Merge pull request spmallick#255 from vikasguptaiisc/master

added code for Age Gender

AgeGender/AgeGender.cpp

@@ -0,0 +1,141 @@
+#include <opencv2/imgproc.hpp>
+#include <opencv2/highgui.hpp>
+#include <opencv2/dnn.hpp>
+#include <tuple>
+#include <iostream>
+#include <opencv2/opencv.hpp>
+#include <iterator>
+using namespace cv;
+using namespace cv::dnn;
+using namespace std;
+
+tuple<Mat, vector<vector<int>>> getFaceBox(Net net, Mat &frame, double conf_threshold)
+{
+    Mat frameOpenCVDNN = frame.clone();
+    int frameHeight = frameOpenCVDNN.rows;
+    int frameWidth = frameOpenCVDNN.cols;
+    double inScaleFactor = 1.0;
+    Size size = Size(300, 300);
+    // std::vector<int> meanVal = {104, 117, 123};
+    Scalar meanVal = Scalar(104, 117, 123);
+
+    cv::Mat inputBlob;
+    cv::dnn::blobFromImage(frameOpenCVDNN, inputBlob, inScaleFactor, size, meanVal, true, false);
+
+    net.setInput(inputBlob, "data");
+    cv::Mat detection = net.forward("detection_out");
+
+    cv::Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
+
+    vector<vector<int>> bboxes;
+
+    for(int i = 0; i < detectionMat.rows; i++)
+    {
+        float confidence = detectionMat.at<float>(i, 2);
+
+        if(confidence > conf_threshold)
+        {
+            int x1 = static_cast<int>(detectionMat.at<float>(i, 3) * frameWidth);
+            int y1 = static_cast<int>(detectionMat.at<float>(i, 4) * frameHeight);
+            int x2 = static_cast<int>(detectionMat.at<float>(i, 5) * frameWidth);
+            int y2 = static_cast<int>(detectionMat.at<float>(i, 6) * frameHeight);
+            vector<int> box = {x1, y1, x2, y2};
+            bboxes.push_back(box);
+            cv::rectangle(frameOpenCVDNN, cv::Point(x1, y1), cv::Point(x2, y2), cv::Scalar(0, 255, 0),2, 4);
+        }
+    }
+
+    return make_tuple(frameOpenCVDNN, bboxes);
+}
+
+int main(int argc, char** argv)
+{
+    string faceProto = "opencv_face_detector.pbtxt";
+    string faceModel = "opencv_face_detector_uint8.pb";
+
+    string ageProto = "age_deploy.prototxt";
+    string ageModel = "age_net.caffemodel";
+
+    string genderProto = "gender_deploy.prototxt";
+    string genderModel = "gender_net.caffemodel";
+
+    Scalar MODEL_MEAN_VALUES = Scalar(78.4263377603, 87.7689143744, 114.895847746);
+
+    vector<string> ageList = {"(0-2)", "(4-6)", "(8-12)", "(15-20)", "(25-32)",
+      "(38-43)", "(48-53)", "(60-100)"};
+
+    vector<string> genderList = {"Male", "Female"};
+
+    // Load Network
+    Net ageNet = readNet(ageModel, ageProto);
+    Net genderNet = readNet(genderModel, genderProto);
+    Net faceNet = readNet(faceModel, faceProto);
+
+    VideoCapture cap;
+    if (argc > 1)
+        cap.open(argv[1]);
+    else
+        cap.open(0);
+
+    while(waitKey(1) < 0) {
+      // read frame
+      Mat frame;
+      cap.read(frame);
+      if (frame.empty())
+      {
+          waitKey();
+          break;
+      }
+
+      vector<vector<int>> bboxes;
+      Mat frameFace;
+      tie(frameFace, bboxes) = getFaceBox(faceNet, frame, 0.7);
+
+      if(bboxes.size() == 0) {
+        cout << "No face detected, checking next frame." << endl;
+        continue;
+      }
+      for (auto it = begin(bboxes); it != end(bboxes); ++it) {
+        Rect rec(it->at(0), it->at(1), it->at(2) - it->at(0), it->at(3) - it->at(1));
+        Mat face = frame(rec); // take the ROI of box on the frame
+
+        Mat blob;
+        blob = blobFromImage(face, 1, Size(227, 227), MODEL_MEAN_VALUES, false);
+        genderNet.setInput(blob);
+        // string gender_preds;
+        vector<float> genderPreds = genderNet.forward();
+        // printing gender here
+        // find max element index
+        // distance function does the argmax() work in C++
+        int max_index_gender = std::distance(genderPreds.begin(), max_element(genderPreds.begin(), genderPreds.end()));
+        string gender = genderList[max_index_gender];
+        cout << "Gender: " << gender << endl;
+
+        /* // Uncomment if you want to iterate through the gender_preds vector
+        for(auto it=begin(gender_preds); it != end(gender_preds); ++it) {
+          cout << *it << endl;
+        }
+        */
+
+        ageNet.setInput(blob);
+        vector<float> agePreds = ageNet.forward();
+        /* // uncomment below code if you want to iterate through the age_preds
+         * vector
+        cout << "PRINTING AGE_PREDS" << endl;
+        for(auto it = age_preds.begin(); it != age_preds.end(); ++it) {
+          cout << *it << endl;
+        }
+        */
+
+        // finding maximum indicd in the age_preds vector
+        int max_indice_age = std::distance(agePreds.begin(), max_element(agePreds.begin(), agePreds.end()));
+        string age = ageList[max_indice_age];
+        cout << "Age: " << age << endl;
+        string label = gender + ", " + age; // label
+        cv::putText(frameFace, label, Point(it->at(0), it->at(1) -20), cv::FONT_HERSHEY_SIMPLEX, 0.8, Scalar(0, 0, 255), 2, cv::LINE_AA);
+        imshow("Frame", frameFace);
+        imwrite("out.jpg",frameFace);
+      }
+
+    }
+}

AgeGender/AgeGender.py

@@ -0,0 +1,88 @@
+# Import required modules
+import cv2 as cv
+import math
+import time
+import argparse
+
+def getFaceBox(net, frame, conf_threshold=0.7):
+    frameOpencvDnn = frame.copy()
+    frameHeight = frameOpencvDnn.shape[0]
+    frameWidth = frameOpencvDnn.shape[1]
+    blob = cv.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], True, False)
+
+    net.setInput(blob)
+    detections = net.forward()
+    bboxes = []
+    for i in range(detections.shape[2]):
+        confidence = detections[0, 0, i, 2]
+        if confidence > 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])
+            cv.rectangle(frameOpencvDnn, (x1, y1), (x2, y2), (0, 255, 0), int(round(frameHeight/150)), 8)
+    return frameOpencvDnn, bboxes
+
+
+parser = argparse.ArgumentParser(description='Use this script to run age and gender recognition using OpenCV.')
+parser.add_argument('--input', help='Path to input image or video file. Skip this argument to capture frames from a camera.')
+
+args = parser.parse_args()
+
+faceProto = "opencv_face_detector.pbtxt"
+faceModel = "opencv_face_detector_uint8.pb"
+
+ageProto = "age_deploy.prototxt"
+ageModel = "age_net.caffemodel"
+
+genderProto = "gender_deploy.prototxt"
+genderModel = "gender_net.caffemodel"
+
+MODEL_MEAN_VALUES = (78.4263377603, 87.7689143744, 114.895847746)
+ageList = ['(0 - 2)', '(4 - 6)', '(8 - 12)', '(15 - 20)', '(25 - 32)', '(38 - 43)', '(48 - 53)', '(60 - 100)']
+genderList = ['Male', 'Female']
+
+# Load network
+ageNet = cv.dnn.readNet(ageModel, ageProto)
+genderNet = cv.dnn.readNet(genderModel, genderProto)
+faceNet = cv.dnn.readNet(faceModel, faceProto)
+
+# Open a video file or an image file or a camera stream
+cap = cv.VideoCapture(args.input if args.input else 0)
+
+while cv.waitKey(1) < 0:
+    # Read frame
+    t = time.time()
+    hasFrame, frame = cap.read()
+    if not hasFrame:
+        cv.waitKey()
+        break
+
+    frameFace, bboxes = getFaceBox(faceNet, frame)
+    if not bboxes:
+        print("No face Detected, Checking next frame")
+        continue
+
+    for bbox in bboxes:
+        # print(bbox)
+        face = frame[bbox[1]:bbox[3],bbox[0]:bbox[2]]
+
+        blob = cv.dnn.blobFromImage(face, 1, (227, 227), MODEL_MEAN_VALUES, swapRB=False)
+        genderNet.setInput(blob)
+        genderPreds = genderNet.forward()
+        gender = genderList[genderPreds[0].argmax()]
+        # print("Gender Output : {}".format(genderPreds))
+        print("Gender : {}".format(gender))
+
+        ageNet.setInput(blob)
+        agePreds = ageNet.forward()
+        age = ageList[agePreds[0].argmax()]
+        # print("Age Output : {}".format(agePreds))
+        print("Age : {}".format(age))
+
+        label = "{}, {}".format(gender, age)
+        cv.putText(frameFace, label, (bbox[0], bbox[1]-20), cv.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2, cv.LINE_AA)
+        cv.imshow("Age Gender Demo", frameFace)
+        cv.imwrite("out.jpg",frameFace)
+    print("time : {:.3f}".format(time.time() - t))

AgeGender/CMakeLists.txt

@@ -0,0 +1,19 @@
+cmake_minimum_required(VERSION 2.8.12)
+
+PROJECT(age_gender)
+# PATH to OpenCV ( uncomment and provide path if required )
+# set(OpenCV_DIR /Users/visionifai/codes/installations/OpenCV4/lib/cmake/opencv4/)
+
+find_package( OpenCV REQUIRED )
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX_STANDARD_REQUIRED TRUE)
+
+include_directories( ${OpenCV_INCLUDE_DIRS})
+
+MACRO(add_example name)
+  ADD_EXECUTABLE(${name} ${name}.cpp)
+  TARGET_LINK_LIBRARIES(${name} ${OpenCV_LIBS})
+ENDMACRO()
+
+add_example(AgeGender)

AgeGender/README.md

@@ -0,0 +1,26 @@
+## Code for Age Gender recognition using Deep Learning
+
+### Models
+Download models from
+
+Gender Net : https://www.dropbox.com/s/iyv483wz7ztr9gh/gender_net.caffemodel?dl=0"
+
+Age Net : https://www.dropbox.com/s/xfb20y596869vbb/age_net.caffemodel?dl=0"
+
+### Run Code
+
+#### C++
+```
+cmake .
+make
+./AgeGender <input_file>(Leave blank for webcam)
+```
+
+#### Python
+```
+python AgeGender.py --input <input_file>(Leave blank for webcam)
+```
+
+### Sample Result
+
+![](sample-output.jpg)