Download presentation
Presentation is loading. Please wait.
Published byMaryann Sims Modified over 9 years ago
1
Kylie Gorman WEEK 1-2 REVIEW
2
CONVERTING AN IMAGE FROM RGB TO HSV AND DISPLAY CHANNELS
3
Original HSV Version
4
Hue Saturation Value
5
EDGE DETECTION
6
Sobel and Roberts Sobel X Sobel Y Roberts X Roberts Y
7
Canny Edge Detector 1. Smooth image with Gaussian filter 2. Compute derivative of filtered image 3. Find magnitude and orientation of gradient 4. Apply “Non- maximum Suppression” 5. Apply “Hysteresis Threshold”
8
HARRIS CORNER DETECTOR
9
Harris Corner Steps Compute x and y derivatives of image Compute products of derivatives at every pixel: Ix2 Ixy Iy2 Compute the sums of the products of the derivatives at each pixel Place each pixel into a matrix H Compute R = Det(H) – k(Trace(H))^2 Threshold on value of R
10
My Own Implementation
11
Harris Corner Function in MATLAB
12
SCALE INVARIANT FEATURE TRANSFORM (SIFT)
13
SIFT Algorithm: Finding Keypoints Use Difference-of-Gaussian Function Good approximation of Laplacian of Gaussian, but faster to compute Construct Scale Space Key Point Localization Use Scale Space to Find Extrema Throw Out Poorly Defined Peaks Orientation Assignment Multiple Orientations Improves Stability of Matching Keypoint Descriptor Computed from Local Image Gradients
14
SIFT using Vl_feat
15
Using SIFT to Match Same Image
16
Different Images
17
SUPPORT VECTOR MACHINES (SVM)
18
Linear SVM
19
Multi-Class SVM
20
OPTICAL FLOW
21
Optical Flow with Lucas-Kanade The Optical Flow Equation f x u + f y v = -f t has 2 unknown variables 3x3 window gives 9 equations with 2 unknown variables Put equations into matrix to get Au = f t To solve, multiply by the transpose of A: A T Au = A T f t u = (A T A) -1 A T f t Least Square Fit Solve for u and v
22
Lucas-Kanade with Images
23
Lucas-Kanade with Video Original Clip: http://www.youtube.com/watch?v=y6r8i_008SU
24
Lucas-Kanade with Vector Results
25
With Roberts Derivative Resized Image to ½ Original Resized Image to ¼ Original
26
With Sobel Derivative Resized Image to ½ Original Resized Image to ¼ Original
27
ADA BOOST
28
ADA Boost Expert is a pattern and a threshold Convolve an image with pattern and plot value on a number line Search for threshold
29
Face Detection
30
BAG OF WORDS/ FEATURES
31
Bag of Words/ Features Step One: Feature Extraction Extract Regions (SIFT, Harris) Compute Descriptors (SIFT) Step Two: Quantization Find Clusters and Frequencies (K-means) Step Three: Classification Compute Distance Matrix Classification (SVM)
33
PROJECT POSSIBILITIES
34
Final Project Project: Color-Attributes-Related Image Retrieval Graduate Student: Yang Zhang Goal: Enable people to retrieve an image according to an object with attributes or attributes alone. The project will focus on color as the starting attribute. Program: MATLAB
35
Steps 1. Validating Model: Download other code and compare it to our own code. 2. Coding: Add more features to the system the improve its performance. 3. Collecting Dataset: There are not any existing color image datasets on the Internet. Use automatic image collecting tool to create our own color object dataset. 4. Possible Bonus: Implement novel ideas about general attribute image retrieval system. Determine if it is effective or not.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.