add feature blob option for feature extraction

modules/cnn_3dobj/README.md

@@ -37,19 +37,19 @@ $ make
 #Demo1:
 ###Imagas generation from different pose, 4 models are used, there will be 276 images in all which each class contains 69 iamges
 ```
-$ ./sphereview_test -ite_depth=2 -plymodel=../3Dmodel/ape.ply -imagedir=../data/images_all/ -labeldir=../data/label_all.txt -num_class=4 -label_class=0
+$ ./sphereview_test -plymodel=../3Dmodel/ape.ply -label_class=0
 ```
 ###press q to start
 ```
-$ ./sphereview_test -ite_depth=2 -plymodel=../3Dmodel/ant.ply -imagedir=../data/images_all/ -labeldir=../data/label_all.txt -num_class=4 -label_class=1
+$ ./sphereview_test -plymodel=../3Dmodel/ant.ply -label_class=1
 ```
 ###press q to start
 ```
-$ ./sphereview_test -ite_depth=2 -plymodel=../3Dmodel/cow.ply -imagedir=../data/images_all/ -labeldir=../data/label_all.txt -num_class=4 -label_class=2
+$ ./sphereview_test -plymodel=../3Dmodel/cow.ply -label_class=2
 ```
 ###press q to start
 ```
-$ ./sphereview_test -ite_depth=2 -plymodel=../3Dmodel/plane.ply -imagedir=../data/images_all/ -labeldir=../data/label_all.txt -num_class=4 -label_class=3
+$ ./sphereview_test -plymodel=../3Dmodel/plane.ply -label_class=3
 ```
 ###press q to start, when all images are created in images_all folder as a collection of images for network tranining and feature extraction, then proceed on.
 ###After this demo, the binary files of images and labels will be stored as 'binary_image' and 'binary_label' in current path, you should copy them into the leveldb folder in Caffe triplet training, for example: copy these 2 files in <caffe_source_directory>/data/linemod and rename them as 'binary_image_train', 'binary_image_test' and 'binary_label_train', 'binary_label_train'.

modules/cnn_3dobj/include/opencv2/cnn_3dobj.hpp

@@ -160,10 +160,10 @@ class CV_EXPORTS_W Classification
 		void GetLabellist(const std::vector<string>& name_gallery);
 		/** @brief Get the label of the gallery images for result displaying in prediction.
 		*/
-		std::vector<std::pair<string, float> > Classify(const cv::Mat& reference, const cv::Mat& img, int N, bool mean_substract = false);
+		std::vector<std::pair<string, float> > Classify(const cv::Mat& reference, const cv::Mat& target, int N);
 		/** @brief Make a classification.
 		*/
-		void FeatureExtract(InputArray inputimg, OutputArray feature, bool mean_subtract);
+		void FeatureExtract(InputArray inputimg, OutputArray feature, bool mean_subtract, std::string feature_blob);
 		/** @brief Extract a single featrue of one image.
 		*/
 		std::vector<int> Argmax(const std::vector<float>& v, int N);

modules/cnn_3dobj/samples/classifyIMG_demo.cpp

@@ -41,10 +41,11 @@ int main(int argc, char** argv)
 {
 	const String keys = "{help | | this demo will convert a set of images in a particular path into leveldb database for feature extraction using Caffe.}"
 		     "{src_dir | ../data/images_all/ | Source direction of the images ready for being used for extract feature as gallery.}"
-		     "{caffemodel | ../data/3d_triplet_iter_10000.caffemodel | caffe model for feature exrtaction.}"
+		     "{caffemodel | ../data/3d_triplet_iter_20000.caffemodel | caffe model for feature exrtaction.}"
 		     "{network_forIMG | ../data/3d_triplet_testIMG.prototxt | Network definition file used for extracting feature from a single image and making a classification}"
 		     "{mean_file | ../data/images_mean/triplet_mean.binaryproto | The mean file generated by Caffe from all gallery images, this could be used for mean value substraction from all images.}"
 		     "{target_img | ../data/images_all/3_13.png | Path of image waiting to be classified.}"
+		     "{feature_blob | feat | Name of layer which will represent as the feature, in this network, ip1 or feat is well.}"
 		     "{num_candidate | 6 | Number of candidates in gallery as the prediction result.}"
 		     "{device | CPU | device}"
 		     "{dev_id | 0 | dev_id}";
@@ -60,6 +61,7 @@ int main(int argc, char** argv)
 	string network_forIMG   = parser.get<string>("network_forIMG");
 	string mean_file    = parser.get<string>("mean_file");
 	string target_img   = parser.get<string>("target_img");
+	string feature_blob = parser.get<string>("feature_blob");
 	int num_candidate = parser.get<int>("num_candidate");
 	string device = parser.get<string>("device");
 	int dev_id = parser.get<int>("dev_id");
@@ -77,7 +79,7 @@ int main(int argc, char** argv)
 	for (unsigned int i = 0; i < name_gallery.size(); i++) {
 	  img_gallery.push_back(cv::imread(name_gallery[i], -1));
 	}
-	classifier.FeatureExtract(img_gallery, feature_reference, false);
+	classifier.FeatureExtract(img_gallery, feature_reference, false, feature_blob);
 
 	std::cout << std::endl << "---------- Prediction for "
 	    << target_img << " ----------" << std::endl;
@@ -89,9 +91,9 @@ int main(int argc, char** argv)
 	for (unsigned int i = 0; i < feature_reference.rows; i++)
 	  std::cout << feature_reference.row(i) << endl;
 	cv::Mat feature_test;
-	classifier.FeatureExtract(img, feature_test, false);
+	classifier.FeatureExtract(img, feature_test, false, feature_blob);
 	std::cout << std::endl << "---------- Featrue of target image: " << target_img << "----------" << endl << feature_test << std::endl;
-	prediction = classifier.Classify(feature_reference, img, num_candidate, false);
+	prediction = classifier.Classify(feature_reference, feature_test, num_candidate);
 	// Print the top N prediction.
 	std::cout << std::endl << "---------- Prediction result(Distance - File Name in Gallery) ----------" << std::endl;
 	for (size_t i = 0; i < prediction.size(); ++i) {

modules/cnn_3dobj/samples/sphereview_3dobj_demo.cpp

@@ -41,11 +41,11 @@ using namespace std;
 using namespace cv::cnn_3dobj;
 int main(int argc, char *argv[]){
 	const String keys = "{help | | demo :$ ./sphereview_test -ite_depth=2 -plymodel=../3Dmodel/ape.ply -imagedir=../data/images_ape/ -labeldir=../data/label_ape.txt -num_class=4 -label_class=0, then press 'q' to run the demo for images generation when you see the gray background and a coordinate.}"
-			     "{ite_depth | 1 | Iteration of sphere generation.}"
-			     "{plymodel | ../ape.ply | path of the '.ply' file for image rendering. }"
-			     "{imagedir | ../data/images_ape/ | path of the generated images for one particular .ply model. }"
-			     "{labeldir | ../data/label_ape.txt | path of the generated images for one particular .ply model. }"
-			     "{num_class | 2 | total number of classes of models}"
+			     "{ite_depth | 2 | Iteration of sphere generation.}"
+			     "{plymodel | ../3Dmodel/ape.ply | path of the '.ply' file for image rendering. }"
+			     "{imagedir | ../data/images_all/ | path of the generated images for one particular .ply model. }"
+			     "{labeldir | ../data/label_all.txt | path of the generated images for one particular .ply model. }"
+			     "{num_class | 4 | total number of classes of models}"
 			     "{label_class | 0 | class label of current .ply model}";
 	cv::CommandLineParser parser(argc, argv, keys);
 	parser.about("Demo for Sphere View data generation");

modules/cnn_3dobj/src/cnn_classification.cpp

@@ -81,15 +81,13 @@ namespace cnn_3dobj
   };
 
   //Return the top N predictions.
-  std::vector<std::pair<string, float> > Classification::Classify(const cv::Mat& reference, const cv::Mat& img, int N, bool mean_substract)
+  std::vector<std::pair<string, float> > Classification::Classify(const cv::Mat& reference, const cv::Mat& target, int N)
   {
-    cv::Mat feature;
-    Classification::FeatureExtract(img, feature, mean_substract);
     std::vector<float> output;
     for (int i = 0; i < reference.rows; i++)
     {
       cv::Mat f1 = reference.row(i);
-      cv::Mat f2 = feature;
+      cv::Mat f2 = target;
       cv::Mat output_temp = f1-f2;
       output.push_back(cv::norm(output_temp));
     }
@@ -132,7 +130,7 @@ namespace cnn_3dobj
     mean_ = cv::Mat(input_geometry_, mean.type(), channel_mean);
   };
 
-  void Classification::FeatureExtract(InputArray inputimg, OutputArray feature, bool mean_subtract)
+  void Classification::FeatureExtract(InputArray inputimg, OutputArray feature, bool mean_subtract, std::string featrue_blob)
   {
     Blob<float>* input_layer = net_->input_blobs()[0];
     input_layer->Reshape(1, num_channels_,
@@ -147,7 +145,7 @@ namespace cnn_3dobj
       Preprocess(img, &input_channels, mean_subtract);
       net_->ForwardPrefilled();
       /* Copy the output layer to a std::vector */
-      Blob<float>* output_layer = net_->output_blobs()[0];
+      Blob<float>* output_layer = net_->blob_by_name(featrue_blob).get();
       const float* begin = output_layer->cpu_data();
       const float* end = begin + output_layer->channels();
       std::vector<float> featureVec = std::vector<float>(begin, end);
@@ -164,7 +162,7 @@ namespace cnn_3dobj
         Preprocess(img[i], &input_channels, mean_subtract);
         net_->ForwardPrefilled();
         /* Copy the output layer to a std::vector */
-        Blob<float>* output_layer = net_->output_blobs()[0];
+        Blob<float>* output_layer = net_->blob_by_name(featrue_blob).get();
         const float* begin = output_layer->cpu_data();
         const float* end = begin + output_layer->channels();
         std::vector<float> featureVec = std::vector<float>(begin, end);