Download presentation
Presentation is loading. Please wait.
Published byAmberlynn Gibbs Modified over 9 years ago
1
PRESENTATION REU IN COMPUTER VISION 2014 AMARI LEWIS CRCV UNIVERSITY OF CENTRAL FLORIDA
2
IMPLEMENTING DIFFERENT WAYS TO IMPROVE PICTURES… Original The top image combines the different channels and uses convolution F *h= Σ Σ f(k,l)h(-k,-l) F= image H=kernel
3
COMBINE CHANNELS
4
GAUSSIAN Type of smoothing, a weighted average of the surrounding pixels using this formula: The sigma value determines the amount of ‘blurr’ the image will display. Gaussian smoothing Original
5
‘LAPLACIAN’ Finds the 2 nd Derivative of Gaussian
6
HISTOGRAM – USED TO REPRESENT EACH COLOR IN THE IMAGE OBSERVE BELOW
7
EDGE DETECTION- Roberts Roberts: finds edges using the Roberts approximation to the derivative. It returns edges at those points where the gradient of I is maximum. Canny Uses two thresholds to determine between weak and strong edges Canny Roberts
8
EDGE DETECTION WITH THRESHOLD Sobel X: [1 0 -1, 2 0 -2, 1 0 -1] Y: [1 2 1, 0 0 0, -1 -2 -1] Calculates: √(d/x)²+(d/dy)²
9
PYRAMIDS
10
ADABOOST – FACE DETECTION Boosting defines a classifier using an additive model F(x) = ∂1f1(x) +∂2f2(x)+∂3f3(x)…. F:strong classifier X- feature vectors Sigma= weight f – weak classifiers
11
TRIAL 2
12
SVM SVM (Support Vector Machine) classifier is able to test trained data to analyze and divide results. (object ore non—object) This is an example of linear classification Linearsvm calculates : f(x) = w^Tx+b where w is the normal line or weight vector and b is the bias
13
RESIZING MULTIPLE IMAGES THROUGH FOR LOOPS..
16
LUCAS KANADE (LEAST OF SQUARES) Optical flow equation- Considers a 3x3 window
17
Lucas Kanade
20
OPTICAL FLOW
22
LUCAS KANADE WITH PYRAMIDS
24
CLUSTERING, BAG OF FEATURES
25
THE PROJECT I’M INTERESTED IN WORKING ON THE APPLICATIONS OF LIGHT FIELDS IN COMPUTER VISION AIDEAN SHARGHI
26
THANK YOU !! I APPRECIATE THE OPPORTUNITY ONCE AGAIN AND I AM LEARNING A LOT FROM THIS EXPERIENCE THANKS, OLIVER NINA DR. LOBO DR. SHAH
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.