一、圖像閾值
ret, dst = cv2.threshold(src, thresh, maxval, type)
- src: 輸入圖,只能輸入單通道圖像,通常來說爲灰度圖
- dst: 輸出圖
- thresh: 閾值
- maxval: 當像素值超過了閾值(或者小於閾值,根據type來決定),所賦予的值
- type:二值化操作的類型,包含以下5種類型: cv2.THRESH_BINARY; cv2.THRESH_BINARY_INV; cv2.THRESH_TRUNC; cv2.THRESH_TOZERO;cv2.THRESH_TOZERO_INV
- cv2.THRESH_BINARY 超過閾值部分取maxval(最大值),否則取0
- cv2.THRESH_BINARY_INV THRESH_BINARY的反轉
- cv2.THRESH_TRUNC 大於閾值部分設爲閾值,否則不變
- cv2.THRESH_TOZERO 大於閾值部分不改變,否則設爲0
- cv2.THRESH_TOZERO_INV THRESH_TOZERO的反轉
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2019/12/31 14:03
# @Author : King110108
# @File : threshold_filter.py
# @Description:
# @IDE : PyCharm
import cv2 #opencv讀取的格式是BGR
import matplotlib.pyplot as plt #Matplotlib是RGB
import numpy as np
#顯示一張圖片,第一個參數是窗口名字,第二個參數是要顯示的圖片
def cv_show(name,img):
cv2.imshow(name,img)
cv2.waitKey(0)
cv2.destroyAllWindows()
#灰度處理
img=cv2.imread('jay1.jpg')
img_gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
print(img_gray.shape)
ret, thresh1 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY)
ret, thresh2 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY_INV)
ret, thresh3 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TRUNC)
ret, thresh4 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO)
ret, thresh5 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO_INV)
titles = ['Original Image', 'BINARY', 'BINARY_INV', 'TRUNC', 'TOZERO', 'TOZERO_INV']
images = [img, thresh1, thresh2, thresh3, thresh4, thresh5]
for i in range(6):
plt.subplot(2, 3, i + 1), plt.imshow(images[i], 'gray')
plt.title(titles[i])
plt.xticks([]), plt.yticks([])
plt.show()
二、圖像平滑處理
圖片平滑處理即對圖片濾波降噪的過程。
均值濾波--簡單的平均卷積操作
blur = cv2.blur(img, (3, 3))
cv2.imshow('blur', blur)
cv2.waitKey(0)
cv2.destroyAllWindows()
方框濾波--基本和均值一樣,可以選擇歸一化,False越界會產生高亮圖
boxFilter= cv2.boxFilter(img,-1,(3,3), normalize=True)
cv2.imshow('boxFilter', boxFilter)
cv2.waitKey(0)
cv2.destroyAllWindows()
高斯濾波--高斯模糊的卷積核裏的數值是滿足高斯分佈,相當於更重視中間的
aussianBlur = cv2.GaussianBlur(img, (5, 5), 1)
cv2.imshow('aussianBlur ', aussianBlur )
cv2.waitKey(0)
cv2.destroyAllWindows()
中值濾波--相當於用中值代替
medianBlur= cv2.medianBlur(img, 5) # 中值濾波
cv2.imshow('medianBlur', medianBlur)
cv2.waitKey(0)
cv2.destroyAllWindows()