CHAPTER 4 Flashcards
(17 cards)
……….. is the ability of
software to identify objects,
places, people, writing and
actions in digital images
Recognition
Computers can use machine
vision technologies in
combination with a camera and
artificial intelligence (AI) software
to achieve………………….
image recognition
types of Object Recognition
- Model-based Object Recognition
- Generic Object Recognition
…………….Recognition relies upon the existence of a set of predefined objects.
Model-based Object Recognition
…………….. is identifying the category
membership of an object
contained in an image.
Generic object recognition
Main Steps
Preprocessing
Recognition
……………….A model database is built by establishing associations between features and models.
Preprocessing
………………Scene features are used to retrieve appropriate associations stored in the model database.
Recognition
Challenges
The appearance of an object can have a large range of variation due to:
– viewpoint changes
– shape changes (e.g., non-rigid objects)
– photometric effects
– scene clutter
Requirements
Invariance
Robustness
Robustness?
– Noise (i.e., sensor noise)
– Detection errors (e.g., edge or corner detection)
– Illumination/Shadows
– Partial occlusion (i.e., self and from other objects)
– Intrinsic shape distortions (i.e., non-rigid objects)
Invariance
– Geometric transformations (translation, rotation, scale)
* Caused by viewpoint changes due to camera/object motion
Performance Criteria
(1) Scope: What kind of objects can be recognized and in what kind of scenes
(2) Robustness: – Does the method tolerate reasonable amounts of noise and occlusion in the scene ?
– Does it degrade gracefully as those tolerances are exceeded ?
(3) Efficiency:– How much time and memory are required to search the solution space ?
(4) Accuracy:
– Correct recognition
– False positives (wrong recognitions) – False negatives (missed recognitions)
Object-centered Representation
A 3D model of the object is available.
Advantage: every view of the object is available.
Disadvantage: might not be easy to build.
Viewer-centered Representation
- Objects are described by a set of characteristic views or aspects
Advantages:
- Easier to build compared to object-centered.
- Matching is easier since it involves 2D information.
Disadvantages:
- Requires a large number of views
Matching Schemes
- Geometry-based
- Employ geometric features
- Appearance-based
- Represent objects from many possible viewpoints and illumination directions using dimensionality reduction
T/F Different views of the same object can give rise to widely different images!
T
