Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality
We propose a system that supports real-time product recognition and tracking based on text detection for mobile augmented reality. To accurately distinguish products with visually similar packages, we develop a method that recognizes product names by utilizing the characteristics of texts printed on...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9882114/ |
| _version_ | 1798001573123588096 |
|---|---|
| author | Sangwon Hwang Jisun Lee Seungwoo Kang |
| author_facet | Sangwon Hwang Jisun Lee Seungwoo Kang |
| author_sort | Sangwon Hwang |
| collection | DOAJ |
| description | We propose a system that supports real-time product recognition and tracking based on text detection for mobile augmented reality. To accurately distinguish products with visually similar packages, we develop a method that recognizes product names by utilizing the characteristics of texts printed on the product packages. It first filters out irrelevant products and effectively ranks candidate products through an inverted index search. We significantly reduce processing overhead by selectively performing product name recognition. In addition, we present an optical-flow-based method that enables efficient and responsive product tracking. Our evaluation shows that the proposed system achieves significantly better product recognition accuracy (80%) compared to alternative solutions, Vuforia (55.4%) and MobileNetV2 (69.6%). We also show that it achieves reasonable tracking accuracy and processing latency to support quality mobile AR experiences. |
| first_indexed | 2024-04-11T11:38:24Z |
| format | Article |
| id | doaj.art-dcfcaa90963f40c08b21818419e577d5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T11:38:24Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dcfcaa90963f40c08b21818419e577d52022-12-22T04:25:53ZengIEEEIEEE Access2169-35362022-01-0110987699878210.1109/ACCESS.2022.32053449882114Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented RealitySangwon Hwang0Jisun Lee1Seungwoo Kang2https://orcid.org/0000-0001-5278-2911MAXST, Seoul, Republic of KoreaSmart Tourism Research Center, Kyung Hee University, Seoul, Republic of KoreaSchool of Computer Science and Engineering, KOREATECH, Cheonan, Chungcheongnam-do, Republic of KoreaWe propose a system that supports real-time product recognition and tracking based on text detection for mobile augmented reality. To accurately distinguish products with visually similar packages, we develop a method that recognizes product names by utilizing the characteristics of texts printed on the product packages. It first filters out irrelevant products and effectively ranks candidate products through an inverted index search. We significantly reduce processing overhead by selectively performing product name recognition. In addition, we present an optical-flow-based method that enables efficient and responsive product tracking. Our evaluation shows that the proposed system achieves significantly better product recognition accuracy (80%) compared to alternative solutions, Vuforia (55.4%) and MobileNetV2 (69.6%). We also show that it achieves reasonable tracking accuracy and processing latency to support quality mobile AR experiences.https://ieeexplore.ieee.org/document/9882114/Mobile augmented realityproduct recognitionproduct trackingtext detection |
| spellingShingle | Sangwon Hwang Jisun Lee Seungwoo Kang Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality IEEE Access Mobile augmented reality product recognition product tracking text detection |
| title | Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality |
| title_full | Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality |
| title_fullStr | Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality |
| title_full_unstemmed | Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality |
| title_short | Enabling Product Recognition and Tracking Based on Text Detection for Mobile Augmented Reality |
| title_sort | enabling product recognition and tracking based on text detection for mobile augmented reality |
| topic | Mobile augmented reality product recognition product tracking text detection |
| url | https://ieeexplore.ieee.org/document/9882114/ |
| work_keys_str_mv | AT sangwonhwang enablingproductrecognitionandtrackingbasedontextdetectionformobileaugmentedreality AT jisunlee enablingproductrecognitionandtrackingbasedontextdetectionformobileaugmentedreality AT seungwookang enablingproductrecognitionandtrackingbasedontextdetectionformobileaugmentedreality |