Opencv学习笔记 - DNN模块初探三

尝试使用Caffe的人脸识别模型，进行人脸识别

一、数据准备

res10_300x300_ssd_iter_140000.caffemodel

deploy.prototxt.txt

下载地址：https://download.csdn.net/download/bashendixie5/13455671

二、Python版本

# import the necessary packages
import numpy as np
import argparse
import cv2

# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe('C:/Users/xiaomao/Desktop/deploy.prototxt', 'C:/Users/xiaomao/Desktop/res10_300x300_ssd_iter_140000.caffemodel')
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
image = cv2.imread('C:/Users/xiaomao/Desktop/1.jpg')

(h, w) = image.shape[:2]
#调整大小版本
#blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0))
#不调整大小版本
blob = cv2.dnn.blobFromImage(image, 1.0, None, (104.0, 177.0, 123.0))
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
net.setInput(blob)
detections = net.forward()

# loop over the detections
for i in range(0, detections.shape[2]):
    # extract the confidence (i.e., probability) associated with the
    # prediction
    confidence = detections[0, 0, i, 2]
    # filter out weak detections by ensuring the `confidence` is
    # greater than the minimum confidence
    # 
    if confidence > 0.13:
        # compute the (x, y)-coordinates of the bounding box for the
        # object
        box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
        (startX, startY, endX, endY) = box.astype("int")

        # draw the bounding box of the face along with the associated
        # probability
        text = "{:.2f}%".format(confidence * 100)
        y = startY - 10 if startY - 10 > 10 else startY + 10
        cv2.rectangle(image, (startX, startY), (endX, endY),
                      (0, 0, 255), 2)
        cv2.putText(image, text, (startX, y),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
# show the output image
cv2.imshow("Output", image)
cv2.waitKey(0)

阈值0.15

阈值0.15

阈值0.15（PS：2015年英国对加拿大橄榄球，一名球迷裸下身跑下场又跑回看台）

阈值0.13，怀疑是因为太远所以识别很差

三、C++版本

#include <fstream>
#include <sstream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace std;
using namespace dnn;

int main(int argc, char** argv)
{
    Net net = readNetFromCaffe("C:/Users/xiaomao/Desktop/deploy.prototxt",
        "C:/Users/xiaomao/Desktop/res10_300x300_ssd_iter_140000.caffemodel");
    Mat image = imread("C:/Users/xiaomao/Desktop/5.jpg");
    Mat image1;
    //调整图像大小
    //resize(image, image1, Size(300, 300));
    //Mat blob = blobFromImage(image1, 1, Size(300, 300), Scalar(104, 117, 123));
    //不调整图像大小
    Mat blob = blobFromImage(image, 1, Size(), Scalar(104, 117, 123));

    net.setInput(blob);
    Mat detections = net.forward();
    Mat detectionMat(detections.size[2], detections.size[3], CV_32F, detections.ptr<float>());

    for (int i = 0; i < detectionMat.rows; i++)
    {
        //自定义阈值
        if (detectionMat.at<float>(i, 2) >= 0.14)
        {
            int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * image.cols);
            int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * image.rows);
            int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * image.cols);
            int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * image.rows);

            Rect object((int)xLeftBottom, (int)yLeftBottom,
                (int)(xRightTop - xLeftBottom),
                (int)(yRightTop - yLeftBottom));

            rectangle(image, object, Scalar(0, 255, 0));
        }
    }


    //显示图片
    imshow("img", image);
    waitKey(0);
    return 0;
}