Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system
<p>Automatic number plate recognition (ANPR) systems are becoming vital for safety and security purposes. Typical ANPR systems are based on three stages: number plate localization (NPL), character segmentation (CS), and optical character recognition (OCR). Recently, high definition (HD) camera...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , |
| Published: |
2018
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513566564941824 |
|---|---|
| author | Ali Farhat (1461478) |
| author2 | Omar Hommos (14153343) Ali Al-Zawqari (14153346) Abdulhadi Al-Qahtani (14153349) Faycal Bensaali (12427401) Abbes Amira (6952001) Xiaojun Zhai (9040469) |
| author2_role | author author author author author author |
| author_facet | Ali Farhat (1461478) Omar Hommos (14153343) Ali Al-Zawqari (14153346) Abdulhadi Al-Qahtani (14153349) Faycal Bensaali (12427401) Abbes Amira (6952001) Xiaojun Zhai (9040469) |
| author_role | author |
| dc.creator.none.fl_str_mv | Ali Farhat (1461478) Omar Hommos (14153343) Ali Al-Zawqari (14153346) Abdulhadi Al-Qahtani (14153349) Faycal Bensaali (12427401) Abbes Amira (6952001) Xiaojun Zhai (9040469) |
| dc.date.none.fl_str_mv | 2018-07-11T00:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1186/s13640-018-0298-2 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Optical_character_recognition_on_heterogeneous_SoC_for_HD_automatic_number_plate_recognition_system/21598488 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Engineering Electronics, sensors and digital hardware Information and computing sciences Information systems Optical character recognition Automatic number plate recognition systems FPGA High-level synthesis Vivado |
| dc.title.none.fl_str_mv | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p>Automatic number plate recognition (ANPR) systems are becoming vital for safety and security purposes. Typical ANPR systems are based on three stages: number plate localization (NPL), character segmentation (CS), and optical character recognition (OCR). Recently, high definition (HD) cameras have been used to improve their recognition rates. In this paper, four algorithms are proposed for the OCR stage of a real-time HD ANPR system. The proposed algorithms are based on feature extraction (vector crossing, zoning, combined zoning, and vector crossing) and template matching techniques. All proposed algorithms have been implemented using MATLAB as a proof of concept and the best one has been selected for hardware implementation using a heterogeneous system on chip (SoC) platform. The selected platform is the Xilinx Zynq-7000 All Programmable SoC, which consists of an ARM processor and programmable logic. Obtained hardware implementation results have shown that the proposed system can recognize one character in 0.63 ms, with an accuracy of 99.5% while utilizing around 6% of the programmable logic resources. In addition, the use of the heterogenous SoC consumes 36 W which is equivalent to saving around 80% of the energy consumed by the PC used in this work, whereas it is smaller in size by 95%.</p><h2>Other Information</h2> <p> Published in: EURASIP Journal on Image and Video Processing<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1186/s13640-018-0298-2" target="_blank">http://dx.doi.org/10.1186/s13640-018-0298-2</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_4e93fb34d98f36d498eb2745a7d59162 |
| identifier_str_mv | 10.1186/s13640-018-0298-2 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/21598488 |
| publishDate | 2018 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition systemAli Farhat (1461478)Omar Hommos (14153343)Ali Al-Zawqari (14153346)Abdulhadi Al-Qahtani (14153349)Faycal Bensaali (12427401)Abbes Amira (6952001)Xiaojun Zhai (9040469)EngineeringElectronics, sensors and digital hardwareInformation and computing sciencesInformation systemsOptical character recognitionAutomatic number plate recognition systemsFPGAHigh-level synthesisVivado<p>Automatic number plate recognition (ANPR) systems are becoming vital for safety and security purposes. Typical ANPR systems are based on three stages: number plate localization (NPL), character segmentation (CS), and optical character recognition (OCR). Recently, high definition (HD) cameras have been used to improve their recognition rates. In this paper, four algorithms are proposed for the OCR stage of a real-time HD ANPR system. The proposed algorithms are based on feature extraction (vector crossing, zoning, combined zoning, and vector crossing) and template matching techniques. All proposed algorithms have been implemented using MATLAB as a proof of concept and the best one has been selected for hardware implementation using a heterogeneous system on chip (SoC) platform. The selected platform is the Xilinx Zynq-7000 All Programmable SoC, which consists of an ARM processor and programmable logic. Obtained hardware implementation results have shown that the proposed system can recognize one character in 0.63 ms, with an accuracy of 99.5% while utilizing around 6% of the programmable logic resources. In addition, the use of the heterogenous SoC consumes 36 W which is equivalent to saving around 80% of the energy consumed by the PC used in this work, whereas it is smaller in size by 95%.</p><h2>Other Information</h2> <p> Published in: EURASIP Journal on Image and Video Processing<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1186/s13640-018-0298-2" target="_blank">http://dx.doi.org/10.1186/s13640-018-0298-2</a></p>2018-07-11T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1186/s13640-018-0298-2https://figshare.com/articles/journal_contribution/Optical_character_recognition_on_heterogeneous_SoC_for_HD_automatic_number_plate_recognition_system/21598488CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/215984882018-07-11T00:00:00Z |
| spellingShingle | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system Ali Farhat (1461478) Engineering Electronics, sensors and digital hardware Information and computing sciences Information systems Optical character recognition Automatic number plate recognition systems FPGA High-level synthesis Vivado |
| status_str | publishedVersion |
| title | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| title_full | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| title_fullStr | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| title_full_unstemmed | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| title_short | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| title_sort | Optical character recognition on heterogeneous SoC for HD automatic number plate recognition system |
| topic | Engineering Electronics, sensors and digital hardware Information and computing sciences Information systems Optical character recognition Automatic number plate recognition systems FPGA High-level synthesis Vivado |