Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition

Background: Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or texture. Methods: We propose a trainable filte...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 35; číslo 2; s. 490 - 503
Hlavní autoři:	Azzopardi, G., Petkov, N.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Los Alamitos, CA IEEE 01.02.2013 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Applied sciences Artificial Intelligence Biological and medical sciences Computer science; control theory; systems Computer vision Detection, estimation, filtering, equalization, prediction Detectors Exact sciences and technology Eye and associated structures. Visual pathways and centers. Vision Feature detection feature representation Fundamental and applied biological sciences. Psychology Gabor filters Handwriting recognition Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Information, signal and communications theory medical information systems object recognition optical character recognition Pattern recognition Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Prototypes Recall Recognition Reproducibility of Results Sensitivity and Specificity Shape Signal and communications theory Signal, noise Studies Subtraction Technique Surface layer Telecommunications and information theory Texture Vectors Vertebrates: nervous system and sense organs Gabor filter Computer vision Visual cortex Information system feature representation shape Bifurcation Retina Selectivity medical information systems Pattern recognition Character recognition Object recognition Texture Feature detection Efficiency Optical character recognition Scene analysis Classification Filter bank Circulatory system Manuscript character Medical application
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Background: Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or texture. Methods: We propose a trainable filter which we call Combination Of Shifted FIlter REsponses (COSFIRE) and use for keypoint detection and pattern recognition. It is automatically configured to be selective for a local contour pattern specified by an example. The configuration comprises selecting given channels of a bank of Gabor filters and determining certain blur and shift parameters. A COSFIRE filter response is computed as the weighted geometric mean of the blurred and shifted responses of the selected Gabor filters. It shares similar properties with some shape-selective neurons in visual cortex, which provided inspiration for this work. Results: We demonstrate the effectiveness of the proposed filters in three applications: the detection of retinal vascular bifurcations (DRIVE dataset: 98.50 percent recall, 96.09 percent precision), the recognition of handwritten digits (MNIST dataset: 99.48 percent correct classification), and the detection and recognition of traffic signs in complex scenes (100 percent recall and precision). Conclusions: The proposed COSFIRE filters are conceptually simple and easy to implement. They are versatile keypoint detectors and are highly effective in practical computer vision applications.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2012.106