基于opencv的人脸识别和物体检测_opencv物体识别

opencv基于haar特征和cascade分类器进行人脸识别，基于R-CNN进行物体识别。

要求：

先看完成情况：

所需python库：获取方式1.win+R-cmd-pip install+库名 

获取方式2.pycharm环境下，File-Settings-Python Interpreter-点击加号进行下载

import cv2
import datetime
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import torchvision.transforms as T
import torchvision
import socket

1、人脸识别及储存识别信息：

1.1、训练

要进行特定人脸的识别需要使用若干张照片进行训练，获得训练的数据，再捕捉特定人员的特征进而识别出信息。

import cv2
import os
import numpy as np
from PIL import Image
#训练
def getimagesandlabels(path):
    facesamples = []
    ids = []
    imagepaths = [os.path.join(path, f) for f in os.listdir(path)]
    face_detector = cv2.CascadeClassifier('D:\opencv\opencv\sources\data\haarcascades\haarcascade_frontalface_default.xml')
    for imagePath in imagepaths:
        pil_img = Image.open(imagePath).convert('L')
        img_numpy = np.array(pil_img, 'uint8')
        id = int(os.path.split(imagePath)[-1].split(".")[0])
        faces = face_detector.detectMultiScale(img_numpy)        #检测人脸
        for(x, y, w, h) in faces:
            facesamples.append(img_numpy[y:y+h, x:x+w])
            ids.append(id)
    return facesamples, ids
 
if __name__ == '__main__':
    path = './train/'                          #训练使用图片的位置
    faces, ids1 = getimagesandlabels(path)
    recognizer = cv2.face.LBPHFaceRecognizer_create()
    recognizer.train(faces, np.array(ids1))
    recognizer.write('trainer/trainer.yml')    #保存训练的数据

我获得的训练结果：

1.2人脸识别

调用训练结果进行人脸识别和信息获取，并储存识别时间和人员id。

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('trainer/trainer.yml')                       #调用训练结果
cap = cv2.VideoCapture(0)                                    #开启摄像头
 
def facecapture():
    while True:
        ret, frame = cap.read()                              #获得每帧画面存进frame
        faces = face_cascade.detectMultiScale(frame, 1.3, 5)
        img = frame
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)         #图片灰化
        for (x, y, w, h) in faces:
            # 画出人脸框
            img = cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
            id, confidence = recognizer.predict(gray[y:y + h, x:x + h])
            s = str(id) + str(',') + str(confidence)
            if confidence < 80:
                cv2.putText(img, str(s), (x, y - 7), 3, 0.75, (0, 0, 255), 2, cv2.LINE_AA)
        # 实时展示效果画面
        cv2.imshow('frame2', img)
        k = cv2.waitKey(1) & 0xFF
        if k == ord('c'):
            t = datetime.datetime.now().date().isoformat()#获取当时时间
            cv2.imwrite('./save/' + str(t) + str(' ') + str(id) + '.jpg', img)#储存图片及识别信息。id为识别结果，与训练时图片命名有关
            print('success')
        if k == ord('q'):
            break
    return img

结果展示（n，1n，2n分别为不同人员，n为匹配的训练的第n张照片）：

摄像头实时（很流畅~）显示样例（逗号后为置信度，越低越可靠）：

 2、通信

# 客户端设置
s = socket.socket()
host = 'ip'                 # ip为所用ip地址
port = 12345                # 设置端口
s.bind((host, port))        # 绑定端口
s.listen(5)
# 服务端连接
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
address_server = ('ip', 12345)
sock.connect(address_server)        # 失败会自动反馈
print('connected success')

利用socket进行数据传输（本文未能成功传输视频，帧率太低）

3、物体识别

直接下载训练完的结果，进行物体识别。

model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()
COCO_INSTANCE_CATEGORY_NAMES = [
    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', 'umbrella', 'N/A', 'N/A',
    'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
    'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
    'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
    'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
    'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
    'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]                       #官方提供的分类
 
#识别物体
def get_prediction(img_path, threshold):
    img = Image.open(img_path)
    img = img.convert('RGB')
    transform = T.Compose([T.ToTensor()])
    img = transform(img)
    pred = model([img])
    pred_class = [COCO_INSTANCE_CATEGORY_NAMES[i] for i in list(pred[0]['labels'].numpy())]
    pred_boxes = [[(int(i[0]), int(i[1])), (int(i[2]), int(i[3]))] for i in list(pred[0]['boxes'].detach().numpy())]
    pred_score = list(pred[0]['scores'].detach().numpy())
    pred_t = [pred_score.index(x) for x in pred_score if x > threshold][-1]
    pred_boxes = pred_boxes[:pred_t + 1]
    pred_class = pred_class[:pred_t + 1]
    print("pred_class:", pred_class)
    print("pred_boxes:", pred_boxes)
    return pred_boxes, pred_class
 
#展示识别结果
def object_detection_api(img_path, threshold=0.5):
    boxes, pred_cls = get_prediction(img_path, threshold)
    img = cv2.imread(img_path)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    #画出物体框
    for i in range(len(boxes)-1):
        cv2.rectangle(img, (boxes[i][0]), (boxes[i][1]), color=(0, 255, 0), thickness=2)
        cv2.putText(img, (str(i+1)+pred_cls[i]), (boxes[i][0]),  cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), thickness=1)
    plt.imshow(img)
    plt.show()

结果展示：

 前文包装的函数直接调用，即可获得结果：

img=facecapture()
# 通信，发送照片信息
encode_param = [int(cv2.IMWRITE_JPEG_QUALITY), 50]
img_encode = cv2.imencode('.jpg', img, encode_param)[1]
data = np.array(img_encode)
stringData = data.tobytes()
sock.send(stringData)
print(str(stringData))
 
object_detection_api(img_path='test/0202.jpeg')       # 输入物体照片路径即可
 
cap.release()
cv2.destroyAllWindows()

发送的信息（很长，不全部截取了）：

 PS：物体识别可多种物体同时检测：

 以上便是所有功能及结果展示。