lec18 - Announcements HW 4 to be posted later today It does...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1 CSE152, Spr 11 Intro Computer Vision Recognition I Introduction to Computer Vision CSE 152 Lecture 18 CSE152, Spr 11 Intro Computer Vision Announcements • HW 4 to be posted later today. • It does not require a lot of coding, but does require understanding Order of material changed – we’ll first cover recognition so that you’re prepared for assignment. Then return to motion. CSE152, Spr 11 Intro Computer Vision Recognition Given a database of objects and an image determine what, if any of the objects are present in the image. CSE152, Spr 11 Intro Computer Vision Face Camel Mammal Barbara Steele Two challenges: Recognizing instances Recognizing categories Categories vs. Instances CSE152, Spr 11 Intro Computer Vision Object Recognition: The Problem Given: A database D of “known” objects and an image I: 1. Determine which (if any) objects in D appear in I 2. Determine the pose (rotation and translation) of the object Segmentation (where is it 2D) Recognition (what is it) Pose Est. (where is it 3D) WHAT AND WHERE!!! CSE152, Spr 11 Intro Computer Vision Recognition Challenges Within-class variability – Different objects within the class have different shapes or different material characteristics – Deformable – Articulated – Compositional Pose variability: – 2-D Image transformation (translation, rotation, scale) – 3-D Pose Variability (perspective, orthographic projection) Lighting – Direction (multiple sources & type) – Color – Shadows Occlusion – partial Clutter in background -> false positives
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
2 CSE152, Spr 11 Intro Computer Vision Object Recognition Issues: How general is the problem? 2D vs. 3D range of viewing conditions available context segmentation cues What sort of data is best suited to the problem? Whole images Local 2D features (color, texture, 3D (range) data What information do we have in the database? Collection of images? 3-D models? Learned representation? Learned classifiers? How many objects are involved? small: brute force search large: ?? CSE152, Spr 11 Intro Computer Vision A Rough Recognition Spectrum Appearance-Based Recognition (Eigenface, Fisherface) Local Features + Spatial Relations 3-D Model-Based Recognition Geometric Invariants Image Abstractions/ Volumetric Primitives Shape Contexts Function Bags of Features Increasing Generality CSE152, Spr 11 Intro Computer Vision Appearance-Based Vision: A Pattern Classification Viewpoint 1. Feature Space + Nearest Neighbor 2. Dimensionality Reduction 3. Bayesian Classification 4. Appearance Manifolds CSE152, Spr 11 Intro Computer Vision Sketch of a Pattern Recognition Architecture Feature Extraction Classification Image (window) Object Identity Feature Vector CSE152, Spr 11
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 7

lec18 - Announcements HW 4 to be posted later today It does...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online