ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection
Detection and recognition of traffic panels and their textual information are important applications of advanced driving assistance systems (ADAS). They can significantly contribute in enhancing road safety by optimizing the driving experience. However, these tasks might face two major challenges. F...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9466101/ |
| _version_ | 1819098128054222848 |
|---|---|
| author | Kaoutar Sefrioui Boujemaa Mohammed Akallouch Ismail Berrada Khalid Fardousse Afaf Bouhoute |
| author_facet | Kaoutar Sefrioui Boujemaa Mohammed Akallouch Ismail Berrada Khalid Fardousse Afaf Bouhoute |
| author_sort | Kaoutar Sefrioui Boujemaa |
| collection | DOAJ |
| description | Detection and recognition of traffic panels and their textual information are important applications of advanced driving assistance systems (ADAS). They can significantly contribute in enhancing road safety by optimizing the driving experience. However, these tasks might face two major challenges. First, the lack of suitable and good quality datasets. Second, the in-feasibility of global standardization of traffic panels in terms of shape, color and language of the written text. Present research is intensively directed toward Latin text-based panels, while other scripts such as Arabic remain quiet undervalued. In this paper, we address this issue by introducing ATTICA, a new open-source multi-task dataset, consisting of two main sub-datasets: ATTICA_Sign for traffic signs/panels detection and ATTICA_Text for Arabic text extraction/recognition. Our dataset gathers 1215 images with 3173 traffic panel boxes, 870 traffic sign boxes and 7293 Arabic text boxes. In order to examine the utility and advantages of our dataset, we adopt state-of-the-art deep learning based approaches. The conducted experiments show promising results confirming the valuable addition of our dataset in this field of research. |
| first_indexed | 2024-12-22T00:26:03Z |
| format | Article |
| id | doaj.art-01b36002ed904aa08783136ee2e60ef9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T00:26:03Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-01b36002ed904aa08783136ee2e60ef92022-12-21T18:45:03ZengIEEEIEEE Access2169-35362021-01-019939379394710.1109/ACCESS.2021.30928219466101ATTICA: A Dataset for Arabic Text-Based Traffic Panels DetectionKaoutar Sefrioui Boujemaa0https://orcid.org/0000-0001-8746-3902Mohammed Akallouch1https://orcid.org/0000-0002-3438-3885Ismail Berrada2Khalid Fardousse3https://orcid.org/0000-0003-3374-5810Afaf Bouhoute4https://orcid.org/0000-0001-7741-7849Department of Computer Science, Sidi Mohamed Ben Abdellah University (USMBA), Fez, MoroccoDepartment of Computer Science, Sidi Mohamed Ben Abdellah University (USMBA), Fez, MoroccoSchool of Computer Science, Mohammed VI Polytechnic University, Benguérir, MoroccoDepartment of Computer Science, Sidi Mohamed Ben Abdellah University (USMBA), Fez, MoroccoDepartment of Computer Science, Sidi Mohamed Ben Abdellah University (USMBA), Fez, MoroccoDetection and recognition of traffic panels and their textual information are important applications of advanced driving assistance systems (ADAS). They can significantly contribute in enhancing road safety by optimizing the driving experience. However, these tasks might face two major challenges. First, the lack of suitable and good quality datasets. Second, the in-feasibility of global standardization of traffic panels in terms of shape, color and language of the written text. Present research is intensively directed toward Latin text-based panels, while other scripts such as Arabic remain quiet undervalued. In this paper, we address this issue by introducing ATTICA, a new open-source multi-task dataset, consisting of two main sub-datasets: ATTICA_Sign for traffic signs/panels detection and ATTICA_Text for Arabic text extraction/recognition. Our dataset gathers 1215 images with 3173 traffic panel boxes, 870 traffic sign boxes and 7293 Arabic text boxes. In order to examine the utility and advantages of our dataset, we adopt state-of-the-art deep learning based approaches. The conducted experiments show promising results confirming the valuable addition of our dataset in this field of research.https://ieeexplore.ieee.org/document/9466101/Traffic panelssign detectionsign recognitionscene Arabic text detectiontraffic textual information retrievaltraffic panels dataset |
| spellingShingle | Kaoutar Sefrioui Boujemaa Mohammed Akallouch Ismail Berrada Khalid Fardousse Afaf Bouhoute ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection IEEE Access Traffic panels sign detection sign recognition scene Arabic text detection traffic textual information retrieval traffic panels dataset |
| title | ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection |
| title_full | ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection |
| title_fullStr | ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection |
| title_full_unstemmed | ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection |
| title_short | ATTICA: A Dataset for Arabic Text-Based Traffic Panels Detection |
| title_sort | attica a dataset for arabic text based traffic panels detection |
| topic | Traffic panels sign detection sign recognition scene Arabic text detection traffic textual information retrieval traffic panels dataset |
| url | https://ieeexplore.ieee.org/document/9466101/ |
| work_keys_str_mv | AT kaoutarsefriouiboujemaa atticaadatasetforarabictextbasedtrafficpanelsdetection AT mohammedakallouch atticaadatasetforarabictextbasedtrafficpanelsdetection AT ismailberrada atticaadatasetforarabictextbasedtrafficpanelsdetection AT khalidfardousse atticaadatasetforarabictextbasedtrafficpanelsdetection AT afafbouhoute atticaadatasetforarabictextbasedtrafficpanelsdetection |