OpenCV基础
OpenCV是一个开源的计算机视觉库。提供了很多图像处理常用的工具
批注:本文所有图片数据都在我的GitHub仓库
读取图片并显示
import numpy as np import cv2 as cv original = cv.imread('../machine_learning_date/forest.jpg') cv.imshow('Original', original)
显示图片某个颜色通道的图像
blue = np.zeros_like(original) blue[:, :, 0] = original[:, :, 0] # 0 - 蓝色通道 cv.imshow('Blue', blue) green = np.zeros_like(original) green[:, :, 1] = original[:, :, 1] # 1 - 绿色通道 cv.imshow('Green', green) red = np.zeros_like(original) red[:, :, 2] = original[:, :, 2] # 2 - 红色通道 cv.imshow('Red', red)
图像剪裁
h, w = original.shape[:2] # (397, 600) l, t = int(w / 4), int(h / 4) # 左上 r, b = int(w * 3 / 4), int(h * 3 / 4) # 右下 cropped = original[t:b, l:r] cv.imshow('Cropped', cropped)
图像缩放
cv2.resize(src,dsize,dst=None,fx=None,fy=None,interpolation=None)
参数:
- scr:原图
- dsize:输出图像尺寸
- fx:沿水平轴的比例因子
- fy:沿垂直轴的比例因子
- interpolation:插值方法
# 输出图像大小=输入图像大小/4 scaled1 = cv.resize(original, (int(w / 4), int(h / 4)), interpolation=cv.INTER_LINEAR) cv.imshow('Scaled1', scaled1)
# 原图像大小,沿x轴,y轴的缩放系数 scaled2 = cv.resize(scaled1, None, fx=4, fy=4, interpolation=cv.INTER_LINEAR) cv.imshow('Scaled2', scaled2) cv.waitKey() # 等待用户按键触发,或者按 Ese 键 停止等待
图像文件保存
cv.imwrite('../ml_data/blue.jpg', blue)
边缘检测
物体的边缘检测是物体识别常用的手段。边缘检测常用亮度梯度方法。通过识别亮度梯度变化最大的像素点从而检测出物体的边缘。
import cv2 as cv # 读取并展示图像 original = cv.imread('../machine_learning_date/chair.jpg', cv.IMREAD_GRAYSCALE) cv.imshow('Original', original)
索贝尔边缘识别
cv.Sobel(original, cv.CV_64F, 1, 0, ksize=5)
参数:
- src:源图像
- ddepth:cv.CV_64F:卷积运算使用数据类型为64位浮点型(保证微分的精度)
- dx:1表示取水平方向索贝尔偏微分
- dy:0表示不取垂直方向索贝尔偏微分
- ksize:卷积核为5*5的方阵
水平方向索贝尔偏微分
hsobel = cv.Sobel(original, cv.CV_64F, 1, 0, ksize=5) cv.imshow('H-Sobel', hsobel)
垂直方向索贝尔偏微分
vsobel = cv.Sobel(original, cv.CV_64F, 0, 1, ksize=5) cv.imshow('V-Sobel', vsobel)
水平和垂直方向索贝尔偏微分
sobel = cv.Sobel(original, cv.CV_64F, 1, 1, ksize=5) cv.imshow('Sobel', sobel)
拉普拉斯边缘识别
cv.Laplacian(original, cv.CV_64F)
laplacian = cv.Laplacian(original, cv.CV_64F) cv.imshow('Laplacian', laplacian)
Canny边缘识别
cv.Canny(original, 50, 240)
- image:输入图像
-
threshold1:50,水平方向阈值
- threshold1:240,垂直方向阈值
canny = cv.Canny(original, 50, 80) cv.imshow('Canny', canny) cv.waitKey()
亮度提升
OpenCV提供了直方图均衡化的方式实现亮度提升,更有利于边缘识别与物体识别模型的训练。
彩色图转为灰度图
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
直方图均衡化
equalized_gray = cv.equalizeHist(gray)
案例:
读取图像
import cv2 as cv # 读取图片 original = cv.imread('../machine_learning_date/sunrise.jpg') cv.imshow('Original', original) # 显示图片
彩色图转为灰度图
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY) cv.imshow('Gray', gray)
灰度图直方图均衡化
equalized_gray = cv.equalizeHist(gray) cv.imshow('Equalized Gray', equalized_gray)
YUV:亮度,色度,饱和度
yuv = cv.cvtColor(original, cv.COLOR_BGR2YUV) yuv[..., 0] = cv.equalizeHist(yuv[..., 0]) # 亮度 直方图均衡化 yuv[..., 1] = cv.equalizeHist(yuv[..., 1]) # 色度 直方图均衡化 yuv[..., 2] = cv.equalizeHist(yuv[..., 2]) # 饱和度 直方图均衡化 equalized_color = cv.cvtColor(yuv, cv.COLOR_YUV2BGR) cv.imshow('Equalized Color', equalized_color) cv.waitKey()
角点检测
平直棱线的交汇点(颜色梯度方向改变的像素点的位置)
Harris角点检测器
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
corners = cv.cornerHarris(gray, 7, 5, 0.04)
- src:输入单通道8位或浮点图像。
- blockSize:角点检测区域大小
- ksize:Sobel求导中使用的窗口大小
- k:边缘线方向改变超过阈值0.04弧度即为一个角点,一般取[0.04 0.06]
案例:
import cv2 as cv original = cv.imread('../machine_learning_date/box.png') cv.imshow('Original', original) gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY) # 转换成灰度,减少计算量 cv.imshow('Gray', gray) corners = cv.cornerHarris(gray, 7, 5, 0.04) # Harris角点检测器 # 图像混合 mixture = original.copy() mixture[corners > corners.max() * 0.01] = [0, 0, 255] # BGR [0, 0, 255]变红 cv.imshow('Corner', mixture) cv.waitKey()
图像识别
特征点检测
常用特征点检测有:STAR特征点检测 / SIFT特征点检测
特征点检测结合了 边缘检测 与 角点检测 从而识别出图形的特征点
STAR特征点检测相关API如下:
star = cv.xfeatures2d.StarDetector_create() # 创建STAR特征点检测器
keypoints = star.detect(gray) # 检测出gray图像所有的特征点
把所有的特征点绘制在mixture图像中
cv.drawKeypoints(original, keypoints, mixture, flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
参数:
- image:原图片
- keypoints:源图像中的关键点
- outImage:输出图片
- flags:标志设置图形特征
案例:
import cv2 as cv original = cv.imread('../machine_learning_date/table.jpg') gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY) # 变成灰度图,减少计算 cv.imshow('Gray', gray) star = cv.xfeatures2d.StarDetector_create() # 创建STAR特征点检测器 keypoints = star.detect(gray) # 检测出gray图像所有的特征点 mixture = original.copy() # drawKeypoints方法可以把所有的特征点绘制在mixture图像中 cv.drawKeypoints(original, keypoints, mixture, flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS) cv.imshow('Mixture', mixture) cv.waitKey()
SIFT特征点检测相关API:
sift = cv.xfeatures2d.SIFT_create() # 创建SIFT特征点检测器
keypoints = sift.detect(gray) # 检测出gray图像所有的特征点
案例:
import cv2 as cv original = cv.imread('../machine_learning_date/table.jpg') gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY) cv.imshow('Gray', gray) sift = cv.xfeatures2d.SIFT_create() # 创建SIFT特征点检测器 keypoints = sift.detect(gray) # 检测出gray图像所有的特征点 mixture = original.copy() # 把所有的特征点绘制在mixture图像中 cv.drawKeypoints(original, keypoints, mixture, flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS) cv.imshow('Mixture', mixture) cv.waitKey()
特征值矩阵
图像特征值矩阵(描述)记录了图像的特征点以及每个特征点的梯度信息,相似图像的特征值矩阵也相似。这样只要有足够多的样本,就可以基于隐马尔科夫模型进行图像内容的识别。
特征值矩阵相关API:
sift = cv.xfeatures2d.SIFT_create() keypoints = sift.detect(gray) _, desc = sift.compute(gray, keypoints)
案例:
import cv2 as cv import matplotlib.pyplot as plt original = cv.imread('../machine_learning_date/table.jpg') gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY) cv.imshow('Gray', gray) sift = cv.xfeatures2d.SIFT_create() # 创建SIFT特征点检测器 keypoints = sift.detect(gray) # 检测出gray图像所有的特征点 _, desc = sift.compute(gray, keypoints) print(desc.shape) # (454, 128) plt.matshow(desc.T, cmap='jet', fignum='Description') plt.title('Description') plt.xlabel('Feature') plt.ylabel('Sample') plt.tick_params(which='both', top=False, labeltop=False, labelbottom=True, labelsize=10) plt.show()
物体识别
1、读取training文件夹中的训练图片样本,每个图片对应一个desc矩阵,每个desc都有一个类别(car)
2、把所有类别为car的desc合并在一起,形成训练集
| desc | || desc | car || desc | |.....
由上述训练集样本可以训练一个用于匹配car的HMM。
3、训练3个HMM分别对应每个物体类别。 保存在列表中。
4、读取testing文件夹中的测试样本,整理测试样本
| desc | car || desc | moto |
5、针对每一个测试样本:
- 分别使用3个HMM模型,对测试样本计算score得分。
- 取3个模型中得分最高的模型所属类别作为预测类别。
import os import numpy as np import cv2 as cv import hmmlearn.hmm as hl def search_files(directory): directory = os.path.normpath(directory) objects = {} for curdir, subdirs, files in os.walk(directory): for file in files: if file.endswith('.jpg'): label = curdir.split(os.path.sep)[-1] if label not in objects: objects[label] = [] path = os.path.join(curdir, file) objects[label].append(path) return objects # 加载训练集样本数据,训练模型,模型存储 train_objects = search_files('../machine_learning_date/objects/training') train_x, train_y = [], [] for label, filenames in train_objects.items(): descs = np.array([]) for filename in filenames: image = cv.imread(filename) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) # 范围缩放,使特征描述矩阵样本数量一致 h, w = gray.shape[:2] f = 200 / min(h, w) gray = cv.resize(gray, None, fx=f, fy=f) sift = cv.xfeatures2d.SIFT_create() # 创建SIFT特征点检测器 keypoints = sift.detect(gray) # 检测出gray图像所有的特征点 _, desc = sift.compute(gray, keypoints) # 转换成特征值矩阵 if len(descs) == 0: descs = desc else: descs = np.append(descs, desc, axis=0) train_x.append(descs) train_y.append(label) models = {} for descs, label in zip(train_x, train_y): model = hl.GaussianHMM(n_components=4, covariance_type='diag', n_iter=100) models[label] = model.fit(descs) # 测试模型 test_objects = search_files('../machine_learning_date/objects/testing') test_x, test_y = [], [] for label, filenames in test_objects.items(): descs = np.array([]) for filename in filenames: image = cv.imread(filename) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) sift = cv.xfeatures2d.SIFT_create() keypoints = sift.detect(gray) _, desc = sift.compute(gray, keypoints) if len(descs) == 0: descs = desc else: descs = np.append(descs, desc, axis=0) test_x.append(descs) test_y.append(label) # 遍历所有测试样本 使用model匹配测试样本查看每个模型的匹配分数 pred_y = [] for descs, test_label in zip(test_x, test_y): best_score, best_label = None, None for pred_label, model in models.items(): score = model.score(descs) if (best_score == None) or (best_score < score): best_score = score best_label = pred_label print(test_label, '->', pred_label, score) # airplane -> airplane -373374.23370679974 # airplane -> car -374022.20182585815 # airplane -> motorbike -374127.46289302857 # car -> airplane -163638.3153800373 # car -> car -163691.52001099114 # car -> motorbike -164410.0557508754 # motorbike -> airplane -467472.6294620241 # motorbike -> car -470149.6143097087 # motorbike -> motorbike -464606.0040570249 pred_y.append(best_label) print(test_y) # ['airplane', 'car', 'motorbike'] print(pred_y) # ['airplane', 'airplane', 'motorbike']
人脸识别
人脸识别与图像识别的区别在于人脸识别需要识别出两个人的不同点。
视频捕捉
通过OpenCV访问视频捕捉设备(视频头),从而获取图像帧。
视频捕捉相关API:
import cv2 as cv # 获取视频捕捉设备 video_capture = cv.VideoCapture(0) # 读取一帧 frame = video_capture.read()[1] cv.imshow('VideoCapture', frame) # 释放视频捕捉设备 video_capture.release() # 销毁cv的所有窗口 cv.destroyAllWindows()
案例:
import cv2 as cv vc = cv.VideoCapture(0) while True: frame = vc.read()[1] cv.imshow('VideoCapture', frame) if cv.waitKey(33) == 27: # 退出键是27 break vc.release() cv.destroyAllWindows()
人脸定位
哈尔级联人脸定位
import cv2 as cv # 通过特征描述文件构建哈尔级联人脸识别器 fd = cv.CascadeClassifier('../data/haar/face.xml') # 从一个图像中识别出所有的人脸区域 # 1.3:为最小的人脸尺寸 # 5:最多找5张脸 # 返回: # faces: 抓取人脸(矩形区域)列表 [(l,t,w,h),(),()..] faces = fd.detectMultiScale(frame, 1.3, 5) face = faces[0] # 第一张脸 # 绘制椭圆 cv.ellipse( frame, # 图像 (l + a, t + b), # 椭圆心 (a, b), # 半径 0, # 椭圆旋转角度 0, 360, # 起始角, 终止角 (255, 0, 255), # 颜色 2 # 线宽 )
案例:
import cv2 as cv # 哈尔级联人脸定位器 fd = cv.CascadeClassifier('../../data/haar/face.xml') ed = cv.CascadeClassifier('../../data/haar/eye.xml') nd = cv.CascadeClassifier('../../data/haar/nose.xml') vc = cv.VideoCapture(0) while True: frame = vc.read()[1] faces = fd.detectMultiScale(frame, 1.3, 5) for l, t, w, h in faces: a, b = int(w / 2), int(h / 2) cv.ellipse(frame, (l + a, t + b), (a, b), 0, 0, 360, (255, 0, 255), 2) face = frame[t:t + h, l:l + w] eyes = ed.detectMultiScale(face, 1.3, 5) for l, t, w, h in eyes: a, b = int(w / 2), int(h / 2) cv.ellipse(face, (l + a, t + b), (a, b), 0, 0, 360, (0, 255, 0), 2) noses = nd.detectMultiScale(face, 1.3, 5) for l, t, w, h in noses: a, b = int(w / 2), int(h / 2) cv.ellipse(face, (l + a, t + b), (a, b), 0, 0, 360, (0, 255, 255), 2) cv.imshow('VideoCapture', frame) if cv.waitKey(33) == 27: break vc.release() cv.destroyAllWindows()
人脸识别
简单人脸识别:OpenCV的LBPH(局部二值模式直方图)
# -*- coding: utf-8 -*- from __future__ import unicode_literals import os import numpy as np import cv2 as cv import sklearn.preprocessing as sp fd = cv.CascadeClassifier('../../data/haar/face.xml') def search_faces(directory): directory = os.path.normpath(directory) faces = {} for curdir, subdirs, files in os.walk(directory): for jpeg in (file for file in files if file.endswith('.jpg')): path = os.path.join(curdir, jpeg) label = path.split(os.path.sep)[-2] if label not in faces: faces[label] = [] faces[label].append(path) return faces train_faces = search_faces( '../../data/faces/training') codec = sp.LabelEncoder() codec.fit(list(train_faces.keys())) train_x, train_y = [], [] for label, filenames in train_faces.items(): for filename in filenames: image = cv.imread(filename) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) faces = fd.detectMultiScale(gray, 1.1, 2, minSize=(100, 100)) for l, t, w, h in faces: train_x.append( gray[t:t + h, l:l + w]) train_y.append( codec.transform([label])[0]) train_y = np.array(train_y) # 局部二值模式直方图人脸识别分类器 model = cv.face.LBPHFaceRecognizer_create() model.train(train_x, train_y) test_faces = search_faces( '../../data/faces/testing') test_x, test_y, test_z = [], [], [] for label, filenames in test_faces.items(): for filename in filenames: image = cv.imread(filename) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) faces = fd.detectMultiScale(gray, 1.1, 2, minSize=(100, 100)) for l, t, w, h in faces: test_x.append( gray[t:t + h, l:l + w]) test_y.append( codec.transform([label])[0]) a, b = int(w / 2), int(h / 2) cv.ellipse(image, (l + a, t + b), (a, b), 0, 0, 360, (255, 0, 255), 2) test_z.append(image) test_y = np.array(test_y) pred_test_y = [] for face in test_x: pred_code = model.predict(face)[0] pred_test_y.append(pred_code) escape = False while not escape: for code, pred_code, image in zip( test_y, pred_test_y, test_z): label, pred_label = \ codec.inverse_transform([code, pred_code]) text = '{} {} {}'.format( label, '==' if code == pred_code else '!=', pred_label) cv.putText(image, text, (10, 60), cv.FONT_HERSHEY_SIMPLEX, 2, (255, 255, 255), 6) cv.imshow('Recognizing...', image) if cv.waitKey(1000) == 27: escape = True break