Book ChapterDOI
Invariant Features for Gray Scale Images
Hanns Schulz-Mirbach
- pp 1-14
Reads0
Chats0
TLDR
This paper considers image rotations and translations and presents algorithms for constructing invariant features and develops algorithms for recognizing several objects in a single scene without the necessity to segment the image beforehand.Abstract:
Invariant features are image characteristics which remain unchanged under the action of a transformation group. We consider in this paper image rotations and translations and present algorithms for constructing invariant features. After briefly sketching the theoretical background we develop algorithms for recognizing several objects in a single scene without the necessity to segment the image beforehand. The objects can be rotated and translated independently. Moderate occlusions are tolerable. Furthermore we show how to use these techniques for the recognition of articulated objects. The methods work directly with the gray values and do not rely on the extraction of geometric primitives like edges or corners in a preprocessing step. All algorithms have been implemented and tested both on synthetic and real image data. We present some illustrative experimental results.read more
Citations
More filters
Journal ArticleDOI
Features for image retrieval: an experimental comparison
TL;DR: An experimental comparison of a large number of different image descriptors for content-based image retrieval is presented and the often used, but very simple, color histogram performs well in the comparison and thus can be recommended as a simple baseline for many applications.
Journal ArticleDOI
Integral Invariants for Shape Matching
TL;DR: Numerical results on shape matching demonstrate that this framework can match shapes despite the deformation of subparts, missing parts and noise, and a notion of distance between shapes is defined.
Journal ArticleDOI
Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization
TL;DR: A vision-based approach to mobile robot localization that integrates an image-retrieval system with Monte Carlo localization that is able to globally localize a mobile robot, to reliably keep track of the robot's position, and to recover from localization failures.
Journal ArticleDOI
Vehicle Logo Recognition Using a SIFT-Based Enhanced Matching Scheme
TL;DR: It is shown that the enhanced matching approach proposed in this paper boosts the recognition accuracy compared with the standard SIFT-based feature-matching method.
Proceedings ArticleDOI
Robust vision-based localization for mobile robots using an image retrieval system based on invariant features
TL;DR: A vision-based approach to mobile robot localization, that integrates an image retrieval system with Monte-Carlo localization that is robust against distortion and occlusions, and able to globally localize itself to reliably keep tracking of its position and to recover from localization failures.
References
More filters
Journal ArticleDOI
Recognizing solid objects by alignment with an image
TL;DR: A new method for computing a transformation from a three-dimensional model coordinate frame to the two-dimensional image coordinate frame, using three pairs of model and image points, is developed, showing that this transformation always exists for three noncollinear points, and is unique up to a reflective ambiguity.
Journal ArticleDOI
Geometric invariants and object recognition
TL;DR: The role of the general invariance concept in object recognition is discussed, the classical and recent literature on projective invariance is reviewed, and shape descriptors, computed from the geometry of the shape, that remain unchanged under geometric transformations such as changing the viewpoint are reviewed.
Book
Recognizing Planar Objects Using Invariant Image Features
TL;DR: Translation, rotation, scale and contrast invariants, algebraic and projective invariant, and recognition of partially occluded objects are summarized.