[人工智能]计算机视觉：图片的边缘检测、映射和油画效果

1.图片的边缘检测

1.1 调用cv2 api方法

import cv2

img = cv2.imread(filename='../anqila21.jpg',flags=1)
imgInfo = img.shape
height = imgInfo[0]
width = imgInfo[1]
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)   # 灰度处理
imgG = cv2.GaussianBlur(gray,(3,3),0)   # 高斯滤波，第二个参数为模板大小
dst = cv2.Canny(imgG,50,50)
cv2.imshow('dst',dst)
cv2.waitKey(0)

1.2 算法实现

现在我们使用算法实现，并且把它的背景颜色改为白色，线条颜色改为黑色，为了让效果更加明了，换一张大一点的图片。

import cv2
import numpy as np
import math

# 算法实现
img = cv2.imread(filename='../../anqila.jpg',flags=1)
imgInfo = img.shape
height = imgInfo[0]
width = imgInfo[1]
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)   # 灰度处理
dst = np.zeros((height,width,1),np.uint8)
'''
sobel
[ 1  2  1       [ 1  0  -1
  0  0  0         2  0  -2
 -1 -2 -1]        1  0  -1]
'''
for i in range(height-2):
    for j in range(width-2):
        gy = gray[i,j]*1+gray[i,j+1]*2+gray[i,j+2]*1-gray[i+2,j]*1-gray[i+2,j+1]*2-gray[i+2,j+2]*1
        gx = gray[i,j]*1-gray[i,j+2]*1+gray[i+1,j]*2-gray[i+1,j+2]*2+gray[i+2,j]*1-gray[i+2,j+2]*1
        grad = math.sqrt(gx**2+gy**2)
        if grad >50:
            dst[i,j] = 0
        else:
            dst[i,j] = 255
cv2.imshow('dst',dst)
cv2.waitKey(0)

2. 图片的映射

import cv2
import numpy as np

img = cv2.imread(filename='../anqila21.jpg',flags=1)
imgInfo = img.shape
height = imgInfo[0]
width = imgInfo[1]
# b = b*1.5
# g = g*1.3
dst = np.zeros((height,width,3),np.uint8)
for i in range(height):
    for j in range(width):
        (b,g,r) = img[i,j]
        b = b*1.5
        g = g*1.3
        if b>255:
            b = 255
        if g>255:
            g = 255
        dst[i,j]=(b,g,r)
cv2.imshow('dst',dst)
cv2.waitKey(0)

是不是觉得有点像电影里面的效果了呢？

3. 图片的油画效果

import cv2
import numpy as np

img = cv2.imread(filename='../anqila21.jpg',flags=1)
imgInfo = img.shape
height = imgInfo[0]
width = imgInfo[1]
# gray
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)  # 转换成灰度图片
dst = np.zeros((height,width,3),np.uint8)
flag = 2    # 参数，这个参数越小，油画效果与真实图片比较逼真
for i in range(flag,height-flag):
    for j in range(flag,width-flag):

        array1 = np.zeros(8,np.uint8)  # 灰度等级

        for m in range(-1*flag,flag):
            for n in range(-1*flag,flag):
                p1 = int(gray[i+m,j+n]/32)  # p1 0~3
                array1[p1]+=1
        currentMax = array1[0]
        l = 0
        for k in range(1,8):
            if currentMax<array1[k]:
                currentMax = array1[k]
                l = k

        for m in range(-1 * flag, flag):
            for n in range(-1 * flag, flag):
                if (l * 32) <= gray[i + m, j + n] <= ((l + 1) * 32):
                    (b,g,r) = img[i+m,j+n]
                    dst[i,j] = (b,g,r)
cv2.imshow('dst',dst)
cv2.waitKey(0)