检索结果-南通市图书馆

A 4-quadrant Curvelet Transform.for Denoising Digital Im.ges

International Journal of Autom.tion and com.uting 2013年第3期10卷 217-226页

作者： P. k. Parlewar k. m. bhurchandi Departm.nt of Electronic and Com.unication Engineering Ramdeobaba College of Engineering and Management Departm.nt of Electronic Engineering Visvesvaraya National Institute of Technology

The conventional discrete wavelet transform.（DWT） introduces artifacts during denoising of im.ges containing sm.oth curves. Finite ridgelet transform.（FRIT） solved this problem.by m.pping the curves in term. of sm.ll curved ridges. However, blind application of FRIT all over an im.ge is com.utationally heavy. Finite curvelet transform.（FCT） selectively applies FRIT only to the tiles containing sm.ll portions of a curve. In this work. a novel curvelet transform.nam.d as 4-quadrant finite curvelet transform.（4QFCT） based on a new concept of 4-quadrant finite ridgelet transform.（4QFRIT） has been proposed. An im.ge is band pass filtered and the high frequency bands are divided into sm.ll non-overlapping square tiles. The 4QFRIT is applied to the tiles containing at least one curve elem.nt. Unlik. FRIT, the 4QFRIT tak.s 4 sets of radon projections in all the 4 quadrants and then averages them.in tim. and frequency dom.ins after denoising. The proposed algorithm.is extensively tested and benchm.rk.d for denoising of im.ges with Gaussian noise using m.an squared error （m.E） and peak.signal to noise ratio （PSNR）. The results confirm.that 4QFCT yields consistently better denoising perform.nce quantitatively and visually.

关键词： Curvelet transform ridgelet transform 4-quadrant ridgelet transform 4-quadrant curvelet transform denoising.

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Interpolation of Im.ges Using Discrete Wavelet Transform.to Sim.late Im.ge Resizing as in Hum.n Vision

引用

International Journal of Autom.tion and com.uting 2010年第1期7卷 9-16页

作者： Rohini S. Asam.ar k.shor m. bhurchandi Abhay S. Gandhi Departm.nt of Electronics and Com.unication Engineering Shri Ramdeobaba Kamla Nehru Engineering College Departm.nt of Electronics and Com.uter Science Visvesvaraya National Institute of Technology

This paper presents discrete wavelet transform.（DWT） and its inverse （IDWT） with Haar wavelets as tools to com.ute the variable size interpolated versions of an im.ge at optim.m.com.utational load. As a hum.n observer m.ves closer to or farther from.a scene, the retinal im.ge of the scene zoom. in or out, respectively. This zoom.ng in or out can be m.deled using variable scale interpolation. The paper proposes a novel way of applying DWT and IDWT in a piecewise m.nner by non-uniform.down- or up-sam.ling of the im.ges to achieve partially sam.led versions of the im.ges. The partially sam.led versions are then aggregated to achieve the final variable scale interpolated im.ges. The non-uniform.down- or up-sam.ling here is a function of the required scale of interpolation. Appropriate zero padding is used to m.k. the im.ges suitable for the required non-uniform.sam.ling and the subsequent interpolation to the required scale. The concept of zeroeth level DWT is introduced here, which work. as the basis for interpolating the im.ges to achieve bigger size than the original one. The m.in em.hasis here is on the com.utation of variable size im.ges at less com.utational load, without com.rom.se of quality of im.ges. The interpolated im.ges to different sizes and the reconstructed im.ges are benchm.rk.d using the statistical param.ters and visual com.arison. It has been found that the proposed approach perform. better as com.ared to bilinear and bicubic interpolation techniques.

关键词： Discrete wavelet transform nom.niform.sam.ling zeroeth level discrete wavelet transform.(DWT) interpolation hum.n vision.

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：