Make BoVW extractor rotation invariant

Vocabulary for image training data store # 1 out of 5

Creating Bag-Of-Features.

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: 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 1974 images...done. Extracted 1704412 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 4 has the least number of strongest features: 41049. Using the strongest 41049 features from each of the other image categories.
Using K-Means clustering to create a 250 word visual vocabulary.
Number of features : 164196
Number of clusters (K) : 250
Initializing cluster centers...100.00%.
Clustering...completed 32/100 iterations (~0.83 seconds/iteration)...converged in 32 iterations.
Finished creating Bag-Of-Features

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: Slum
Encoding 1974 images...done. Elapsed time is 462.176249 seconds.

Creating Visual Vocabulary for image training data store # 2 out of 5

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: 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 3098 images...done. Extracted 1641367 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 4 has the least number of strongest features: 45881. Using the strongest 45881 features from each of the other image categories.
Using K-Means clustering to create a 125 word visual vocabulary.
Number of features : 183524
Number of clusters (K) : 125
Initializing cluster centers...100.00%.
Clustering...completed 21/100 iterations (~0.81 seconds/iteration)...converged in 21 iterations.
Finished creating Bag-Of-Features

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: Slum
Encoding 3098 images...done. Elapsed time is 506.558481 seconds.

Creating Visual Vocabulary for image training data store # 3 out of 5

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: 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 5585 images...done. Extracted 1559813 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: 41427. Using the strongest 41427 features from each of the other image categories.
Using K-Means clustering to create a 84 word visual vocabulary.
Number of features : 165708
Number of clusters (K) : 84
Initializing cluster centers...100.00%.
Clustering...completed 18/100 iterations (~0.68 seconds/iteration)...converged in 18 iterations.
Finished creating Bag-Of-Features

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: Slum
Encoding 5585 images...done. Elapsed time is 649.923009 seconds.

Creating Visual Vocabulary for image training data store # 4 out of 5

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: 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 12662 images...done. Extracted 1374853 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: 22674. Using the strongest 22674 features from each of the other image categories.
Using K-Means clustering to create a 63 word visual vocabulary.
Number of features : 90696
Number of clusters (K) : 63
Initializing cluster centers...100.00%.
Clustering...completed 30/100 iterations (~0.40 seconds/iteration)...converged in 30 iterations.
Finished creating Bag-Of-Features

Creating Visual Vocabulary for image training data store # 5 out of 5

Image category 1: BuiltUp
Image category 2: Mixed
Image category 3: NonBuiltUp
Image category 4: 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 53289 images...done. Extracted 875081 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: 6630. Using the strongest 6630 features from each of the other image categories.
Using K-Means clustering to create a 50 word visual vocabulary.
Number of features : 26520
Number of clusters (K) : 50
Initializing cluster centers...100.00%.
Clustering...completed 30/100 iterations (~0.11 seconds/iteration)...converged in 30 iterations.
Finished creating Bag-Of-Features