Download presentation
Presentation is loading. Please wait.
Published byAlisha Crawford Modified over 8 years ago
1
Lecture 3 Template Matching Edge Detection
2
2 Processes for Assignment 1 Understand Image Format Pre Processing - Gaussian, Mean Filter to clean up the image Thresholding - Binary Image Segmentation - Blob Coloring 8-neighbor Thinning Template Matching - Similar to convolution Template - “Filter” - Sum Square Difference skeleton กุ้ง
3
3 Template Matching You may have a template Put a template, do subtraction low numbe = good match Number = 0
4
4 Not only documents Chips - need numbers bank checks in industrial - fixed font is enough Template Matching - Train your machine for fixed font OCR- Optical Character Recognition
5
5 Try matching a segment with every template The lowest score is the best match Preserve Aspect Ratio width/height Template Matching Rule of Thumb 8 12 Scale down Template Matching Templates
6
6 When people say edges, they means object contour Edge Detection - finding edge contours Contour Edge (something to do with shape) Texture Edge
7
7 Edge Detector Edge - Points in image with a lot of change in intensity Scan Line Edge Points x y Intensity Bluring (Smoothing) Step Edge
8
8 Simple Edge Detector edge else no edge Edge if I / X > 30 First Difference Image
9
9 First Difference We should blur the image first Use Gaussian Filter to reduce noise
10
10 First Difference
11
11 Second Derivative 0 = Edge First Derivative Blurring Second Derivative edge
12
12 Second Derivative = Edge Detector Using 2nd Derivative
13
13 Edge Detector Using 2nd Derivative Any zero Crossing Edge Zero-Crossing Change + to -, - to + In 2D
14
14 Edge Detector by Photoshop (1) 1. Open peppers.jpg 2. Change to Grayscale
15
15 Edge Detector by Photoshop(2) 3. Custom Filter
16
16 Edge Detector by Photoshop(2) 3. Custom Filter
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.