scikit-image圖像處理入門

skimage是純python語言實(shí)現(xiàn)的BSD許可開源圖像處理算法庫，主要的優(yōu)勢(shì)在于：

• 提供一套高質(zhì)量易用性強(qiáng)的圖像算法庫API

• 滿足研究人員與學(xué)生學(xué)習(xí)圖像處理算法的需要，算法API參數(shù)可調(diào)

• 滿足工業(yè)級(jí)應(yīng)用開發(fā)需求，有實(shí)際應(yīng)用價(jià)值

scikit-image主要模塊如下：

官方主頁

https://scikit-image.org/

安裝

pip?install?scikit-image

導(dǎo)入支持的模塊

from?skimage?import?data,?io,?filters,?feature,?segmentation
from?skimage?import?color,?exposure,?measure,?morphology,?draw
from?matplotlib?import?pyplot?as?plt
from?skimage?import?transform?as?tf

從data中獲取測(cè)試圖像與數(shù)據(jù)并顯示

image?=?data.chelsea()
io.imshow(image)
io.show()

這個(gè)是開源作者養(yǎng)的寵物貓

灰度轉(zhuǎn)換

gray?=?color.rgb2gray(image)
fig,?axes?=?plt.subplots(1,?2,?figsize=(8,?4))
ax?=?axes.ravel()

ax[0].imshow(image)
ax[0].set_title("Input?RGB")
ax[1].imshow(gray,?cmap=plt.cm.gray)
ax[1].set_title("gray")

fig.tight_layout()
plt.show()

通道分離操作

hsv_img?=?color.rgb2hsv(image)
hue_img?=?hsv_img[:,?:,?0]
value_img?=?hsv_img[:,?:,?2]

fig,?(ax0,?ax1,?ax2)?=?plt.subplots(ncols=3,?figsize=(8,?2))
ax0.imshow(image)
ax0.set_title("RGB?image")
ax0.axis('off')
ax1.imshow(hue_img,?cmap='hsv')
ax1.set_title("Hue?channel")
ax1.axis('off')
ax2.imshow(value_img)
ax2.set_title("Value?channel")
ax2.axis('off')

fig.tight_layout()
plt.show()

濾波操作

image?=?data.chelsea()
gray?=?color.rgb2gray(image)
blur?=?filters.gaussian(image,?15)
usm?=?filters.unsharp_mask(image,?3,?1.0)
sobel?=?filters.sobel(gray)
prewitt?=?filters.prewitt(gray)
eh?=?exposure.equalize_adapthist(gray)
lapl?=?filters.laplace(image,?3)
median?=?filters.median(gray)

圖像二值化處理

image?=?io.imread("D:/images/dice.jpg")
gray?=?color.rgb2gray(image)
ret?=?filters.threshold_otsu(gray)
print(ret)

輪廓發(fā)現(xiàn)

binary?=?gray?>?ret
ax[0].imshow(gray?>?ret,?cmap='gray')
ax[0].set_title("binary")
contours?=?measure.find_contours(binary,?0.8)
for?n,?contour?in?enumerate(contours):
?????????ax[1].plot(contour[:,?1],?contour[:,?0],?linewidth=2)
ax[1].set_title("contours")

Canny邊緣

image?=?io.imread("D:/images/master.jpg")
gray?=?color.rgb2gray(image)
edge?=?feature.canny(gray,?3)

骨架提取

image?=?data.horse()
gray?=?color.rgb2gray(image)
ret?=?filters.threshold_otsu(gray)
binary?=?gray?skele?=?morphology.skeletonize(binary)

harris角點(diǎn)檢測(cè)

image?=?io.imread("D:/images/home.jpg")
gray?=?color.rgb2gray(image)
coords?=?feature.corner_peaks(feature.corner_harris(gray),?min_distance=5)

BRIEF特征匹配

keypoints1?=?corner_peaks(corner_harris(img1),?min_distance=5)
keypoints2?=?corner_peaks(corner_harris(img2),?min_distance=5)
keypoints3?=?corner_peaks(corner_harris(img3),?min_distance=5)

extractor?=?BRIEF()
extractor.extract(img1,?keypoints1)
keypoints1?=?keypoints1[extractor.mask]
descriptors1?=?extractor.descriptors

extractor.extract(img2,?keypoints2)
keypoints2?=?keypoints2[extractor.mask]
descriptors2?=?extractor.descriptors

extractor.extract(img3,?keypoints3)
keypoints3?=?keypoints3[extractor.mask]
descriptors3?=?extractor.descriptors

matches12?=?match_descriptors(descriptors1,?descriptors2,?cross_check=True)
matches13?=?match_descriptors(descriptors1,?descriptors3,?cross_check=True)

上述同時(shí)顯示兩張圖像的相似代碼

fig,?axes?=?plt.subplots(1,?2,?figsize=(8,?4))
ax?=?axes.ravel()

ax[0].imshow(image)
ax[0].set_title("Input?RGB")
ax[1].imshow(gray?>?ret,?cmap='gray')
ax[1].set_title("binary")
ax[0].axis('off')
ax[1].axis('off')

fig.tight_layout()
plt.show()

完整的演示代碼下載地址

https://github.com/gloomyfish1998/opencv_tutorial/blob/master/python/ski_image_demo.py