Merge pull request #21409 from sturkmen72:patch-3

doc/tutorials/dnn/dnn_face/dnn_face.markdown

@@ -8,19 +8,19 @@
 | | |
 | -: | :- |
 | Original Author | Chengrui Wang, Yuantao Feng |
-| Compatibility | OpenCV >= 4.5.1 |
+| Compatibility | OpenCV >= 4.5.4 |
 
 ## Introduction
 
-In this section, we introduce the DNN-based module for face detection and face recognition. Models can be obtained in [Models](#Models). The usage of `FaceDetectorYN` and `FaceRecognizerSF` are presented in [Usage](#Usage).
+In this section, we introduce cv::FaceDetectorYN class for face detection and cv::FaceRecognizerSF class for face recognition.
 
 ## Models
 
 There are two models (ONNX format) pre-trained and required for this module:
-- [Face Detection](https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx):
+- [Face Detection](https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet):
-    - Size: 337KB
+    - Size: 338KB
     - Results on WIDER Face Val set: 0.830(easy), 0.824(medium), 0.708(hard)
-- [Face Recognition](https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view?usp=sharing)
+- [Face Recognition](https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface)
     - Size: 36.9MB
     - Results:
 
@@ -32,9 +32,7 @@ There are two models (ONNX format) pre-trained and required for this module:
     | AgeDB-30 | 94.90%   | 1.202              | 0.277              |
     | CFP-FP   | 94.80%   | 1.253              | 0.212              |
 
-## Usage
+## Code
-
-### DNNFaceDetector
 
 @add_toggle_cpp
 -   **Downloadable code**: Click

modules/objdetect/include/opencv2/objdetect.hpp

@@ -49,8 +49,8 @@
 /**
 @defgroup objdetect Object Detection
 
-Haar Feature-based Cascade Classifier for Object Detection
+@{
-----------------------------------------------------------
+    @defgroup objdetect_cascade_classifier Cascade Classifier for Object Detection
 
 The object detector described below has been initially proposed by Paul Viola @cite Viola01 and
 improved by Rainer Lienhart @cite Lienhart02 .
@@ -90,8 +90,7 @@ middle) and the sum of the image pixels under the black stripe multiplied by 3 i
 compensate for the differences in the size of areas. The sums of pixel values over a rectangular
 regions are calculated rapidly using integral images (see below and the integral description).
 
-To see the object detector at work, have a look at the facedetect demo:
+Check @ref tutorial_cascade_classifier "the corresponding tutorial" for more details.
-<https://github.com/opencv/opencv/tree/4.x/samples/cpp/dbt_face_detection.cpp>
 
 The following reference is for the detection part only. There is a separate application called
 opencv_traincascade that can train a cascade of boosted classifiers from a set of samples.
@@ -99,10 +98,13 @@ opencv_traincascade that can train a cascade of boosted classifiers from a set o
 @note In the new C++ interface it is also possible to use LBP (local binary pattern) features in
 addition to Haar-like features. .. [Viola01] Paul Viola and Michael J. Jones. Rapid Object Detection
 using a Boosted Cascade of Simple Features. IEEE CVPR, 2001. The paper is available online at
-<http://research.microsoft.com/en-us/um/people/viola/Pubs/Detect/violaJones_CVPR2001.pdf>
+<https://github.com/SvHey/thesis/blob/master/Literature/ObjectDetection/violaJones_CVPR2001.pdf>
 
-@{
+    @defgroup objdetect_hog HOG (Histogram of Oriented Gradients) descriptor and object detector
-    @defgroup objdetect_c C API
+    @defgroup objdetect_qrcode QRCode detection and encoding
+    @defgroup objdetect_dnn_face DNN-based face detection and recognition
+Check @ref tutorial_dnn_face "the corresponding tutorial" for more details.
+    @defgroup objdetect_common Common functions and classes
 @}
  */
 
@@ -111,13 +113,15 @@ typedef struct CvHaarClassifierCascade CvHaarClassifierCascade;
 namespace cv
 {
 
-//! @addtogroup objdetect
+//! @addtogroup objdetect_common
 //! @{
 
 ///////////////////////////// Object Detection ////////////////////////////
 
-//! class for grouping object candidates, detected by Cascade Classifier, HOG etc.
+/** @brief This class is used for grouping object candidates detected by Cascade Classifier, HOG etc.
-//! instance of the class is to be passed to cv::partition (see cxoperations.hpp)
+
+instance of the class is to be passed to cv::partition
+ */
 class CV_EXPORTS SimilarRects
 {
 public:
@@ -162,6 +166,10 @@ CV_EXPORTS   void groupRectangles(std::vector<Rect>& rectList, std::vector<int>&
 CV_EXPORTS   void groupRectangles_meanshift(std::vector<Rect>& rectList, std::vector<double>& foundWeights,
                                             std::vector<double>& foundScales,
                                             double detectThreshold = 0.0, Size winDetSize = Size(64, 128));
+//! @}
+
+//! @addtogroup objdetect_cascade_classifier
+//! @{
 
 template<> struct DefaultDeleter<CvHaarClassifierCascade>{ CV_EXPORTS void operator ()(CvHaarClassifierCascade* obj) const; };
 
@@ -243,7 +251,7 @@ public:
     CV_WRAP bool load( const String& filename );
     /** @brief Reads a classifier from a FileStorage node.
 
-    @note The file may contain a new cascade classifier (trained traincascade application) only.
+    @note The file may contain a new cascade classifier (trained by the traincascade application) only.
      */
     CV_WRAP bool read( const FileNode& node );
 
@@ -260,12 +268,6 @@ public:
     cvHaarDetectObjects. It is not used for a new cascade.
     @param minSize Minimum possible object size. Objects smaller than that are ignored.
     @param maxSize Maximum possible object size. Objects larger than that are ignored. If `maxSize == minSize` model is evaluated on single scale.
-
-    The function is parallelized with the TBB library.
-
-    @note
-       -   (Python) A face detection example using cascade classifiers can be found at
-            opencv_source_code/samples/python/facedetect.py
     */
     CV_WRAP void detectMultiScale( InputArray image,
                           CV_OUT std::vector<Rect>& objects,
@@ -338,7 +340,10 @@ public:
 };
 
 CV_EXPORTS Ptr<BaseCascadeClassifier::MaskGenerator> createFaceDetectionMaskGenerator();
+//! @}
 
+//! @addtogroup objdetect_hog
+//! @{
 //////////////// HOG (Histogram-of-Oriented-Gradients) Descriptor and Object Detector //////////////
 
 //! struct for detection region of interest (ROI)
@@ -666,6 +671,10 @@ public:
     */
     void groupRectangles(std::vector<cv::Rect>& rectList, std::vector<double>& weights, int groupThreshold, double eps) const;
 };
+//! @}
+
+//! @addtogroup objdetect_qrcode
+//! @{
 
 class CV_EXPORTS_W QRCodeEncoder {
 protected:
@@ -827,7 +836,7 @@ protected:
     Ptr<Impl> p;
 };
 
-//! @} objdetect
+//! @}
 }
 
 #include "opencv2/objdetect/detection_based_tracker.hpp"

modules/objdetect/include/opencv2/objdetect/detection_based_tracker.hpp

@@ -51,7 +51,7 @@
 namespace cv
 {
 
-//! @addtogroup objdetect
+//! @addtogroup objdetect_cascade_classifier
 //! @{
 
 class CV_EXPORTS DetectionBasedTracker
@@ -215,7 +215,7 @@ class CV_EXPORTS DetectionBasedTracker
         void detectInRegion(const cv::Mat& img, const cv::Rect& r, std::vector<cv::Rect>& detectedObjectsInRegions);
 };
 
-//! @} objdetect
+//! @}
 
 } //end of cv namespace
 

modules/objdetect/include/opencv2/objdetect/face.hpp

@@ -7,13 +7,15 @@
 
 #include <opencv2/core.hpp>
 
-/** @defgroup dnn_face DNN-based face detection and recognition
- */
-
 namespace cv
 {
 
-/** @brief DNN-based face detector, model download link: https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx.
+//! @addtogroup objdetect_dnn_face
+//! @{
+
+/** @brief DNN-based face detector
+
+model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet
  */
 class CV_EXPORTS_W FaceDetectorYN
 {
@@ -80,7 +82,9 @@ public:
                                               int target_id = 0);
 };
 
-/** @brief DNN-based face recognizer, model download link: https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view.
+/** @brief DNN-based face recognizer
+
+model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface
  */
 class CV_EXPORTS_W FaceRecognizerSF
 {
@@ -105,11 +109,11 @@ public:
     CV_WRAP virtual void feature(InputArray aligned_img, OutputArray face_feature) = 0;
 
     /** @brief Calculating the distance between two face features
-     *  @param _face_feature1 the first input feature
+     *  @param face_feature1 the first input feature
-     *  @param _face_feature2 the second input feature of the same size and the same type as _face_feature1
+     *  @param face_feature2 the second input feature of the same size and the same type as face_feature1
      *  @param dis_type defining the similarity with optional values "FR_OSINE" or "FR_NORM_L2"
      */
-    CV_WRAP virtual double match(InputArray _face_feature1, InputArray _face_feature2, int dis_type = FaceRecognizerSF::FR_COSINE) const = 0;
+    CV_WRAP virtual double match(InputArray face_feature1, InputArray face_feature2, int dis_type = FaceRecognizerSF::FR_COSINE) const = 0;
 
     /** @brief Creates an instance of this class with given parameters
      *  @param model the path of the onnx model used for face recognition
@@ -120,6 +124,7 @@ public:
     CV_WRAP static Ptr<FaceRecognizerSF> create(const String& model, const String& config, int backend_id = 0, int target_id = 0);
 };
 
+//! @}
 } // namespace cv
 
 #endif

samples/dnn/face_detect.cpp

@@ -44,8 +44,8 @@ int main(int argc, char** argv)
         "{image2 i2         |            | Path to the input image2. When image1 and image2 parameters given then the program try to find a face on both images and runs face recognition algorithm}"
         "{video v           | 0          | Path to the input video}"
         "{scale sc          | 1.0        | Scale factor used to resize input video frames}"
-        "{fd_model fd       | yunet.onnx | Path to the model. Download yunet.onnx in https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx }"
+        "{fd_model fd       | face_detection_yunet_2021dec.onnx| Path to the model. Download yunet.onnx in https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet}"
-        "{fr_model fr       | face_recognizer_fast.onnx | Path to the face recognition model. Download the model at https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view}"
+        "{fr_model fr       | face_recognition_sface_2021dec.onnx | Path to the face recognition model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface}"
         "{score_threshold   | 0.9        | Filter out faces of score < score_threshold}"
         "{nms_threshold     | 0.3        | Suppress bounding boxes of iou >= nms_threshold}"
         "{top_k             | 5000       | Keep top_k bounding boxes before NMS}"
@@ -65,6 +65,7 @@ int main(int argc, char** argv)
     int topK = parser.get<int>("top_k");
 
     bool save = parser.get<bool>("save");
+    float scale = parser.get<float>("scale");
 
     double cosine_similar_thresh = 0.363;
     double l2norm_similar_thresh = 1.128;
@@ -87,6 +88,9 @@ int main(int argc, char** argv)
             return 2;
         }
 
+        int imageWidth = int(image1.cols * scale);
+        int imageHeight = int(image1.rows * scale);
+        resize(image1, image1, Size(imageWidth, imageHeight));
         tm.start();
 
         //! [inference]
@@ -199,7 +203,6 @@ int main(int argc, char** argv)
     else
     {
         int frameWidth, frameHeight;
-        float scale = parser.get<float>("scale");
         VideoCapture capture;
         std::string video = parser.get<string>("video");
         if (video.size() == 1 && isdigit(video[0]))

samples/dnn/face_detect.py

@@ -16,8 +16,8 @@ parser.add_argument('--image1', '-i1', type=str, help='Path to the input image1.
 parser.add_argument('--image2', '-i2', type=str, help='Path to the input image2. When image1 and image2 parameters given then the program try to find a face on both images and runs face recognition algorithm.')
 parser.add_argument('--video', '-v', type=str, help='Path to the input video.')
 parser.add_argument('--scale', '-sc', type=float, default=1.0, help='Scale factor used to resize input video frames.')
-parser.add_argument('--face_detection_model', '-fd', type=str, default='yunet.onnx', help='Path to the face detection model. Download the model at https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx.')
+parser.add_argument('--face_detection_model', '-fd', type=str, default='face_detection_yunet_2021dec.onnx', help='Path to the face detection model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet')
-parser.add_argument('--face_recognition_model', '-fr', type=str, default='face_recognizer_fast.onnx', help='Path to the face recognition model. Download the model at https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view.')
+parser.add_argument('--face_recognition_model', '-fr', type=str, default='face_recognition_sface_2021dec.onnx', help='Path to the face recognition model. Download the model at https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface')
 parser.add_argument('--score_threshold', type=float, default=0.9, help='Filtering out faces of score < score_threshold.')
 parser.add_argument('--nms_threshold', type=float, default=0.3, help='Suppress bounding boxes of iou >= nms_threshold.')
 parser.add_argument('--top_k', type=int, default=5000, help='Keep top_k bounding boxes before NMS.')
@@ -56,11 +56,15 @@ if __name__ == '__main__':
     # If input is an image
     if args.image1 is not None:
         img1 = cv.imread(cv.samples.findFile(args.image1))
+        img1Width = int(img1.shape[1]*args.scale)
+        img1Height = int(img1.shape[0]*args.scale)
 
+        img1 = cv.resize(img1, (img1Width, img1Height))
         tm.start()
+
         ## [inference]
         # Set input size before inference
-        detector.setInputSize((img1.shape[1], img1.shape[0]))
+        detector.setInputSize((img1Width, img1Height))
 
         faces1 = detector.detect(img1)
         ## [inference]