本文分别从提高红外图像对比度、抑制噪声、增强红外图像彩色对比度这三
个角度研究了红外弱小目标图像的增强方法。文章介绍了红外图像增强的基本概
念和图像增强的效果评价，究了红外图像的成像机理和特点。首先分析了红外弱小目标图像噪声成因和目标成像特点，在抑制噪声方面重点分析比较了平滑滤波和中值滤波的优缺点，然后分析和研究了常用的基于直方图的方法、灰度变换、空间滤波以及基于数学形态学的弱小目标图像增强算法。最后本文研究了红外弱小目标图像的伪彩色增强，实验结果表明增强后的图像改善了视觉效果，提高了对比度。
2022-12-12 19:28:40
4.71MB
1
一个非常经典的密码学验证工具。虽然比较旧，但仍然很有用。几乎可以验证现代密码学中所有的密码学方案，如古典密码、公钥密码、对称密码等。此外还有一些小工具。
2022-12-12 14:00:50
5.15MB
1
The Python code and supporting material, including example data files, are
available as a single ZIP compressed archive. This must be uncompressed before
use and will extract into a folder (directory) called "PythonForBiology", inside
which the Python files, ending in ".py", and various sub-folders can be found.
This arrangement of files and folders will allow the Python code to run directly
from inside the uncompressed "PythonForBiology", i.e. the locations of any
modules or data files mentioned in the code (and book) are specified relative to
this location.
The "examples" sub-folder contains all of the data files that are used as
examples to support the Python code described in the book.
The "databases" sub-folder relates to Chapter 20 and contains SQL and Python
files sub-divided into sections to support both SQLite and MySQL database
implementations.
The "speedy" folder relates to Chapter 27 and contains code relevant to the
binding of fast functions written in the C or Cython languages, including any
files required for compilation.
Many of the book chapters have a corresponding Python file containing the
completed scripts and programs for that chapter. These files may be run directly
as Python to test the code they contain. Note that several of these files will
not work isolation, given that they import functionality from the others, which
are assumed to be in the same folder.
Chapters 1-4 and 10 do not have a corresponding Python file given that they only
discuss the code in terms of short or incomplete fragments.
2022-12-11 21:14:25
7.85MB
1
边做边学！PyTorch开发深度学习
支持库。
1.本文档中处理的任务内容和深度学习模型
第1章图像分类和迁移学习（VGG）
第2章对象识别（SSD）
第3章语义分割（PSPNet）
第4章姿势估计（OpenPose）
第5章GAN的图像生成（DCGAN，自我注意GAN）
第6章GAN异常检测（AnoGAN，Efficient GAN）
第7章通过自然语言处理（变压器）进行情感分析
第8章通过自然语言处理（BERT）进行情感分析
第9章视频分类（3DCNN，ECO）
本手册的详细内容在下面分别说明。
2.问题/更正由问题管理
问题和更正在此GitHub问题中进行管理。
如有任何疑问，请单击此处。
3.关于印刷错误
单击此处以获取本书中的印刷错误列表。我很抱歉。
2022-12-10 22:02:12
5.29MB
1