OpenCV-Python速查：从载入图片到人脸识别！

2019-06-09 本文已影响2人 14e61d025165

什么是OpenCV-Python？

OpenCV是一个计算机视觉和机器学习的开源库。拥有2500+个优化算法——一套非常全面的既经典又最先进的计算机视觉和机器学习算法的集合，具备很多接口，包括Python，Java，C++和Matlab。

这次，让我们来攻克Python的接口：

Python学习交流群：1004391443，这里是python学习者聚集地，有大牛答疑，有资源共享！小编也准备了一份python学习资料，有想学习python编程的，或是转行，或是大学生，还有工作中想提升自己能力的，正在学习的小伙伴欢迎加入学习。

安装方式
导入/查看图像
裁剪：Cropping
调整：Resizing
旋转：Rotating
灰度和阈值：Grayscaling and Thresholding
模糊/平滑：Blurring/Smoothing
绘制矩形/边界框
画线
在图片上写入文字
人脸识别
轮廓(Contours)——一种物体检测的方法
保存图像

安装方式有两种：Window用户，Linux用户；不管是使用哪种方式都请阅读原文查看。

导入图像 & 显示

import cv2

image = cv2.imread("./Path/To/Image.extension")

cv2.imshow("Image", image)

cv2.waitKey(0)

cv2.destroyAllWindows()

提醒1：通过OpenCV的种方式读取图像，它不是RGB色域的——而是BGR色域的。有时候这不会是一个问题，只有在你想加入彩色内容到你的图像中的时候会有麻烦。

有两个解决办法：

将R - 1st（红色）与B - 3rd（蓝色）切换，使红色为（0,0,255）而不是（255,0,0）。
改变色域为RGB

<pre spellcheck="false" style="box-sizing: border-box; margin: 5px 0px; padding: 5px 10px; border: 0px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-numeric: inherit; font-variant-east-asian: inherit; font-weight: 400; font-stretch: inherit; font-size: 16px; line-height: inherit; font-family: inherit; vertical-align: baseline; cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; background-color: rgb(240, 240, 240); border-radius: 3px; white-space: pre-wrap; color: rgb(34, 34, 34); letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
</pre>

然后在你的rgb_image上继续编写代码，而不是在image上。

提醒2：按下任意按键，来关闭显示图像的窗口。如果你使用关闭按钮可以能会导致卡主（在我使用Jupyter Notebook时，有发生这样的情况）

简单起见，整个教程中我会使用下面的方法来显示图像：

import cv2

def viewImage(image, name_of_window):

cv2.namedWindow(name_of_window, cv2.WINDOW_NORMAL)

cv2.imshow(name_of_window, image)

cv2.waitKey(0)

cv2.destroyAllWindows()

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928509 ql-align-center" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; text-align: left; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

图片来源: Pixabay

裁剪：Cropping

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928520" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

图片来源: Pixabay

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928524" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

裁剪后的狗狗

import cv2

cropped = image[10:500, 500:2000]

viewImage(cropped, "Doggo after cropping.")

在图像：image[10:500, 500:2000] 中以(y, x)为起点，裁剪大小为(h, w)的图像： image[y:y+h, x:x+w]

调整大小：Resizing

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928529 ql-align-center" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; text-align: left; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

图像来源: Pexels

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928534 ql-align-center" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; text-align: left; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

调整20%之后

import cv2

scale_percent = 20 # percent of original size

width = int(img.shape[1] * scale_percent / 100)

height = int(img.shape[0] * scale_percent / 100)

dim = (width, height)

resized = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)

viewImage(resized, "After resizing with 20%")

调整大小的函数保持了和原来图像一样的尺寸比。

更多关于图像缩放的函数，查看原文。

旋转：Rotating

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928539" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image <input class="pgc-img-caption-ipt" placeholder="图片描述(最多50字)" value="" style="box-sizing: border-box; outline: 0px; color: rgb(102, 102, 102); position: absolute; left: 187.5px; transform: translateX(-50%); padding: 6px 7px; max-width: 100%; width: 375px; text-align: center; cursor: text; font-size: 12px; line-height: 1.5; background-color: rgb(255, 255, 255); background-image: none; border: 0px solid rgb(217, 217, 217); border-radius: 4px; transition: all 0.2s cubic-bezier(0.645, 0.045, 0.355, 1) 0s;"></tt-image> <tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928542" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 照片来自Pexels的Jonathan Meyer.下方：旋转180度后的狗狗

import cv2

(h, w, d) = image.shape

center = (w // 2, h // 2)

M = cv2.getRotationMatrix2D(center, 180, 1.0)

rotated = cv2.warpAffine(image, M, (w, h))

viewImage(rotated, "Doggo after rotation by 190 degrees")

image.shape输出了图像的高度，宽度和通道数。M是旋转矩阵——根据图像中心旋转180度。-ve按照顺指针方向旋转图像 & +ve 则是按照逆时针方向旋转。

灰度和阈值（黑&白效果）

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928548" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

图像来源: Pexels

import cv2

gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

ret, threshold_image = cv2.threshold(im, 127, 255, 0)

viewImage(gray_image, "Gray-scale doggo")

viewImage(threshold_image, "Black & White doggo")

gray_image是图像的灰度单通道版本。阈值函数将所有阴影变为比127更暗（更小）到0并且所有更亮（更大）到255。

另外一个例子：

<pre spellcheck="false" style="box-sizing: border-box; margin: 5px 0px; padding: 5px 10px; border: 0px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-numeric: inherit; font-variant-east-asian: inherit; font-weight: 400; font-stretch: inherit; font-size: 16px; line-height: inherit; font-family: inherit; vertical-align: baseline; cursor: text; counter-reset: list-1 0 list-2 0 list-3 0 list-4 0 list-5 0 list-6 0 list-7 0 list-8 0 list-9 0; background-color: rgb(240, 240, 240); border-radius: 3px; white-space: pre-wrap; color: rgb(34, 34, 34); letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;">ret, threshold = cv2.threshold(im, 150, 200, 10)
</pre>

这将使所有阴影小于150到10并且全部大于200。

更多关于阈值函数，查阅原文。

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928552" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image <input class="pgc-img-caption-ipt" placeholder="图片描述(最多50字)" value="" style="box-sizing: border-box; outline: 0px; color: rgb(102, 102, 102); position: absolute; left: 187.5px; transform: translateX(-50%); padding: 6px 7px; max-width: 100%; width: 375px; text-align: center; cursor: text; font-size: 12px; line-height: 1.5; background-color: rgb(255, 255, 255); background-image: none; border: 0px solid rgb(217, 217, 217); border-radius: 4px; transition: all 0.2s cubic-bezier(0.645, 0.045, 0.355, 1) 0s;"></tt-image> <tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928558" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 灰度图像狗狗下方: 黑白狗狗

模糊/平滑

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928563" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image <input class="pgc-img-caption-ipt" placeholder="图片描述(最多50字)" value="" style="box-sizing: border-box; outline: 0px; color: rgb(102, 102, 102); position: absolute; left: 187.5px; transform: translateX(-50%); padding: 6px 7px; max-width: 100%; width: 375px; text-align: center; cursor: text; font-size: 12px; line-height: 1.5; background-color: rgb(255, 255, 255); background-image: none; border: 0px solid rgb(217, 217, 217); border-radius: 4px; transition: all 0.2s cubic-bezier(0.645, 0.045, 0.355, 1) 0s;"></tt-image> <tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928569" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 图像来自Pixabay. 下方: 模糊的狗狗

import cv2

blurred = cv2.GaussianBlur(image, (51, 51), 0)

viewImage(blurred, "Blurred doggo")

GussianBlur函数接收3个参数：

第一个参数是你想要模糊的图像
第二个参数必须是两个正奇数的元组。当他们增加时，模糊效果会增加。
第三个参数是sigmaX和sigmaY。当保留为0时，他们将根据内核大小自动计算

更多的模糊函数，参看原文。

在图像上绘制矩形/边界框

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928575" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image <input class="pgc-img-caption-ipt" placeholder="图片描述(最多50字)" value="" style="box-sizing: border-box; outline: 0px; color: rgb(102, 102, 102); position: absolute; left: 187.5px; transform: translateX(-50%); padding: 6px 7px; max-width: 100%; width: 375px; text-align: center; cursor: text; font-size: 12px; line-height: 1.5; background-color: rgb(255, 255, 255); background-image: none; border: 0px solid rgb(217, 217, 217); border-radius: 4px; transition: all 0.2s cubic-bezier(0.645, 0.045, 0.355, 1) 0s;"></tt-image> <tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928577" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 图像来自Pexels. 下方: 狗狗脸上画了一个矩形框

import cv2

output = image.copy()

cv2.rectangle(output, (2600, 800), (4100, 2400), (0, 255, 255), 10)

viewImage(output, "Doggo with a rectangle on his face")

矩形框函数接收5个参数：

第一个参数是图像
第二个参数是x1, y1 ——对应左上角
第三个参数是x2, y2 ——对应右下角
第四个参数是矩形颜色（GBR/RGB，具体取决于你导入图像的方式）
第五个参数矩形线条的粗细

在图片上绘制线段

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928588" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image <input class="pgc-img-caption-ipt" placeholder="图片描述(最多50字)" value="" style="box-sizing: border-box; outline: 0px; color: rgb(102, 102, 102); position: absolute; left: 187.5px; transform: translateX(-50%); padding: 6px 7px; max-width: 100%; width: 375px; text-align: center; cursor: text; font-size: 12px; line-height: 1.5; background-color: rgb(255, 255, 255); background-image: none; border: 0px solid rgb(217, 217, 217); border-radius: 4px; transition: all 0.2s cubic-bezier(0.645, 0.045, 0.355, 1) 0s;"></tt-image> <tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928594" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 图像来自Pexels. 下方: 2只狗狗被一条直线分隔

import cv2

output = image.copy()

cv2.line(output, (60, 20), (400, 200), (0, 0, 255), 5)

viewImage(output, "2 Doggos separated by a line")

line函数需要传入5个参数：

第一个参数是你需要在上面绘制线段的图像。
第二个参数是直线的x1, y1坐标。
第三个参数是直线的x2 y2坐标。
第四个参数是线段的颜色（可以是GBR/也可以是RGB，这取决于你导入的图片的格式）。
第五个参数是线段的粗细。

在图片上输入文字

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928600" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

上方: 图像来自Pexels. 下方: 含有文字的图片

import cv2

output = image.copy()

cv2.putText(output, "We <3 Dogs", (1500, 3600),cv2.FONT_HERSHEY_SIMPLEX, 15, (30, 105, 210), 40)

viewImage(output, "image with text")

putText 函数包含七个参数：

第一个参数是您需要在上面输入文字的图片
第二个参数是需要输入的文字内容
第三个参数是文字开始区域的左下角的x,y坐标
第四个参数是字体
第五个参数是字体大小
第六个参数是字体颜色（可以是GBR/也可以是RGB，这取决于你导入的图片的格式）。
第七个参数是字体的粗细

人脸识别

非常抱歉，此处我们不能放狗狗的图片了。:(

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928608" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

来自于 Pixabay的免费图片

import cv2

image_path = "./Path/To/Photo.extension"

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

image = cv2.imread(image_path)

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

faces = face_cascade.detectMultiScale(

gray,

scaleFactor= 1.1,

minNeighbors= 5,

minSize=(10, 10)

)

faces_detected = format(len(faces)) + " faces detected!"

print(faces_detected)# Draw a rectangle around the faces

for (x, y, w, h) in faces:

cv2.rectangle(image, (x, y), (x+w, y+h), (255, 255, 0), 2)

viewImage(image,faces_detected)

detectMultiScale函数是一个检测物体的通用函数。当我们把它用于人脸检测时，它就会从图像中检测出人脸。

detectMultiScale函数包含四个参数：

第一个参数是灰度图
第二个参数是缩放比例。因为在我们的图片中，有些人脸由于更靠近照相机，导致他们看起来比后面的人脸更大些。缩放参数就是为了解决这种问题的。
检测算法使用了滑动窗口来检测目标物体。minNeighbors参数定义了当识别出一个人脸之前在当前物体周围需要检测的物体数目。
同时minSize参数给出了窗口的大小

<tt-image data-tteditor-tag="tteditorTag" contenteditable="false" class="syl1560063928614" data-render-status="finished" data-syl-blot="image" style="box-sizing: border-box; cursor: text; color: rgb(34, 34, 34); font-family: "PingFang SC", "Hiragino Sans GB", "Microsoft YaHei", "WenQuanYi Micro Hei", "Helvetica Neue", Arial, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-indent: 0px; text-transform: none; white-space: pre-wrap; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(255, 255, 255); text-decoration-style: initial; text-decoration-color: initial; display: block;">

image

在图片中检测出两张人脸

轮廓—— 一种物体检测的方法

使用基于颜色的图片分段，我们可以实现物体的检测。cv2.findContours 和 cv2.drawContours 两个函数可以帮我们实现上述目标。

近期，我写了一篇非常详细的文章，文章的题目是使用python来实现基于颜色的图片分段的物体检测。如果你想了解关于轮廓的知识，你可以去阅读这篇文章。

最后，保存图片

import cv2

image = cv2.imread("./Import/path.extension")

cv2.imwrite("./Export/Path.extension", image)

OpenCV-Python速查：从载入图片到人脸识别！

猜你喜欢

热点阅读