jetbot 07 之人脸识别 (人脸比对)

 

jetson nano 下来尝一下github 近3.7w星的代码 .

https://github.com/ageitgey/face_recognition

一 通过demo分析一下人脸比对的算法流程.

      a 输入几个要比对的人脸样本, 定位人脸 face_location, 对人脸区域编码  face_encodings

      b 在待检测的图像里,先进行人脸定位 face_location, 定位出的人脸区 作编码 face_encodings

      c 定位出的 encodings 与 录入的样本face_encodings逐一比较, 找到一个距离最小的(最像的)

      d 最小的距离满足 < conf_threshod , 则 标定为 对应的人, 否则未找到 .

二 安装 face_recognition

pip3 install face_recognition

 

三 实践

face_recognition 使用的 face_location 算法在我的环境都不大理想. hog 算法占较高cpu且准确率不高, cnn 模型占 gpu内存较高.

由于把它换掉了

 

3.1 demo 1 猜猜哪个是"我"

输入三个人的照片,再从一堆照片里比对哪个是我们三个人之一.

import cv2
import face_recognition
import numpy as np
import traceback


class FaceInfo(object):
    def __init__(self, path, name):
        self.name = name
        self.path = path
        self.face_img, self.face_encoding = self.face_img_load(path)

    @classmethod
    def face_img_load(cls, path):
        image = face_recognition.load_image_file(path)
        locations = face_recognition.face_locations(image)

        face_encodings = face_recognition.face_encodings(image, locations)

        y0, x1, y1, x0 = locations[0]
        face_image = image[y0: y1, x0: x1]

        face_image = cv2.resize(face_image, (64, 64))
        #face_image = cv2.cvtColor(face_image, cv2.COLOR_RGB2BGR)

        return face_image, face_encodings[0]


hu_face = FaceInfo('img/hu_face.jpg', 'hu')
cheng_face = FaceInfo('img/cheng_face.jpg', 'cheng')
han_face = FaceInfo('img/han_face.jpg', 'han')

# Create arrays of known face encodings and their names
known_face_encodings = [
    hu_face.face_encoding,
    cheng_face.face_encoding,
    han_face.face_encoding
]

known_face_names = [
    "hu",
    "cheng",
    "han"
]

face_templates = [
    hu_face.face_img,
    cheng_face.face_img,
    han_face.face_img
]

tolerance_thresh = 0.6

out_win = "foo"
cv2.namedWindow(out_win, cv2.WINDOW_NORMAL)
cv2.setWindowProperty(out_win, cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN)



for i in range(1, 24):
    try:
        img_path = 'img/%d.jpg' % i
        test_image = face_recognition.load_image_file(img_path)
        if test_image.shape[1] < 800:
            pass
        elif test_image.shape[1] < 1600:
            test_image = cv2.resize(test_image, (0, 0), fx=0.5, fy=0.5, interpolation=cv2.INTER_LINEAR)
        else:
            test_image = cv2.resize(test_image, (0, 0), fx=0.25, fy=0.25, interpolation=cv2.INTER_LINEAR)

        # (top, right, bottom, left)
        face_locations = face_recognition.face_locations(test_image)
        face_encodings = face_recognition.face_encodings(test_image, face_locations)

        print("face nums = %s" % (len(face_locations)))

        match_names = []

        match_face_imgs = []
        for face_encoding in face_encodings:
            name = 'foo'
            face_img = None
            face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
            best_idx = np.argmin(face_distances)

            # face samelike tolerance
            if face_distances[best_idx] <= tolerance_thresh:
                name = known_face_names[best_idx]
                face_img = face_templates[best_idx]
                print('detect face samlike [%s] distane = %.3f, all = %s' % (name, face_distances[best_idx], face_distances))

            match_names.append(name)
            match_face_imgs.append(face_img)

        i = 0
        for loc, name, face_img in zip(face_locations, match_names, match_face_imgs):
            y0, x1, y1, x0 = loc

            cv2.putText(test_image, name, (x0, y0), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 3)
            cv2.rectangle(test_image, (x0, y0), (x1, y1), (0, 0, 255), 2)

            if face_img is not None:
                if (i + 1) * 64 <= test_image.shape[0]:
                    test_image[0: 64, i * 64 : (i + 1) * 64] = face_img

            i += 1

        test_image = cv2.cvtColor(test_image, cv2.COLOR_RGB2BGR)
        cv2.imshow(out_win, test_image)
        cv2.waitKey(3000)
    except:
        pass

3.2 demo2 实时摄像头之 "xx" 你好

这里换了 opencv dnn  yoloface darknet  作人脸检测器, 优化速度, 640x360分辨率人脸定位 在 40ms以内, 人脸比对在 30ms以内. 加了语音播报, 首次定位到某某人会说 XX你好

#!/usr/bin/python3
# -*- coding:utf-8 -*-
import sys
sys.path.append('/workspace/hugo_py')
sys.path.append('./yoloface')
import os 

cur_path=os.path.dirname(os.path.abspath(__file__))
import Speech

import cv2
import face_recognition
import numpy as np
import traceback
from camera import JetCamera
import traceback
import time
from yoloface.darknet_detect_live import DarkNetWrap

cap_w = 640
cap_h = 360
cap_fps = 10


class FaceInfo(object):
    def __init__(self, path, name, face_detector):
        self.name = name
        self.path = path
        self.face_detector = face_detector
        self.face_img, self.face_encoding = self.face_img_load(path)

    def face_img_load(self, path):
        image = face_recognition.load_image_file(path)
        boxs = self.face_detector.detect(image)
        print('----------------- boxs', boxs)
        x0, y0, x1, y1 = boxs[0]

        locations = [y0, x1, y1, x0]

        face_encodings = face_recognition.face_encodings(image, [locations])

        y0, x1, y1, x0 = locations
        face_image = image[y0: y1, x0: x1]

        face_image = cv2.resize(face_image, (64, 64))
        #face_image = cv2.cvtColor(face_image, cv2.COLOR_RGB2BGR)

        return face_image, face_encodings[0]


class FaceDetectDNN(object):
    def __init__(self, DNN="TF", conf_threshold = 0.7):
        # OpenCV DNN supports 2 networks.
        # 1. FP16 version of the original caffe implementation ( 5.4 MB )
        # 2. 8 bit Quantized version using Tensorflow ( 2.7 MB )

        self.conf_threshold = conf_threshold

        '''模型加载'''
        DNN = "TF"
        if DNN == "CAFFE":
            modelFile = "./fd_model/res10_300x300_ssd_iter_140000_fp16.caffemodel"
            configFile = "./fd_model/deploy.prototxt"
            self.net = cv2.dnn.readNetFromCaffe(configFile, modelFile)
        else:
            modelFile = "./fd_model/opencv_face_detector_uint8.pb"
            configFile = "./fd_model/opencv_face_detector.pbtxt"
            self.net = cv2.dnn.readNetFromTensorflow(modelFile, configFile)

        # 打开 OPENCV－DNN CUDA 支持
        self.net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
        self.net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)

    def detect(self, frame):
        frameOpencvDnn = frame.copy()
        frameHeight = frameOpencvDnn.shape[0]
        frameWidth = frameOpencvDnn.shape[1]
        '''检测'''
        blob = cv2.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], False, False)

        self.net.setInput(blob)
        detections = self.net.forward()
        bboxes = []
        for i in range(detections.shape[2]):
            confidence = detections[0, 0, i, 2]
            if confidence > self.conf_threshold:
                x1 = int(detections[0, 0, i, 3] * frameWidth)
                y1 = int(detections[0, 0, i, 4] * frameHeight)
                x2 = int(detections[0, 0, i, 5] * frameWidth)
                y2 = int(detections[0, 0, i, 6] * frameHeight)
                bboxes.append([x1, y1, x2, y2])

        return bboxes



def main():
    out_win = "foo"
    cv2.namedWindow(out_win, cv2.WINDOW_NORMAL)
    cv2.setWindowProperty(out_win, cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN)

    cam = JetCamera(cap_w, cap_h, cap_fps)
    cam.open()

    #fd = FaceDetectDNN()
    fd = DarkNetWrap()

    Speech.SetReader(Speech.Reader_Type["Reader_XuXiaoBao"])
    Speech.SetVolume(10)
    Speech.SetSpeed(5)

    last_person_str = ''

    os.chdir(cur_path)
    hu_face = FaceInfo('img/hu_face.jpg', 'hu', face_detector=fd)
    cheng_face = FaceInfo('img/cheng_face.jpg', 'cheng', face_detector=fd)
    han_face = FaceInfo('img/han_face.jpg', 'han', face_detector=fd)

    # Create arrays of known face encodings and their names
    known_face_encodings = [
        hu_face.face_encoding,
        cheng_face.face_encoding,
        han_face.face_encoding
    ]

    known_face_names = [
        "hu",
        "cheng",
        "han",
    ]

    known_face_names_cn = {'hu': '哇哈哈', 'cheng': '郑鸭蛋', 'han': '胡涵茜', 'foo': '不认识'}

    face_templates = [
        hu_face.face_img,
        cheng_face.face_img,
        han_face.face_img
    ]

    tolerance_thresh = 0.6
    cnt = 0
    while True:
        try:
            ret, frame = cam.read()
            # print("camera read one frame ")
            if not ret:
                break

            detect_img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

            # (top, right, bottom, left)
            t0 = time.time()
            boxs =  fd.detect(frame)
            face_locations = []
            for b in boxs:
                x0, y0, x1, y1 = b
                face_locations.append([y0, x1, y1, x0])

            #face_locations = face_recognition.face_locations(detect_img)
            t1 = time.time()
            face_encodings = face_recognition.face_encodings(detect_img, face_locations)
            t2 = time.time()

            print("face nums = %s" % (len(face_locations)))
            match_names = []

            match_face_imgs = []
            for face_encoding in face_encodings:
                name = 'foo'
                face_img = None
                face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
                best_idx = np.argmin(face_distances)

                # face samelike tolerance
                if face_distances[best_idx] <= tolerance_thresh:
                    name = known_face_names[best_idx]
                    face_img = face_templates[best_idx]
                    print('detect face samlike [%s] distane = %.3f, all = %s' % (
                    name, face_distances[best_idx], face_distances))

                match_names.append(name)
                match_face_imgs.append(face_img)

            i = 0
            for loc, name, face_img in zip(face_locations, match_names, match_face_imgs):
                y0, x1, y1, x0 = loc

                cv2.putText(detect_img, name, (x0, y0), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 3)
                cv2.rectangle(detect_img, (x0, y0), (x1, y1), (0, 0, 255), 2)

                if face_img is not None:
                    if (i + 1) * 64 <= detect_img.shape[0]:
                        detect_img[0: 64, i * 64: (i + 1) * 64] = face_img

                i += 1

            detect_img = cv2.cvtColor(detect_img, cv2.COLOR_RGB2BGR)
            cv2.imshow(out_win, detect_img)
            cv2.waitKey(1)

            cnt += 1

            person_str = ''
            for name in match_names:
                person_str += '%s 你好! ' % known_face_names_cn[name]

            if person_str != last_person_str:
                Speech.Block_Speech_text(person_str)
                last_person_str = person_str

            if cnt % 1 == 0:
                print("frame cnt [%d] face recognition detect delay = %.1fms, %.1fms" % (cnt, (t1 - t0) * 1000, (t2 - t1) * 1000))

        except:
            traceback.print_exc()
            break

    cam.close()


if __name__ == '__main__':
    main()