CSSE463: Image Recognition Day 25

Slides:

Advertisements

Similar presentations

Computer vision: models, learning and inference Chapter 13 Image preprocessing and feature extraction.

Advertisements

Lecture 31: Modern object recognition

Presenter: Hoang, Van Dung

Instructor: Mircea Nicolescu Lecture 15 CS 485 / 685 Computer Vision.

Facial feature localization Presented by: Harvest Jang Spring 2002.

Vision-Based Analysis of Small Groups in Pedestrian Crowds Weina Ge, Robert T. Collins, R. Barry Ruback IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE.

Lecture 5 Template matching

Content-based Image Retrieval CE 264 Xiaoguang Feng March 14, 2002 Based on: J. Huang. Color-Spatial Image Indexing and Applications. Ph.D thesis, Cornell.

Feature matching and tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on.

Feature tracking Class 5 Read Section 4.1 of course notes Read Shi and Tomasi’s paper on good features.

CSSE463: Image Recognition Day 30 Due Friday – Project plan Due Friday – Project plan Evidence that you’ve tried something and what specifically you hope.

Object Recognition Using Geometric Hashing

Scale Invariant Feature Transform (SIFT)

Smart Traveller with Visual Translator. What is Smart Traveller? Mobile Device which is convenience for a traveller to carry Mobile Device which is convenience.

Computer Vision P. Schrater Spring 2003

Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.

Overview Introduction to local features

Presenting by, Prashanth B R 1AR08CS035 Dept.Of CSE. AIeMS-Bidadi. Sketch4Match – Content-based Image Retrieval System Using Sketches Under the Guidance.

Computer vision.

CSSE463: Image Recognition Day 30 This week This week Today: motion vectors and tracking Today: motion vectors and tracking Friday: Project workday. First.

1 Interest Operators Harris Corner Detector: the first and most basic interest operator Kadir Entropy Detector and its use in object recognition SIFT interest.

Recognition and Matching based on local invariant features Cordelia Schmid INRIA, Grenoble David Lowe Univ. of British Columbia.

Local invariant features Cordelia Schmid INRIA, Grenoble.

Topic 10 - Image Analysis DIGITAL IMAGE PROCESSING Course 3624 Department of Physics and Astronomy Professor Bob Warwick.

10/24/2015 Content-Based Image Retrieval: Feature Extraction Algorithms EE-381K-14: Multi-Dimensional Digital Signal Processing BY:Michele Saad

Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.

Segmentation: Region Based Methods Region-based methods –iterative methods based on region merging and/or splitting based on the degree of similarity of.

December 9, 2014Computer Vision Lecture 23: Motion Analysis 1 Now we will talk about… Motion Analysis.

Object detection, deep learning, and R-CNNs

Histograms of Oriented Gradients for Human Detection(HOG)

Automatic License Plate Location Using Template Matching University of Wisconsin - Madison ECE 533 Image Processing Fall 2004 Project Kerry Widder.

Jiu XU, Axel BEAUGENDRE and Satoshi GOTO Computer Sciences and Convergence Information Technology (ICCIT), th International Conference on 1 Real-time.

Pictorial Structures and Distance Transforms Computer Vision CS 543 / ECE 549 University of Illinois Ian Endres 03/31/11.

CSSE463: Image Recognition Day 25 Today: introduction to object recognition: template matching Today: introduction to object recognition: template matching.

Representation in Vision Derek Hoiem CS 598, Spring 2009 Jan 22, 2009.

Real-time foreground object tracking with moving camera P Martin Chang.

Finding Clusters within a Class to Improve Classification Accuracy Literature Survey Yong Jae Lee 3/6/08.

Particle Filtering for Symmetry Detection and Segmentation Pramod Vemulapalli.

Non-linear filtering Example: Median filter Replaces pixel value by median value over neighborhood Generates no new gray levels.

WLD: A Robust Local Image Descriptor Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikäinen, Xilin Chen, Wen Gao 报告人：蒲薇榄.

Face recognition using Histograms of Oriented Gradients

Another Example: Circle Detection

SIFT Scale-Invariant Feature Transform David Lowe

Lecture 13: Feature Descriptors and Matching

Lecture 07 13/12/2011 Shai Avidan הבהרה: החומר המחייב הוא החומר הנלמד בכיתה ולא זה המופיע / לא מופיע במצגת.

Distinctive Image Features from Scale-Invariant Keypoints

Content-based Image Retrieval

Feature description and matching

Object detection as supervised classification

A Tutorial on HOG Human Detection

CSE 455 – Guest Lectures 3 lectures Contact Interest points 1

HCI / CprE / ComS 575: Computational Perception

Aim of the project Take your image Submit it to the search engine

SIFT keypoint detection

CSSE463: Image Recognition Day 26

CSSE463: Image Recognition Day 30

CSSE463: Image Recognition Day 25

Midterm Exam Closed book, notes, computer Similar to test 1 in format:

AHED Automatic Human Emotion Detection

Comparing Images Using Hausdorff Distance

Introduction to Artificial Intelligence Lecture 24: Computer Vision IV

CSSE463: Image Recognition Day 25

CSSE463: Image Recognition Day 30

AHED Automatic Human Emotion Detection

Midterm Exam Closed book, notes, computer Similar to test 1 in format:

CSSE463: Image Recognition Day 26

Feature descriptors and matching

CSSE463: Image Recognition Day 30

Recognition and Matching based on local invariant features

Presentation transcript:

CSSE463: Image Recognition Day 25 Today: introduction to template matching: a simple method for object detection Questions? Discuss literature review, rubric, examples of student work. http://abstrusegoose.com/288 about MATLAB: currently down.

Template matching (Sonka, 6.4) Idea: you are looking for an exact match of an object (described by a sub-image, a template) in an image Ideal world: it matches exactly

Template matching (Sonka, 6.4) Algorithm: Evaluate a match criterion at every image location (plus size, reflection, and rotation, if those variations are expected) A “match” is a local maximum of the criterion above a threshold Q1 Q1

Template matching (Sonka, 6.4) One match criterion: Correlation between the template and the image. Note: just use the template as a filter! Simplistic implementation Smarter implementation

Correlation Just the dot product between the template and a neighborhood in the image. Idea: high correlation when the template matches. Demo Idea: we are using the object as a filter!

Correlation Just the dot product between the template and a neighborhood in the image. Idea: high correlation when the template matches. Problem: always high correlation when matching with a plain bright region Idea: we are using the object as a filter! Q2-3

Correlation Just the dot product between the template and a neighborhood in the image. Idea: high correlation when the template matches. Problem: always high correlation when matching with a plain bright region Solution: Normalize the template and each region by subtracting each’s mean from itself before taking dot product Q4-5

Other matching algorithms Chamfering (Hausdorff distance): http://www.cs.cornell.edu/~dph/hausdorff/hausdorff1.html Springs and templates (Crandall and Huttenlocher) http://www.cs.cornell.edu/~dph/papers/cvpr07.pdf Even neural nets (deep or not) need to operate at various scales/patches of the image to detect objects.

Edges are more robust features for detection than intensities Idea: Histogram of Oriented Gradients (HOG features) Sources: Guest lecture by Trenton Tabor, RHIT ‘12 Sonka, et al. text, section 10.6.3 N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection", Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.

What are HOG features? Idea: Histogram of Oriented Gradients (HOG features) [1] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection", Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.

Misc [1] N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection", Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.