a model-based detector of curvilinear regions
Definition of a model-based detector of curvilinear
regions
Cédric LEMAITRE1, Johel MITERAN1 and Jiri MATAS2
1 LE2I Faculté Mirande Aile H. Université de Bourgogne BP 47870 21078 Dijon 2 Center for Machine Perception, Dept.of Cybernetics, CTU Prague, Karlovo nam 13,
CZ 12 135
1 {cedric.lemaitre,miteranj}@u-bourgogne.fr 2 matas@cmp.felk.cvut.cz
Abstract. This paper describes a new approach for detection of curvilinear regions. These features detection can be useful for any matching based algorithm such as stereoscopic vision. Our detector is based on curvilinear structure model, defined observing the real world. Then, we propose a multi-scale search algorithm of curvilinear regions and we report some preliminary results.
Introduction
Detecting specific features has been shown to be useful in many computer vision applications such as stereoscopic vision [1, 2] or object recognition [3], image retrieval [4]. A number of feature detectors [1, 2, 5-9] have been proposed in the literature. As these detectors can be combined in order to improve the recognition performances, it can be useful to add new features.
We propose in this paper to define a new model of such features, based on the extraction of curvilinear regions, often simply named: line extraction. There are a huge number of application fields where curvilinear structures extraction is used. In photogrammetic and remote sensing tasks, it is used to extract roads, railroads or rivers from satellite or low-resolution aerial imagery [10-12], which can be used for the capture or update of data for geographic information systems. Moreover, it is useful in medical imaging for the extraction of anatomical features or simply for the segmentation of medical images from CT or MR devices [13-15].
A few models [12, 14, 16-18] have been described for curvilinear structures detection, often application specific (for roads, vessels). Our aim is to define here a superset of these models, which can be used in the general case of object recognition allowing building an affine-invariant detector.
Steger [18] classified previous work in curvilinear detection into three families. The first approach detects lines by considering the gray values of the image only and uses purely local criteria. The second approach regards lines as object having parallel
Definition of Translation_英语学习_外语学习_教育专区。definition of translationDefinition of Translation WEEK 2 Definition of Translation ? 把已说出或写出的话...
I. Definition of Accounting Accounting is a service activity. Its function is to provide quantitative information, primarily financial in nature, about ...
Definition of Love_英语学习_外语学习_教育专区。Definition of Love Love, it is such a familiar word to all of us. We talk it everyday. However, it...
(一)Definition of Literary Terms 1. Art for Art’s Sake 2’x10 The idea was raised by an Irish author Oscar Wilde (1854-1900), who held that ...
What’s the definition of happiness? The definition of happiness in the dictionary is emotions experienced when in a state of well-being such as pleased...
Definition of Culture(U3)_外语学习_教育专区。英美英语文化Definition of Culture Culture is shared learned behavior which is transmitted from one generation ...
The Definition of Language When used as a general concept, "language" refers to the cognitive faculty that enables humans to learn and use systems of ...
Definition of the UPH 2页 免费Definition of the Pop C...
Definition of Derivative 浸会大学高数浸会大学高数隐藏>> 1 De?nition of Derivative 4. f (x) [(x+?x)2 ?1]?[x2 ?1] = lim ?x ?x→0 = ·...
The Definition of Language When used as a general concept, "language" refers to the cognitive faculty that enables humans to learn and use systems of ...
热门文档