<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[lzmsxf的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/lzmsxf</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; lzmsxf]]></copyright><item><title><![CDATA[非均匀性校正——随机数法]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/125999781</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/125999781</guid><author>lzmsxf</author><pubDate>Tue, 26 Jul 2022 17:39:46 +0800</pubDate><description><![CDATA[非均匀性、固定模式噪声、随机数]]></description><category></category></item><item><title><![CDATA[非均匀性校正——神经网络法]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/125999021</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/125999021</guid><author>lzmsxf</author><pubDate>Tue, 26 Jul 2022 17:31:35 +0800</pubDate><description><![CDATA[非均匀性、固定模式噪声、神经网络法]]></description><category></category></item><item><title><![CDATA[毫无意义的非均匀性校正----2研究现状]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/125879256</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/125879256</guid><author>lzmsxf</author><pubDate>Sun, 24 Jul 2022 10:15:21 +0800</pubDate><description><![CDATA[非均匀性、固定模式噪声、基于定标、基于场景]]></description><category></category></item><item><title><![CDATA[毫无意义的非均匀性校正-----非均匀性定义、特性、来源]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/125873602</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/125873602</guid><author>lzmsxf</author><pubDate>Sun, 24 Jul 2022 09:54:36 +0800</pubDate><description><![CDATA[非均匀性校正、固定模式噪声]]></description><category></category></item><item><title><![CDATA[毫无意义的非均匀性校正----目录]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/125874034</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/125874034</guid><author>lzmsxf</author><pubDate>Sun, 24 Jul 2022 09:46:15 +0800</pubDate><description><![CDATA[非均匀性校正]]></description><category></category></item><item><title><![CDATA[机器学习西瓜书自学(不定期更新)]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/118355593</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/118355593</guid><author>lzmsxf</author><pubDate>Wed, 30 Jun 2021 10:23:19 +0800</pubDate><description><![CDATA[一直在学深度学习，但尴尬的是对机器学习并不了解，因而参考西瓜书对机器学习做一个简单的整理(时间有限，部分内容个人觉得不重要，或学过，或后期可以再学，因而不做学习，也不总结上去)
基础知识
一：基础概念
NP问题：非确定性多项式难题：不能确定得到的多项式是否能真正解决问题
1.特征(feature)、 潜在的规律/真相(ground truth)、
2.二分类中：正反类(postive 、negative class)、
3.监督学习(supervised learning):分类和回归 、 无监督学习(un]]></description><category></category></item><item><title><![CDATA[python+opencv学习day03]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/118089693</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/118089693</guid><author>lzmsxf</author><pubDate>Mon, 21 Jun 2021 16:59:46 +0800</pubDate><description><![CDATA[链接：https://www.bilibili.com/video/BV1RQ4y1R7M6?p=51
import cv2 as cv
import numpy as np

1.角点检测
"""
图像特征-harris(角点检测)
角点：水平和竖直的位置灰度值迅速变化,方形的四个角
基本原理：判断位移(dx,dy)后的自相似性
c = w（I-I’）^2，w为窗口，一般为高斯加权函数，一步步简化
"""
import cv2 as cv
import numpy as np
"""
cv2.corner]]></description><category></category></item><item><title><![CDATA[opencv+python学习day02: 信用卡数字识别]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/117672724</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/117672724</guid><author>lzmsxf</author><pubDate>Mon, 07 Jun 2021 19:41:07 +0800</pubDate><description><![CDATA[跟着b站教程学习p36-p40：
https://www.bilibili.com/video/BV1RQ4y1R7M6?p=40
感觉意义不大，一般用不到这些东西。
抄的视频内容，本来不该写原创，但是不想联系作者，而且链接不知该怎么放，联系侵权自删
import
import imutils
import argparse
import cv2 as cv
import myutils
import numpy as np

能import的代码绝不自己写
下载的myutils中没有conunders，所]]></description><category></category></item><item><title><![CDATA[opencv+python学习day02]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/117652363</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/117652363</guid><author>lzmsxf</author><pubDate>Mon, 07 Jun 2021 15:31:38 +0800</pubDate><description><![CDATA[import cv2 as cv
from numpy import shape

1.上下采样
up = cv.pyrUp(src)
down = cv.pyrDown(src)
"""
下采样：偶数行和列像素点去除pyrDown
上采样：每个像素点扩充，扩充点0填充pyrUp
"""

2.LP金字塔
down = cv.pyrDown(src)
down_up = cv.pyrUp(down)
LP = src - down_up  # LP金字塔一层模型
"""
up-down 的效果明显比down]]></description><category></category></item><item><title><![CDATA[python+opencv学习day01]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/117599289</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/117599289</guid><author>lzmsxf</author><pubDate>Sat, 05 Jun 2021 18:50:07 +0800</pubDate><description><![CDATA[跟着b站的教程学习链接：https://www.bilibili.com/video/BV1RQ4y1R7M6?p=6
内容基本按照教程走，进行了一些简单的注释和总结。
1.读取和处理
图片读取
src = cv.imread("D:/ALL_LEARN/picture/cat.jpg", cv.IMREAD_GRAYSCALE)  # opencv读取文件的路径不能有中文名
# src =img[0:50, 0:200]  # 截取图像中的一部分
b, g, r = cv.split(src)
# cv.]]></description><category></category></item><item><title><![CDATA[利用随机数生成一个不含重复元素的数组]]></title><link>https://blog.youkuaiyun.com/lzmsxf/article/details/117333335</link><guid>https://blog.youkuaiyun.com/lzmsxf/article/details/117333335</guid><author>lzmsxf</author><pubDate>Thu, 27 May 2021 17:18:14 +0800</pubDate><description><![CDATA[package InterviewQuestion;

import java.util.Random;

/**
 * 要求：
 * 1.生成五个随机数
 * 2.若重复，则重新生成五个随机数
 * 3.不重复时，输出为一个数组
 */
public class Random_Interview {
    public static void main(String[] args) {
        int[] arr =new int[5];
        do{ arr = ArrGenerat]]></description><category></category></item></channel></rss>