Closed elboyran closed 7 years ago
Creating Visual Vocabulary for image training data store # 1 out of 1 Creating Bag-Of-Features.
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations.
** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 22323 images...done. Extracted 661030 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering.
** Image category 2 has the least number of strongest features: 80365.
** Using the strongest 80365 features from each of the other image categories.
Using K-Means clustering to create a 10 word visual vocabulary.
Number of features : 241095
Number of clusters (K) : 10
Initializing cluster centers...100.00%.
Clustering...completed 33/100 iterations (~0.59 seconds/iteration)...converged in 33 iterations.
Finished creating Bag-Of-Features
Encoding images using Bag-Of-Features.
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Encoding 22323 images...done.
Elapsed time is 705.031849 seconds.
Creating Visual Vocabulary for image testing data store # 1 out of 1
Creating Bag-Of-Features.
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations.
** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 9567 images...done. Extracted 283449 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering.
** Image category 2 has the least number of strongest features: 34243.
** Using the strongest 34243 features from each of the other image categories.
Using K-Means clustering to create a 10 word visual vocabulary.
Number of features : 102729
Number of clusters (K) : 10
Initializing cluster centers...100.00%.
Clustering...completed 27/100 iterations (~0.27 seconds/iteration)...converged in 27 iterations.
Finished creating Bag-Of-Features
Encoding images using Bag-Of-Features.
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Encoding 9567 images...done.
Elapsed time is 218.313246 seconds.
Creating Visual Vocabulary for image training data store # 1 out of 1
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations. ** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 22323 images...done. Extracted 661030 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering. Image category 2 has the least number of strongest features: 80365. Using the strongest 80365 features from each of the other image categories.
Using K-Means clustering to create a 20 word visual vocabulary.
Number of features : 241095
Number of clusters (K) : 20
Initializing cluster centers...100.00%.
Clustering...completed 29/100 iterations (~0.71 seconds/iteration)...converged in 29 iterations.
Finished creating Bag-Of-Features
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations. ** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 9567 images...done. Extracted 283449 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering. Image category 2 has the least number of strongest features: 34243. Using the strongest 34243 features from each of the other image categories.
Using K-Means clustering to create a 20 word visual vocabulary.
Number of features : 102729
Number of clusters (K) : 20
Initializing cluster centers...100.00%.
Clustering...completed 34/100 iterations (~0.37 seconds/iteration)...converged in 34 iterations.
Finished creating Bag-Of-Features
DONE.
Creating Visual Vocabulary for image training data store # 1 out of 1
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations. ** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 22323 images...done. Extracted 661030 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering. Image category 2 has the least number of strongest features: 80365. Using the strongest 80365 features from each of the other image categories.
Using K-Means clustering to create a 50 word visual vocabulary.
Number of features : 241095
Number of clusters (K) : 50
Initializing cluster centers...100.00%.
Clustering...completed 31/100 iterations (~0.84 seconds/iteration)...converged in 31 iterations.
Finished creating Bag-Of-Features
Image category 1: BuiltUp
Image category 2: NonBuiltUp
Image category 3: Slum
Selecting feature point locations using the Detector method.
Extracting SURF features from the selected feature point locations. ** detectSURFFeatures is used to detect key points for feature extraction.
Extracting features from 9567 images...done. Extracted 283449 features.
Keeping 70 percent of the strongest features from each category.
Balancing the number of features across all image categories to improve clustering. Image category 2 has the least number of strongest features: 34243. Using the strongest 34243 features from each of the other image categories.
Using K-Means clustering to create a 50 word visual vocabulary.
Number of features : 102729
Number of clusters (K) : 50
Initializing cluster centers...100.00%.
Clustering...completed 21/100 iterations (~0.39 seconds/iteration)...converged in 21 iterations.
Finished creating Bag-Of-Features
Vocabulary size: 10
Creating Feature Table for image training data store # 1 out of 1
Creating Feature Table for image testing data store # 1 out of 1
Vocabulary size: 20
Creating Feature Table for image training data store # 1 out of 1
Creating Feature Table for image testing data store # 1 out of 1
Vocabulary size: 50
Creating Feature Table for image training data store # 1 out of 1
Creating Feature Table for image testing data store # 1 out of 1
-----------------------------------------------------------------
DONE.
vocabulary size 10
[x] create BoVW
[x] convert to table
vocabulary size 20
[x] create BoVW
[x] convert to table
vocabulary size 50
[x] create BoVW
[x] convert to table