAHASHI: "Knowledge representation on an object oriented image processing system" the proceeding of the first KOREAーJAPAN joint Conference on Computer Vision. 1. 396-402 (1991)

Hiroshi NAGAHASHI：“面向对象的图像处理系统的知识表示”第一届韩国-日本计算机视觉联合会议记录。1. 396-402 (1991)。

Takeshi Agui, Kenichi Ide: "Automatic extraction and removing of linear objects in pictures" Bulletin of the Japanese Society of Printing Science and Technology. 29,5. 474-479 (1992)

Takeshi Agui、Kenichi Ide：“自动提取和删除图片中的线性对象”日本印刷科学技术学会通报。

Tomoharu Nagao, Takeshi Agui, Hiroshi Nagahashi: "Structural evolution of neural networks by a genetic method" the Trans. of the IECICE. J75-D-II,9. 1634-1637

Tomoharu Nagao、Takeshi Agui、Hiroshi Nagahashi：“通过遗传方法进行神经网络的结构进化”Trans。

Shinichi Suzuki, Takeshi Agui, Tomoharu Nagao: "An inspection method for printed matters using a neural network" Bulletin of the Japanese Society of Printing Science and Technology. 29,5. 488-496 (1992)

Shinichi Suzuki、Takeshi Agui、Tomoharu Nagao：“使用神经网络的印刷品检查方法”日本印刷科学技术学会会刊。