Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Modifying and generalising the Radon transform for improved curve-sensitive feature extraction
Thesis (MSc)--Stellenbosch University, 2017
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2017
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614140357410816 |
|---|---|
| access_status_str | Open Access |
| author | Fick, Carlien |
| author2 | Coetzer, Johannes |
| author_browse | Coetzer, Johannes Fick, Carlien |
| author_facet | Coetzer, Johannes Fick, Carlien |
| author_sort | Fick, Carlien |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MSc)--Stellenbosch University, 2017 |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/102941 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:47:18.472Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2017 |
| publishDateRange | 2017 |
| publishDateSort | 2017 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/102941 Modifying and generalising the Radon transform for improved curve-sensitive feature extraction Fick, Carlien Coetzer, Johannes Swanepoel, Jacques Philip Stellenbosch University. Faculty of Science. Dept. of Mathematical Sciences. Division Applied Mathematics. Curve-sensitive feature extraction UCTD Radon transforms Extraction protocol (Mathematics) Biometric identification Signatures (Writing) -- Forgeries Thesis (MSc)--Stellenbosch University, 2017 ENGLISH ABSTRACT : In this thesis a novel and generic feature extraction protocol that is based on the well-known standard discrete Radon transform (SDRT) is presented. The SDRT is traditionally associated with computerised tomography and involves the calculation of projection profiles of an image from a finite set of angles. Although the SDRT has already been successfully employed for the purpose of feature extraction, it is limited to the detection of straight lines. The proposed feature extraction protocol is based on modifications to the SDRT that facilitate the detection of not only straight lines, but also curved lines (with various curvatures), as well as textural information. This is made possible by first constructing a novel appropriately normalised multiresolution polar transform (MPT) of the image in question. The origin of said MPT may be adjusted according to the type of features targeted. The SDRT, or the novel modified discrete Radon transform (MDRT) conceptualised in this thesis, is subsequently applied to the MPT. The extraction of textural information based on different textural periodicities is facilitated by considering different projection angles associated with the MDRT, while the extraction of textural information based on different textural orientations is facilitated by specifying different origins for the MPT. The extraction of information pertaining to curved lines is made possible by specifying origins for the MPT that are located at different distances from the edge of the image in question – the SDRT is subsequently applied to a given MPT from a specific angle of 90 . An existing system that only employs SDRT-based features constitutes a benchmark. Two novel texture-based systems, that target different textural periodicities and orientations respectively, are developed. A novel system, that constitutes a generalisation of the SDRT-based benchmark, and is geared towards the detection of different curved lines, is also developed. The proficiency of the proposed systems is gauged by considering a data set that contains authentic handwritten signature images and skilled forgeries associated with 51 writers. All of the proposed systems outperform the SDRTbased benchmark. The improvement in proficiency associated with each individual texture-based system is statistically significant. The proficiency of the proposed systems also compares favourably with that of existing state-of-theart systems within the context of offline signature verification. AFRIKAANSE OPSOMMING : In hierdie tesis word ‘n nuwe en generiese kenmerk-onttrekkingsprotokol, wat op die bekende gestandaardiseerde diskrete Radon-transformasie (SDRT) gebaseer is, voorgehou. Die SDRT word tradisioneel met rekenaarmatige tomografie geassosieer, en behels die berekening van projeksie-profiele van ‘n beeld vanuit ‘n eindige versameling hoeke. Alhoewel die SDRT reeds vir kenmerkonttrekking aangewend is, is dit beperk tot die opsporing van reguit lyne. Die voorgestelde kenmerk-onttrekkingsprotokol is op aanpassings van die SDRT gebaseer, en fasiliteer die opsporing van benewens reguit lyne, ook krom lyne (met verskeie krommings), asook tekstuur -inligting. Dit word bewerkstellig deur eers ‘n nuwe korrek-genormaliseerde multiresolusie-pooltransformasie (MPT) op die betrokke beeld toe te pas. Die oorsprong van so ‘n MPT kan, na gelang van die tipe kenmerke wat geteiken word, aangepas word. Die SDRT, of die nuwe aangepaste diskrete Radon-transformasie (MDRT) soos gekonseptualiseer in hierdie tesis, word vervolgens op die MPT toegepas. Die onttrekking van tekstuur-inligting op grond van verskillende tekstuurperiodisiteite word gefasiliteer deur verskillende projeksie-hoeke geassosieer met die MDRT te beskou, terwyl die onttrekking van tekstuur-inligting op grond van verskillende tekstuur-oriëntasies moontlik gemaak word deur verskillende oorspronge vir die MPT te spesifiseer. Die onttrekking van inligting rakende krom lyne word gefasiliteer deur oorspronge op verskillende afstande vanaf die rand van die betrokke beeld vir die MPT te spesifiseer – die SDRT word vervolgens op ‘n gegewe MPT vanaf ‘n spesifieke hoek van 90 toegepas. ‘n Maatstaf word gestel deur ’n bestaande stelsel wat slegs SDRT-gebaseerde kenmerke gebruik. Twee nuwe tekstuur-gebaseerde stelsels, wat onderskeidelik verskillende tekstuur-periodisiteite en –oriëntasies teiken, word ontwikkel. ‘n Nuwe stelsel, wat gebaseer is op ‘n veralgemening van die SDRT-gebaseerde maatstaf, en gerig is op die opsporing van verskillende krom lyne, word ook ontwikkel. Die vaardigheid van die voorgestelde stelsels word afgeskat deur ‘n datastel te beskou wat statiese handtekeninge en hoë-kwaliteit vervalsings, geassosieer met 51 skrywers, bevat. Al die voorgestelde stelsels vaar beter as die SDRT-gebaseerde maatstaf. Die vaardigheidsverbetering geassosieer met elke individuele tekstuur-gebaseerde stelsel is statisties beduidend. Die vaardigheid van die voorgestelde stelsels vergelyk ook goed met dié van bestaande stand-van- die-kuns-stelsels binne die konteks van statiese handtekeningverifikasie. 2017-11-17T10:31:17Z 2017-12-11T11:14:59Z 2017-11-17T10:31:17Z 2017-12-11T11:14:59Z 2017-12-01 Thesis http://hdl.handle.net/10019.1/102941 en_ZA Stellenbosch University xviii, 83 pages : illustrations (mainly colour) application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Curve-sensitive feature extraction UCTD Radon transforms Extraction protocol (Mathematics) Biometric identification Signatures (Writing) -- Forgeries Fick, Carlien Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title | Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title_full | Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title_fullStr | Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title_full_unstemmed | Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title_short | Modifying and generalising the Radon transform for improved curve-sensitive feature extraction |
| title_sort | modifying and generalising the radon transform for improved curve sensitive feature extraction |
| topic | Curve-sensitive feature extraction UCTD Radon transforms Extraction protocol (Mathematics) Biometric identification Signatures (Writing) -- Forgeries |
| url | http://hdl.handle.net/10019.1/102941 |
| work_keys_str_mv | AT fickcarlien modifyingandgeneralisingtheradontransformforimprovedcurvesensitivefeatureextraction |