Academic Journal
Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation
| Τίτλος: | Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation |
|---|---|
| Συγγραφείς: | Mathuria, Aakanksha, Hammerstrom, Dan |
| Πηγή: | Proceedings of the International Conference on Neuromorphic Systems. :1-10 |
| Στοιχεία εκδότη: | ACM, 2019. |
| Έτος έκδοσης: | 2019 |
| Θεματικοί όροι: | Engineering, Isomorphisms (Mathematics) -- Data processing, Image processing -- Data processing, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, 02 engineering and technology, Optical data processing |
| Περιγραφή: | With recent developments in deep networks, there have been significant advances in visual object detection and recognition. However, some of these networks are still easily fooled/hacked and have shown "bag of features" failures. Some of this is due to the fact that even deep networks make only marginal use of the complex structure that exists in real-world images, even after training on huge numbers of images. Biology appears to take advantage of such a structure, but how? In our research, we are studying approaches for robust pattern matching using still, 2D Blocks World images based on graphical representations of the various components of an image. Such higher order information represents the "structure" of the visual object. Here we discuss how the structural information of an image can be captured in a Sparse Distributed Representation (SDR) loosely based on cortical circuits. We apply probabilistic graph isomorphism and subgraph isomorphism to our 2D Blocks World images and achieve O (1) and O (nk) complexity for an approximate match. The optimal match is an NP-Hard problem. The image labeled graph is created using OpenCV to find the object contours and objects' labels and a fixed radius nearest neighbor algorithm to build the edges between the objects. Pattern matching is done using the properties of SDRs. Our research shows the promise of applying graph-based neuromorphic techniques for pattern matching of images based on such structure. |
| Τύπος εγγράφου: | Article |
| Περιγραφή αρχείου: | application/pdf |
| DOI: | 10.1145/3354265.3354286 |
| Σύνδεσμος πρόσβασης: | https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1616&context=ece_fac https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=6654&context=open_access_etds https://pdxscholar.library.pdx.edu/ece_fac/610/ |
| Rights: | URL: https://www.acm.org/publications/policies/copyright_policy#Background |
| Αριθμός Καταχώρησης: | edsair.doi.dedup.....9fcbfeeecff7c20cc3d1b726f5c1a47e |
| Βάση Δεδομένων: | OpenAIRE |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://explore.openaire.eu/search/publication?articleId=doi_dedup___%3A%3A9fcbfeeecff7c20cc3d1b726f5c1a47e Name: EDS - OpenAIRE (ns324271) Category: fullText Text: View record at OpenAIRE |
|---|---|
| Header | DbId: edsair DbLabel: OpenAIRE An: edsair.doi.dedup.....9fcbfeeecff7c20cc3d1b726f5c1a47e RelevancyScore: 872 AccessLevel: 3 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 872.328552246094 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Mathuria%2C+Aakanksha%22">Mathuria, Aakanksha</searchLink><br /><searchLink fieldCode="AR" term="%22Hammerstrom%2C+Dan%22">Hammerstrom, Dan</searchLink> – Name: TitleSource Label: Source Group: Src Data: <i>Proceedings of the International Conference on Neuromorphic Systems</i>. :1-10 – Name: Publisher Label: Publisher Information Group: PubInfo Data: ACM, 2019. – Name: DatePubCY Label: Publication Year Group: Date Data: 2019 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Engineering%22">Engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Isomorphisms+%28Mathematics%29+--+Data+processing%22">Isomorphisms (Mathematics) -- Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing+--+Data+processing%22">Image processing -- Data processing</searchLink><br /><searchLink fieldCode="DE" term="%220202+electrical+engineering%2C+electronic+engineering%2C+information+engineering%22">0202 electrical engineering, electronic engineering, information engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%2202+engineering+and+technology%22">02 engineering and technology</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+data+processing%22">Optical data processing</searchLink> – Name: Abstract Label: Description Group: Ab Data: With recent developments in deep networks, there have been significant advances in visual object detection and recognition. However, some of these networks are still easily fooled/hacked and have shown "bag of features" failures. Some of this is due to the fact that even deep networks make only marginal use of the complex structure that exists in real-world images, even after training on huge numbers of images. Biology appears to take advantage of such a structure, but how? In our research, we are studying approaches for robust pattern matching using still, 2D Blocks World images based on graphical representations of the various components of an image. Such higher order information represents the "structure" of the visual object. Here we discuss how the structural information of an image can be captured in a Sparse Distributed Representation (SDR) loosely based on cortical circuits. We apply probabilistic graph isomorphism and subgraph isomorphism to our 2D Blocks World images and achieve O (1) and O (nk) complexity for an approximate match. The optimal match is an NP-Hard problem. The image labeled graph is created using OpenCV to find the object contours and objects' labels and a fixed radius nearest neighbor algorithm to build the edges between the objects. Pattern matching is done using the properties of SDRs. Our research shows the promise of applying graph-based neuromorphic techniques for pattern matching of images based on such structure. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Article – Name: Format Label: File Description Group: SrcInfo Data: application/pdf – Name: DOI Label: DOI Group: ID Data: 10.1145/3354265.3354286 – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1616&context=ece_fac" linkWindow="_blank">https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1616&context=ece_fac</link><br /><link linkTarget="URL" linkTerm="https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=6654&context=open_access_etds" linkWindow="_blank">https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=6654&context=open_access_etds</link><br /><link linkTarget="URL" linkTerm="https://pdxscholar.library.pdx.edu/ece_fac/610/" linkWindow="_blank">https://pdxscholar.library.pdx.edu/ece_fac/610/</link> – Name: Copyright Label: Rights Group: Cpyrght Data: URL: https://www.acm.org/publications/policies/copyright_policy#Background – Name: AN Label: Accession Number Group: ID Data: edsair.doi.dedup.....9fcbfeeecff7c20cc3d1b726f5c1a47e |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsair&AN=edsair.doi.dedup.....9fcbfeeecff7c20cc3d1b726f5c1a47e |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1145/3354265.3354286 Languages: – Text: Undetermined PhysicalDescription: Pagination: PageCount: 10 StartPage: 1 Subjects: – SubjectFull: Engineering Type: general – SubjectFull: Isomorphisms (Mathematics) -- Data processing Type: general – SubjectFull: Image processing -- Data processing Type: general – SubjectFull: 0202 electrical engineering, electronic engineering, information engineering Type: general – SubjectFull: Computer vision Type: general – SubjectFull: 02 engineering and technology Type: general – SubjectFull: Optical data processing Type: general Titles: – TitleFull: Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Mathuria, Aakanksha – PersonEntity: Name: NameFull: Hammerstrom, Dan IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 07 Type: published Y: 2019 Identifiers: – Type: issn-locals Value: edsair – Type: issn-locals Value: edsairFT Titles: – TitleFull: Proceedings of the International Conference on Neuromorphic Systems Type: main |
| ResultId | 1 |