dlib人脸检测及68个关键点检测

最新推荐文章于 2023-10-09 02:05:08 发布

Seasea77

最新推荐文章于 2023-10-09 02:05:08 发布

阅读量994

点赞数

本文链接：https://blog.csdn.net/weixin_41874898/article/details/112664757

版权

文章目录

1 python实现
2 C++实现

文章参考： https://blog.csdn.net/liuxiao214/article/details/83411820

1 python实现

1.1 dlib准备：

（1）dlib安装：

pip install dlib

大约等10分钟，中途会卡在“Building wheel for dlib (setup.py) …”
其他安装方法参考：
1）https://blog.csdn.net/qq_41185868/article/details/79678783
2）python37 https://www.jianshu.com/p/9503b1434529
3）python35, python36 https://github.com/coneypo/Dlib_install/tree/master/for_windows
（2）dlib检测模型（离线包）下载链接：http://dlib.net/files/
人脸68个特征点模型：shape_predictor_68_face_landmarks.dat.bz2

1.2 人脸框检测

人脸框检测不用加载离线包
demo:

# -*- coding: utf-8 -*-

import dlib
import numpy as np
import cv2


def rect_to_bb(rect):  # 获得人脸矩形的坐标信息
    x = rect.left()
    y = rect.top()
    w = rect.right() - x
    h = rect.bottom() - y
    return (x, y, w, h)


def resize(image, width=1200):  # 将待检测的image进行resize
    r = width * 1.0 / image.shape[1]
    dim = (width, int(image.shape[0] * r))
    resized = cv2.resize(image, dim, interpolation=cv2.INTER_AREA)
    return resized


def detect():
    image_file = "234.jpg"
    detector = dlib.get_frontal_face_detector()
    image = cv2.imread(image_file)
    # image = resize(image, width=500)
    image = resize(image, width=1200)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    rects = detector(gray, 3)  # 2表示采样次数，数字越大检测到人头越多。对于多人头，该值越大检测到人头越多。图片变大也可以检测到多人头。
    for (i, rect) in enumerate(rects):
        (x, y, w, h) = rect_to_bb(rect)
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
        # cv2.putText(image, "Face： {}".format(i + 1), (x - 10, y - 10), cv2.FONT_HERSHEY_COMPLEX, 2, (255, 0, 0),2)
    cv2.imshow("Output", image)
    cv2.waitKey(0)


if __name__ == "__main__":
    detect()

测试结果：
在这里插入图片描述

1.3 人脸68个关键点检测

68个关键点检测需要加载离线包，离线包下载慢可以用下面链接下载：
https://download.csdn.net/download/weixin_41874898/14354822
demo:

# encoding:utf-8

import dlib
import numpy as np
import cv2


def rect_to_bb(rect):  # 获得人脸矩形的坐标信息
    x = rect.left()
    y = rect.top()
    w = rect.right() - x
    h = rect.bottom() - y
    return (x, y, w, h)


def shape_to_np(shape, dtype="int"):  # 将包含68个特征的的shape转换为numpy array格式
    coords = np.zeros((68, 2), dtype=dtype)
    for i in range(0, 68):
        coords[i] = (shape.part(i).x, shape.part(i).y)
    return coords


def resize(image, width=1200):  # 将待检测的image进行resize
    r = width * 1.0 / image.shape[1]
    dim = (width, int(image.shape[0] * r))
    resized = cv2.resize(image, dim, interpolation=cv2.INTER_AREA)
    return resized


def feature():
    image_file = "test.jpg"
    detector = dlib.get_frontal_face_detector()
    predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
    image = cv2.imread(image_file)
    image = resize(image, width=1200)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    rects = detector(gray, 1)
    shapes = []
    for (i, rect) in enumerate(rects):
        shape = predictor(gray, rect)
        shape = shape_to_np(shape)
        shapes.append(shape)
        (x, y, w, h) = rect_to_bb(rect)
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
        cv2.putText(image, "Face: {}".format(i + 1), (x - 10, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5