一、 實驗內(nèi)容
要求編寫一個包含顏色算子，Susan，Harris，角點，sobel邊緣算子的程。
二、 顏色算子實驗
2.1、 提取紅色
- 實驗的程序如下
import numpy as np
import cv2 as cv
image = cv.imread("1.jpg")
image = image / np.ones([1, 1, 3]).astype(np.float32)
image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
print(image.shape)
# 顏色算子
# red
redAdd = np.ones([1, 1, 3]).astype(np.float32)
redAdd[0, 0, 0] = 1.0
redAdd[0, 0, 1] = 0.5
redAdd[0, 0, 2] = 0.25
redSub = np.ones([1, 1, 3]).astype(np.float32)
redSub[0, 0, 0] = 0.25
redSub[0, 0, 1] = 0.5
redSub[0, 0, 2] = 1.0
image1 = np.mean(image * redAdd, 2)
image2 = np.mean(image * redSub, 2) + 100
imageRed = image1 / image2
redMax = np.max(imageRed)
redMin = np.min(imageRed)
imageRed = 255 * (imageRed - redMin) / (redMax - redMin)
cv.imwrite("1red.png", imageRed)
運行結(jié)果如下
- 實驗原圖
- 實驗結(jié)果圖
2.2、 提取綠色
實驗的程序如下
import numpy as np
import cv2 as cv
image = cv.imread("1.jpg")
image = image / np.ones([1, 1, 3]).astype(np.float32)
image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
print(image.shape)
# green
greenAdd = np.ones([1, 1, 3]).astype(np.float32)
greenAdd[0, 0, 0] = 0.5
greenAdd[0, 0, 1] = 1.0
greenAdd[0, 0, 2] = 0.25
greenSub = np.ones([1, 1, 3]).astype(np.float32)
greenSub[0, 0, 0] = 0.5
greenSub[0, 0, 1] = 0.25
greenSub[0, 0, 2] = 1.0
image1 = np.mean(image * greenAdd, 2)
image2 = np.mean(image * greenSub, 2) + 100
imageGreen = image1 / image2
greenMax = np.max(imageGreen)
greenMin = np.min(imageGreen)
imageRed = 255 * (imageGreen - greenMin) / (greenMax - greenMin)
cv.imwrite("1green.png", imageRed)
運行結(jié)果如下
-
實驗原圖
-
實驗結(jié)果圖
2.3、 提取藍(lán)色
- 實驗的程序如下
import numpy as np
import cv2 as cv
image = cv.imread("1.jpg")
image = image / np.ones([1, 1, 3]).astype(np.float32)
image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
print(image.shape)
# bule
buleAdd = np.ones([1, 1, 3]).astype(np.float32)
buleAdd[0, 0, 0] = 0.25
buleAdd[0, 0, 1] = 0.5
buleAdd[0, 0, 2] = 1.0
buleSub = np.ones([1, 1, 3]).astype(np.float32)
buleSub[0, 0, 0] = 1.0
buleSub[0, 0, 1] = 0.5
buleSub[0, 0, 2] = 0.25
image1 = np.mean(image * buleAdd, 2)
image2 = np.mean(image * buleSub, 2) + 100
imageBlue = image1 / image2
blueMax = np.max(imageBlue)
blueMin = np.min(imageBlue)
imageBlue = 255 * (imageBlue - blueMin) / (blueMax - blueMin)
cv.imwrite("1blue.png", imageBlue)
運行結(jié)果如下
-
實驗原圖
-
實驗結(jié)果圖
三、 Susan、Harris角點檢測實驗
3. 1、 實驗程序
3.1.1、Susan角點檢測
Susan角點檢測程序如下
import numpy as np
import cv2 as cv
image = cv.imread("2.jpg")
image = np.mean(image, 2)
height = image.shape[0]
width = image.shape[1]
print(image.shape)
#susan 算子
radius = 5
imageSusan = np.zeros([height, width]).astype(np.float32)
for h in range(radius, height-radius):
for w in range(radius, width-radius):
numSmall = 0
numLarge = 0
numAll = 0
for y in range(-radius, radius + 1):
for x in range(-radius, radius+1):
distance = np.sqrt(y**2 + x**2)
if distance <= radius:
numAll += 1
if image[h + y, w + x] < image[h, w] - 27:
numSmall += 1
if image[h + y, w + x] > image[h, w] + 27:
numLarge += 1
ratio = 1.0 * numSmall / numAll
ratio2 = 1.0 * numLarge / numAll
if ratio < 0.3:
imageSusan[h, w] = 0.3 - ratio
if ratio2 > 0.7:
imageSusan[h, w] = ratio2 - 0.7
imageMax = np.max(imageSusan)
imageMin = np.min(imageSusan)
imageSusan = 255*(imageSusan - imageMin)/(imageMax - imageMin)
print(imageSusan.shape)
cv.imwrite("2.png", imageSusan)
- 運行結(jié)果如下
-
實驗原圖
-
實驗結(jié)果圖
3.1.2、Harris角點檢測
- Harris角點檢測程序如下
import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt
# 讀取圖像
img = cv.imread('3.jpg')
lenna_img = cv.cvtColor(img, cv.COLOR_BGR2RGB)
# 圖像轉(zhuǎn)換成灰度圖像
grayImage = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
grayImage = np.float32(grayImage)
# Harris算子
harrisImage = cv.cornerHarris(grayImage, 2, 3, 0.04)
harrisImage = cv.dilate(harrisImage, None)
# 設(shè)置閾值
thresImage = 0.006 * harrisImage.max()
img[harrisImage > thresImage] = [255, 0, 0]
# 顯示正常中文的標(biāo)簽
plt.rcParams['font.sans-serif'] = ['SimHei']
titles = [u'(a)原始圖像', u'(b)Harris圖像']
images = [lenna_img, img]
for i in range(2):
plt.subplot(1, 2, i + 1), plt.imshow(images[i], 'gray')
plt.title(titles[i])
plt.xticks([]), plt.yticks([])
plt.show()
運行結(jié)果如下
四、 sobel邊緣算子檢測實驗
4.1、sobel邊緣算子檢
- sobel邊緣算子檢程序如下
import numpy as np
import cv2
image = cv2.imread("3.jpg")
height = image.shape[0]
width = image.shape[1]
sobelResult = np.zeros([height - 2, width - 2, 1]).astype(np.float32)
sobelX = np.zeros([3, 3, 1]).astype(np.float32)
sobelY = np.zeros([3, 3, 1]).astype(np.float32)
sobelX[0, 0, 0] = -1
sobelX[1, 0, 0] = -2
sobelX[2, 0, 0] = -1
sobelX[0, 2, 0] = 1
sobelX[1, 2, 0] = 2
sobelX[2, 2, 0] = 1
sobelY[0, 0, 0] = -1
sobelY[0, 1, 0] = -2
sobelY[0, 2, 0] = -1
sobelY[2, 0, 0] = 1
sobelY[2, 1, 0] = 2
sobelY[2, 2, 0] = 1
for h in range(0, height - 3):
for w in range(0, width - 3):
#求方向梯度
imageIncre = image[h:h + 3, w:w + 3]
gradientX = np.sum(imageIncre * sobelX)
gradientY = np.sum(imageIncre * sobelY)
gradient = np.sqrt(gradientX**2 + gradientY**2)
sobelResult[h, w, 0] = gradient
imageMax = np.max(sobelResult)
imageMin = np.min(sobelResult)
sobelResult = 255*(sobelResult - imageMin) / (imageMax - imageMin)
cv2.imwrite("3.png", sobelResult)
2、 運行結(jié)果如下
-
實驗原圖
文章來源：http://www.zghlxwxcb.cn/news/detail-786616.html -
實驗結(jié)果圖
文章來源地址http://www.zghlxwxcb.cn/news/detail-786616.html
五、 實驗總結(jié)
- 1、 掌握了編寫含顏色算子圖像處理、Susan與Harris角點圖像檢測、sobel邊緣算子圖像檢測的程序編寫方法。
- 2、 通過實驗、對于邊緣檢測算子與角點檢測算子有了進(jìn)一步的掌握。
到了這里，關(guān)于模式識別與圖像處理課程實驗一：圖像處理實驗(顏色算子實驗、Susan、Harris角點檢測實驗、 sobel邊緣算子檢測實驗)的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
