Professional Documents
Culture Documents
Outline
• The Problem of Object Recognition
• Approaches to Object Recognition
• Requirements and Performance Criteria
• Representation Schemes
• Matching Schemes
• Example Systems
• Indexing
• Grouping
• Error Analysis
Problem Statement
• Given some knowledge of how certain objects
may appear and an image of a scene possibly
containing those objects, report which objects are
present in the scene and where.
• Representation schemes
– Object-centered
– Viewer-centered
Approaches Differ According To:
(cont’d)
• Matching scheme
– Geometry-based
– Appearance-based
• Robust
– Noise (i.e., sensor noise)
– Local errors in early processing modules (e.g., edge
detection)
– Illumination/Shadows
– Partial occlusion (i.e., self and from other objects)
– Intrinsic shape distortions (i.e., non-rigid objects)
Performance Criteria
• Scope
– What kind of objects can be recognized and in what
kinds of scenes ?
• Robustness
– Does the method tolerate reasonable amounts of noise
and occlusion in the scene ?
– Does it degrade gracefully as those tolerances are
exceeded ?
Performance Criteria (cont’d)
• Efficiency
– How much time and memory are required to search the
solution space ?
• Accuracy
– Correct recognition
– False positives (wrong recognitions)
– False negatives (missed recognitions)
Object-centered Representation (cont’d)
(1) Geometry-based
explore correspondences
between model and scene
features
(2) Appearance-based
represent objects from all
possible viewpoints and all
possible illumination
directions.
Geometry-based Matching