图像识别与人脸识别

图像识别

基础

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import numpy as np
import cv2 as cv
original = cv.imread('../../data/forest.jpg')
cv.imshow('Original', original)
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)
h, w = original.shape[:2]
l, t = int(w / 4), int(h / 4)
r, b = int(w * 3 / 4), int(h * 3 / 4)
# 图片裁剪
cropped = original[t:b, l:r]
cv.imshow('Cropped', cropped)
# 缩放
scaled1 = cv.resize(
    original, (int(w / 4), int(h / 4)),
    interpolation=cv.INTER_LINEAR)
cv.imshow('Scaled1', scaled1)
# 缩放
scaled2 = cv.resize(
    scaled1, None, fx=4, fy=4,
    interpolation=cv.INTER_LINEAR)
cv.imshow('Scaled2', scaled2)
cv.waitKey()
cv.imwrite('../../data/blue.jpg', blue)
cv.imwrite('../../data/green.jpg', green)
cv.imwrite('../../data/red.jpg', red)
cv.imwrite('../../data/cropped.jpg', cropped)
cv.imwrite('../../data/scaled1.jpg', scaled1)
cv.imwrite('../../data/scaled2.jpg', scaled2)

边缘检测

通过梯度剧烈变化，识别轮廓。

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import cv2 as cv
original = cv.imread(
    '../../data/chair.jpg', cv.IMREAD_GRAYSCALE)
cv.imshow('Original', original)
# 三种获取边缘的方式
hsobel = cv.Sobel(original, cv.CV_64F, 1, 0,
                  ksize=5)
cv.imshow('H-Sobel', hsobel)

vsobel = cv.Sobel(original, cv.CV_64F, 0, 1,
                  ksize=5)
cv.imshow('V-Sobel', vsobel)
sobel = cv.Sobel(original, cv.CV_64F, 1, 1,
                 ksize=5)
cv.imshow('Sobel', sobel)
laplacian = cv.Laplacian(original, cv.CV_64F)
cv.imshow('Laplacian', laplacian)
canny = cv.Canny(original, 50, 240)
cv.imshow('Canny', canny)
cv.waitKey()

亮度提升

通过直方图均衡化，提高较暗的部分。让整体亮度

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import cv2 as cv
original = cv.imread('../../data/sunrise.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
# 直方图均衡化
equalized_gray = cv.equalizeHist(gray)
cv.imshow('Equalized Gray', equalized_gray)
yuv = cv.cvtColor(original, cv.COLOR_BGR2YUV)
yuv[..., 0] = cv.equalizeHist(yuv[..., 0])
equalized_color = cv.cvtColor(yuv, cv.COLOR_YUV2BGR)
cv.imshow('Equalized Color', equalized_color)
cv.waitKey()

特征点检测

识别图片中的特殊结构点，作为特征点记录。
根据颜色梯度得到拐角、边缘等颜色梯度大的地方识别。这种地方变化较大且特征明显。
通过这个可以得到特征描述矩阵。

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import cv2 as cv
original = cv.imread(r'C:\Users\Cs\Desktop\table.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
# 创建STAR特征点监测器
# pip install opencv-contrib-python
star = cv.xfeatures2d.StarDetector_create()
keypoints = star.detect(gray)
mixture = original.copy()

cv.drawKeypoints(
    original, keypoints, mixture,
    flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv.imshow('Mixture', mixture)
cv.waitKey()

图像的特征描述矩阵

来源于反映图像中物体的结构特征关键点的空间直方图。

#特征描述
import cv2 as cv
import matplotlib.pyplot as mp
original = cv.imread(r'C:\Users\Cs\Desktop\table.jpg')
cv.imshow('or',original)
gray=cv.cvtColor(original,cv.COLOR_BGR2GRAY)
star=cv.xfeatures2d.StarDetector_create()
keypoints=star.detect(gray)
sift=cv.xfeatures2d.SIFT_create()
_,desc=sift.compute(gray,keypoints)
mp.matshow(desc)
mp.show()

基于特征矩阵的物体识别

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import os
import warnings
import numpy as np
import cv2 as cv
import hmmlearn.hmm as hl

warnings.filterwarnings('ignore', category=DeprecationWarning)
np.seterr(all='ignore')


def search_objects(directory):
    directory = os.path.normpath(directory)
    if not os.path.isdir(directory):
        raise IOError("The directory '" + directory + "' doesn't exist!")
    objects = {}
    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 objects:
                objects[label] = []
            objects[label].append(path)
    return objects

# 获取训练数据
train_objects = search_objects(r'C:\Users\Cs\Desktop\objects\training')
train_x, train_y = [], []
for label, filenames in train_objects.items():
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename, cv.IMREAD_ANYCOLOR)
        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
        # 获取图片尺寸
        h, w = gray.shape[:2]
        f = 200 / min(h, w)
        # 通过缩放统一图片尺寸
        gray = cv.resize(gray, None, fx=f, fy=f)
        # 获取物体二维特征
        # xfeatures2d模块使用有疑问
        star = cv.xfeatures2d.StarDetector_create()
        #得到物体特征矩阵
        # 返回图像中的关键点
        keypoints = star.detect(gray)
        sift = cv.xfeatures2d.SIFT_create()
        # 得到特征点与特征点描述（SIFT SURF ORB  AKAZE）
        _, desc = sift.compute(gray, keypoints)
        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):
# 训练模型
    model = hl.GaussianHMM(
        n_components=4, covariance_type='diag',
        n_iter=1000)
    models[label] = model.fit(descs)
test_objects = search_objects(
    r'C:\Users\Cs\Desktop\objects\testing')
test_x, test_y, test_z = [], [], []
for label, filenames in test_objects.items():
    test_z.append([])
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename)
        test_z[-1].append(image)
        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
        h, w = gray.shape[:2]
        f = 200 / min(h, w)
        gray = cv.resize(gray, None, fx=f, fy=f)
        star = cv.xfeatures2d.StarDetector_create()
        keypoints = star.detect(gray)
        sift = cv.xfeatures2d.SIFT_create()
        _, 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)
pred_test_y = []
# 返回匹配的最佳值
for descs in test_x:
    best_score, best_label = None, None
    for label, model in models.items():
        score = model.score(descs)
        if (best_score is None) or (
                best_score < score):
            best_score, best_label = score, label
    pred_test_y.append(best_label)
i = 0
# 展示图片
for label, pred_label, images in zip(
        test_y, pred_test_y, test_z):
    for image in images:
        i += 1
        cv.imshow('{} - {} {} {}'.format(
            i, label,
            '==' if label == pred_label else '!=',
            pred_label), image)
cv.waitKey()

人脸识别

视频捕捉

视频捕捉设备->图像帧
代码：

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import cv2 as cv
vc = cv.VideoCapture(0)
while True:
    frame = vc.read()[1]
    cv.imshow('VideoCapture', frame)
    if cv.waitKey(33) == 27:
        break
# 记得关闭摄像头
vc.release()
cv.destroyAllWindows()

人脸定位

哈尔级联人脸定位。
代码：

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import cv2 as cv
# 哈尔级联人脸定位器
fd = cv.CascadeClassifier(r'C:\Users\Cs\Desktop\haar\face.xml')
ed = cv.CascadeClassifier(r'C:\Users\Cs\Desktop\haar\eye.xml')
nd = cv.CascadeClassifier(r'C:\Users\Cs\Desktop\haar\nose.xml')
vc = cv.VideoCapture(0)
while True:
    frame = vc.read()[1]
    # 参数：图片矩阵，最小尺寸，最多数量？？
    faces = fd.detectMultiScale(frame, 1.3, 5)
    for l, t, w, h in faces:
        a, b = int(w / 2), int(h / 2)
        # cv.ellipse(图像, 椭圆心, 半径, 旋转角,
        #     起始角, 终止角, 颜色, 线宽)
        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()

3.简单人脸识别：OpenCV的LBPH(局部二值模式直方图)
代码：

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import os
import numpy as np
import cv2 as cv
import sklearn.preprocessing as sp
# 级联搜索，定位人脸位置使用
fd = cv.CascadeClassifier('../../data/haar/face.xml')

#获取训练数据
def search_faces(directory):
    directory = os.path.normpath(directory)
    if not os.path.isdir(directory):
        raise IOError("The directory '" +
                      directory +
                      "' doesn't exist!")
    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():
    #图片切割
    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