Download presentation
Presentation is loading. Please wait.
Published bySamson Gaines Modified over 9 years ago
1
WEEK 1-2 ALEJANDRO TORROELLA
2
CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAYING THE SEPARATE CHANNELS
3
Hue: Value: Saturation:
4
ROBERTS AND SOBEL EDGE DETECTORS ON BOTH RGB AND HSV CHANNELS
5
LAPLACIAN OF GAUSSIAN AND SEPARABILITY
6
Sigma = 1.2, Kernel Size = 9x9
7
CANNY EDGE DETECTOR
8
Sigma = 1.2, Kernel Size = 9x9, Threshold = 0.05
9
IMPROVING LEGIBILITY
11
HARRIS CORNER DETECTOR
13
SIFT DENSE SAMPLING SCHEME
15
SVM TRAINING AND TESTING
16
Used two different kernels: Chi Squared and Histogram Intersections Histogram Intersection gave better results than Chi Squared. Results were still poor, but that’s probably because of low density SIFT descriptors and the way they were implemented. Increasing the density of the SIFT descriptors significantly improved the accuracy of classification. Accuracy_768 = [ histo, chi2 ] = [ 11.1233, 7.9295 ] Accuracy_3072 = [ histo, chi2 ] = [ 24.5595, 8.8106 ]
17
OPTICAL FLOW
18
=
19
THANK YOU FIN.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.