Scene Categorization from Contours: Medial Axis Based Salience Measures

Bibliographic Details
Title:	Scene Categorization from Contours: Medial Axis Based Salience Measures
Authors:	Rezanejad, Morteza, Downs, Gabriel, Wilder, John, Walther, Dirk B., Jepson, Allan, Dickinson, Sven, Siddiqi, Kaleem
Publication Year:	2018
Collection:	Computer Science
Subject Terms:	Computer Science - Computer Vision and Pattern Recognition
More Details:	The computer vision community has witnessed recent advances in scene categorization from images, with the state-of-the art systems now achieving impressive recognition rates on challenging benchmarks such as the Places365 dataset. Such systems have been trained on photographs which include color, texture and shading cues. The geometry of shapes and surfaces, as conveyed by scene contours, is not explicitly considered for this task. Remarkably, humans can accurately recognize natural scenes from line drawings, which consist solely of contour-based shape cues. Here we report the first computer vision study on scene categorization of line drawings derived from popular databases including an artist scene database, MIT67, and Places365. Specifically, we use off-the-shelf pre-trained CNNs to perform scene classification given only contour information as input and find performance levels well above chance. We also show that medial-axis based contour salience methods can be used to select more informative subsets of contour pixels and that the variation in CNN classification performance on various choices for these subsets is qualitatively similar to that observed in human performance. Moreover, when the salience measures are used to weight the contours, as opposed to pruning them, we find that these weights boost our CNN performance above that for unweighted contour input. That is, the medial axis based salience weights appear to add useful information that is not available when CNNs are trained to use contours alone.
Document Type:	Working Paper
Access URL:	http://arxiv.org/abs/1811.10524
Accession Number:	edsarx.1811.10524
Database:	arXiv

FullText	Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/1811.10524 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20181126&spage=&pages=&title=Scene Categorization from Contours: Medial Axis Based Salience Measures&atitle=Scene%20Categorization%20from%20Contours%3A%20Medial%20Axis%20Based%20Salience%20Measures&aulast=Rezanejad%2C%20Morteza&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries
Header	DbId: edsarx DbLabel: arXiv An: edsarx.1811.10524 RelevancyScore: 981 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 981.470642089844
IllustrationInfo
Items	– Name: Title Label: Title Group: Ti Data: Scene Categorization from Contours: Medial Axis Based Salience Measures – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Rezanejad%2C+Morteza%22">Rezanejad, Morteza</searchLink><br /><searchLink fieldCode="AR" term="%22Downs%2C+Gabriel%22">Downs, Gabriel</searchLink><br /><searchLink fieldCode="AR" term="%22Wilder%2C+John%22">Wilder, John</searchLink><br /><searchLink fieldCode="AR" term="%22Walther%2C+Dirk+B%2E%22">Walther, Dirk B.</searchLink><br /><searchLink fieldCode="AR" term="%22Jepson%2C+Allan%22">Jepson, Allan</searchLink><br /><searchLink fieldCode="AR" term="%22Dickinson%2C+Sven%22">Dickinson, Sven</searchLink><br /><searchLink fieldCode="AR" term="%22Siddiqi%2C+Kaleem%22">Siddiqi, Kaleem</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2018 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink> – Name: Abstract Label: Description Group: Ab Data: The computer vision community has witnessed recent advances in scene categorization from images, with the state-of-the art systems now achieving impressive recognition rates on challenging benchmarks such as the Places365 dataset. Such systems have been trained on photographs which include color, texture and shading cues. The geometry of shapes and surfaces, as conveyed by scene contours, is not explicitly considered for this task. Remarkably, humans can accurately recognize natural scenes from line drawings, which consist solely of contour-based shape cues. Here we report the first computer vision study on scene categorization of line drawings derived from popular databases including an artist scene database, MIT67, and Places365. Specifically, we use off-the-shelf pre-trained CNNs to perform scene classification given only contour information as input and find performance levels well above chance. We also show that medial-axis based contour salience methods can be used to select more informative subsets of contour pixels and that the variation in CNN classification performance on various choices for these subsets is qualitatively similar to that observed in human performance. Moreover, when the salience measures are used to weight the contours, as opposed to pruning them, we find that these weights boost our CNN performance above that for unweighted contour input. That is, the medial axis based salience weights appear to add useful information that is not available when CNNs are trained to use contours alone. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/1811.10524" linkWindow="_blank">http://arxiv.org/abs/1811.10524</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.1811.10524
PLink	https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.1811.10524
RecordInfo	BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general Titles: – TitleFull: Scene Categorization from Contours: Medial Axis Based Salience Measures Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Rezanejad, Morteza – PersonEntity: Name: NameFull: Downs, Gabriel – PersonEntity: Name: NameFull: Wilder, John – PersonEntity: Name: NameFull: Walther, Dirk B. – PersonEntity: Name: NameFull: Jepson, Allan – PersonEntity: Name: NameFull: Dickinson, Sven – PersonEntity: Name: NameFull: Siddiqi, Kaleem IsPartOfRelationships: – BibEntity: Dates: – D: 26 M: 11 Type: published Y: 2018
ResultId	1