{ "ok": true, "doi": "10.46243/jst.2024.v9.i4.pp1-10", "events": [ { "seq": 1, "kind": "register", "at": "2026-09-29 22:00:32", "by": "Administrator (admin)", "by_kind": "user", "note": "registered at Crossref; record read from api.crossref.org", "changes": [ { "path": "abstract.lang", "from": null, "to": "en" }, { "path": "abstract.value", "from": null, "to": "Text presented in videos includes vital information for content analysis, indexing, andretrieval of videos. Finding,verifying, and recognizing video text against complex backgroundsis a key technique for extracting this content. The existing system faces challenges ineffectively detecting and recognizing text content in images, limiting its applications to only images and recognizing text in English. This highlights the limitations of the CTPN network, which can only detect text in approximate horizontal directions. Additionally, the CRNN algorithm used for text recognition lacks efficiencyin handling occluded text, indicating the need for improvement in both text detection and recognitionunder complex backgrounds.Our proposed system suggests a method for text detection and recognition in real-time videos, and web cameras with enhanced multilingual support and converts any language text into English.Efficient handling of occluded text, Efficient handling of text orientations, variations of different fontstyles, sizes and text distortions using text detection tools such as the OpenCV. This tool extracts the region of interest of text in the video frames, implementing text detection throughOptical Character Recognition (OCR) and Pytesseract. OCR and Pytesseract extract text from video frames and pre-process frames for better recognition, enabling automated text extraction and analysis in videos. This approach offers a promising solution with much more better results than the existing method for detecting text in videos and web cameras." }, { "path": "agents.0.name.family", "from": null, "to": "B.Avinash" }, { "path": "agents.0.name.given", "from": null, "to": "" }, { "path": "agents.0.role", "from": null, "to": "author" }, { "path": "agents.0.sequence", "from": null, "to": "first" }, { "path": "agents.1.name.family", "from": null, "to": "Shaik.Ishrath Anjum" }, { "path": "agents.1.name.given", "from": null, "to": "" }, { "path": "agents.1.role", "from": null, "to": "author" }, { "path": "agents.1.sequence", "from": null, "to": "additional" }, { "path": "agents.2.name.family", "from": null, "to": "Syed.Roohi" }, { "path": "agents.2.name.given", "from": null, "to": "" }, { "path": "agents.2.role", "from": null, "to": "author" }, { "path": "agents.2.sequence", "from": null, "to": "additional" }, { "path": "agents.3.name.family", "from": null, "to": "Vibudi.Divya Priya" }, { "path": "agents.3.name.given", "from": null, "to": "" }, { "path": "agents.3.role", "from": null, "to": "author" }, { "path": "agents.3.sequence", "from": null, "to": "additional" }, { "path": "agents.4.name.family", "from": null, "to": "Venicharla.Bhargavi" }, { "path": "agents.4.name.given", "from": null, "to": "" }, { "path": "agents.4.role", "from": null, "to": "author" }, { "path": "agents.4.sequence", "from": null, "to": "additional" }, { "path": "agents.5.name.org", "from": null, "to": "Longman Publishers" }, { "path": "agents.5.role", "from": null, "to": "publisher" }, { "path": "characters.0", "from": null, "to": "Language" }, { "path": "container.identifiers.0.medium", "from": null, "to": "electronic" }, { "path": "container.identifiers.0.type", "from": null, "to": "ISSN" }, { "path": "container.identifiers.0.value", "from": null, "to": "2456-5660" }, { "path": "container.issue", "from": null, "to": "04" }, { "path": "container.pages.first", "from": null, "to": "1" }, { "path": "container.titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "container.titles.0.value", "from": null, "to": "Journal of Science & Technology" }, { "path": "container.type", "from": null, "to": "Journal" }, { "path": "container.volume", "from": null, "to": "09" }, { "path": "dates.date_type", "from": null, "to": "PublicationDate" }, { "path": "dates.online", "from": null, "to": "2024-04-01" }, { "path": "dates.published", "from": null, "to": "2024-04-01" }, { "path": "doi", "from": null, "to": "10.46243/jst.2024.v9.i4.pp1-10" }, { "path": "format", "from": null, "to": "smartscholars-doi-metadata/1.0" }, { "path": "identifiers.0.type", "from": null, "to": "DOI" }, { "path": "identifiers.0.value", "from": null, "to": "10.46243/jst.2024.v9.i4.pp1-10" }, { "path": "language", "from": null, "to": "en" }, { "path": "license.applies_to", "from": null, "to": "vor" }, { "path": "license.start", "from": null, "to": "2024-04-01" }, { "path": "license.url", "from": null, "to": "https://creativecommons.org/licenses/by/4.0/" }, { "path": "links.0.primary", "from": null, "to": true }, { "path": "links.0.return_type", "from": null, "to": "text/html" }, { "path": "links.0.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/view/22" }, { "path": "links.1.purpose", "from": null, "to": "text-mining" }, { "path": "links.1.return_type", "from": null, "to": "application/pdf" }, { "path": "links.1.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/22/16" }, { "path": "links.2.purpose", "from": null, "to": "text-mining" }, { "path": "links.2.return_type", "from": null, "to": "application/xml" }, { "path": "links.2.url", "from": null, "to": "https://www.jst.org.in/index.php/pub/article/download/22/1376" }, { "path": "links.3.purpose", "from": null, "to": "similarity-checking" }, { "path": "links.3.url", "from": null, "to": "https://jst.org.in/index.php/pub/article/view/22/16" }, { "path": "modes.0", "from": null, "to": "Visual" }, { "path": "record.issue_number", "from": null, "to": 1 }, { "path": "record.registered", "from": null, "to": "2026-08-27" }, { "path": "record.registrant", "from": null, "to": "Longman Publishers" }, { "path": "record.source", "from": null, "to": "crossref-api" }, { "path": "record.source_agency", "from": null, "to": "Crossref (member 25296)" }, { "path": "record.updated", "from": null, "to": "2026-09-20" }, { "path": "references.0.key", "from": null, "to": "ref1" }, { "path": "references.0.unstructured", "from": null, "to": "Lecouat, B., Bober, M., & Laptev, I, “Realtime Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 120-135, 2023" }, { "path": "references.1.doi", "from": null, "to": "10.1109/cvpr42600.2020.01213" }, { "path": "references.1.key", "from": null, "to": "ref2" }, { "path": "references.1.unstructured", "from": null, "to": "Chen, W., Li, H., & Zhang, T, “Towards Accurate Scene Text Recognition with Semantic Reasoning and Dynamic Graph Attention Networks,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Volume 7, pp. 210-225, 2022" }, { "path": "references.10.doi", "from": null, "to": "10.1609/aaai.v31i1.11196" }, { "path": "references.10.key", "from": null, "to": "ref11" }, { "path": "references.10.unstructured", "from": null, "to": "Liao, M., Shi, B., Bai, X., Wang, X., Liu, W. “TextBoxes: A Fast Text Detector with a Single Deep Neural Network.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 2, pp. 4165-4172, 2017" }, { "path": "references.11.doi", "from": null, "to": "10.1109/cvpr.2017.283" }, { "path": "references.11.key", "from": null, "to": "ref12" }, { "path": "references.11.unstructured", "from": null, "to": "Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J. “EAST: An Efficient and Accurate Scene Text Detector.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 3, pp. 2642- 2651, 2017" }, { "path": "references.12.doi", "from": null, "to": "10.1109/tpami.2016.2646371" }, { "path": "references.12.key", "from": null, "to": "ref13" }, { "path": "references.12.unstructured", "from": null, "to": "Shi, B., Bai, X., Yao, C. “An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), volume 39, issue 11, pp. 2298-2304, 2017" }, { "path": "references.2.doi", "from": null, "to": "10.1109/cvprw59228.2023.00594" }, { "path": "references.2.key", "from": null, "to": "ref3" }, { "path": "references.2.unstructured", "from": null, "to": "Luo, L., Wu, Y., & Zhang, C, “Real-time Video Text Detection and Recognition with Maskguided Fusion,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 180-195, 2023" }, { "path": "references.3.key", "from": null, "to": "ref4" }, { "path": "references.3.unstructured", "from": null, "to": "Ren, Y., Zhang, Y., & Ren, L, “Fast and Accurate Real-time Text Detection and Recognition in Videos,” In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), volume 2, pp. 50-65, 2022" }, { "path": "references.4.doi", "from": null, "to": "10.1109/icme.2015.7177461" }, { "path": "references.4.key", "from": null, "to": "ref5" }, { "path": "references.4.unstructured", "from": null, "to": "Wang, Z., Jin, L., & Li, W, “Deep Learning-based Real-time Text Recognition in Videos using Tesseract,” In Proceedings of the International Conference on Multimedia and Expo (ICME), volume 3, pp. 80-95, 2023" }, { "path": "references.5.key", "from": null, "to": "ref6" }, { "path": "references.5.unstructured", "from": null, "to": "Yang, J., Wang, L., & Li, X, “Real-time Multilingual Scene Text Detection and Recognition,” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 6, pp. 180- 195, 2020" }, { "path": "references.6.key", "from": null, "to": "ref7" }, { "path": "references.6.unstructured", "from": null, "to": "Zhu, X., Tian, X., & Shen, C, “Real-time Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 5, pp. 150-165, 2019" }, { "path": "references.7.key", "from": null, "to": "ref8" }, { "path": "references.7.unstructured", "from": null, "to": "Liu, Z., Chen, S., & Shen, C, “Real-time Endto-End Text Detection and Recognition,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 4, pp. 120-135, 2018" }, { "path": "references.8.doi", "from": null, "to": "10.1109/tpami.2016.2577031" }, { "path": "references.8.key", "from": null, "to": "ref9" }, { "path": "references.8.unstructured", "from": null, "to": "Ren, S., He, K., Girshick, R., Sun, J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), volume 28, pp. 91-99, 2015" }, { "path": "references.9.doi", "from": null, "to": "10.1109/iccv.2017.322" }, { "path": "references.9.key", "from": null, "to": "ref10" }, { "path": "references.9.unstructured", "from": null, "to": "He, K., Gkioxari, G., Dollar, P., Girshick, R. “Mask R-CNN.” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 2, pp. 2980-2988, 2017" }, { "path": "referent", "from": null, "to": "Creation" }, { "path": "structural_type", "from": null, "to": "Digital" }, { "path": "titles.0.lang", "from": null, "to": "en" }, { "path": "titles.0.type", "from": null, "to": "PrincipalTitle" }, { "path": "titles.0.value", "from": null, "to": "Real -Time Text Detection and Recognition Based on Optical Character Recognition(OCR)" }, { "path": "type", "from": null, "to": "JournalArticle" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2024.v9.i4.pp1-10", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "Real -Time Text Detection and Recognition Based on Optical Character Recognition(OCR)", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2024.v9.i4.pp1-10" } ], "agents": [ { "role": "author", "name": { "given": "", "family": "B.Avinash" }, "sequence": "first" }, { "role": "author", "name": { "given": "", "family": "Shaik.Ishrath Anjum" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Syed.Roohi" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Vibudi.Divya Priya" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Venicharla.Bhargavi" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2024-04-01", "date_type": "PublicationDate", "online": "2024-04-01" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "09", "issue": "04", "pages": { "first": "1" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/22", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/22/16", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/22/1376", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://jst.org.in/index.php/pub/article/view/22/16", "purpose": "similarity-checking" } ], "abstract": { "value": "Text presented in videos includes vital information for content analysis, indexing, andretrieval of videos. Finding,verifying, and recognizing video text against complex backgroundsis a key technique for extracting this content. The existing system faces challenges ineffectively detecting and recognizing text content in images, limiting its applications to only images and recognizing text in English. This highlights the limitations of the CTPN network, which can only detect text in approximate horizontal directions. Additionally, the CRNN algorithm used for text recognition lacks efficiencyin handling occluded text, indicating the need for improvement in both text detection and recognitionunder complex backgrounds.Our proposed system suggests a method for text detection and recognition in real-time videos, and web cameras with enhanced multilingual support and converts any language text into English.Efficient handling of occluded text, Efficient handling of text orientations, variations of different fontstyles, sizes and text distortions using text detection tools such as the OpenCV. This tool extracts the region of interest of text in the video frames, implementing text detection throughOptical Character Recognition (OCR) and Pytesseract. OCR and Pytesseract extract text from video frames and pre-process frames for better recognition, enabling automated text extraction and analysis in videos. This approach offers a promising solution with much more better results than the existing method for detecting text in videos and web cameras.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2024-04-01", "applies_to": "vor" }, "references": [ { "key": "ref1", "unstructured": "Lecouat, B., Bober, M., & Laptev, I, “Realtime Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 120-135, 2023" }, { "key": "ref2", "doi": "10.1109/cvpr42600.2020.01213", "unstructured": "Chen, W., Li, H., & Zhang, T, “Towards Accurate Scene Text Recognition with Semantic Reasoning and Dynamic Graph Attention Networks,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Volume 7, pp. 210-225, 2022" }, { "key": "ref3", "doi": "10.1109/cvprw59228.2023.00594", "unstructured": "Luo, L., Wu, Y., & Zhang, C, “Real-time Video Text Detection and Recognition with Maskguided Fusion,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 180-195, 2023" }, { "key": "ref4", "unstructured": "Ren, Y., Zhang, Y., & Ren, L, “Fast and Accurate Real-time Text Detection and Recognition in Videos,” In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), volume 2, pp. 50-65, 2022" }, { "key": "ref5", "doi": "10.1109/icme.2015.7177461", "unstructured": "Wang, Z., Jin, L., & Li, W, “Deep Learning-based Real-time Text Recognition in Videos using Tesseract,” In Proceedings of the International Conference on Multimedia and Expo (ICME), volume 3, pp. 80-95, 2023" }, { "key": "ref6", "unstructured": "Yang, J., Wang, L., & Li, X, “Real-time Multilingual Scene Text Detection and Recognition,” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 6, pp. 180- 195, 2020" }, { "key": "ref7", "unstructured": "Zhu, X., Tian, X., & Shen, C, “Real-time Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 5, pp. 150-165, 2019" }, { "key": "ref8", "unstructured": "Liu, Z., Chen, S., & Shen, C, “Real-time Endto-End Text Detection and Recognition,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 4, pp. 120-135, 2018" }, { "key": "ref9", "doi": "10.1109/tpami.2016.2577031", "unstructured": "Ren, S., He, K., Girshick, R., Sun, J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), volume 28, pp. 91-99, 2015" }, { "key": "ref10", "doi": "10.1109/iccv.2017.322", "unstructured": "He, K., Gkioxari, G., Dollar, P., Girshick, R. “Mask R-CNN.” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 2, pp. 2980-2988, 2017" }, { "key": "ref11", "doi": "10.1609/aaai.v31i1.11196", "unstructured": "Liao, M., Shi, B., Bai, X., Wang, X., Liu, W. “TextBoxes: A Fast Text Detector with a Single Deep Neural Network.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 2, pp. 4165-4172, 2017" }, { "key": "ref12", "doi": "10.1109/cvpr.2017.283", "unstructured": "Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J. “EAST: An Efficient and Accurate Scene Text Detector.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 3, pp. 2642- 2651, 2017" }, { "key": "ref13", "doi": "10.1109/tpami.2016.2646371", "unstructured": "Shi, B., Bai, X., Yao, C. “An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), volume 39, issue 11, pp. 2298-2304, 2017" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-08-27", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/22", "sha256_before": null, "sha256_after": "c306f48456cce5de9daabc8b05263be1821dc79341cf186ec7af3913b7b61fe5" }, { "seq": 2, "kind": "update", "at": "2026-09-29 23:59:52", "by": "Administrator (admin)", "by_kind": "user", "note": "record re-read from api.crossref.org", "changes": [ { "path": "container.titles.0.value", "from": "Journal of Science & Technology", "to": "Journal of Science & Technology" } ], "record_after": { "format": "smartscholars-doi-metadata/1.0", "doi": "10.46243/jst.2024.v9.i4.pp1-10", "referent": "Creation", "type": "JournalArticle", "structural_type": "Digital", "modes": [ "Visual" ], "characters": [ "Language" ], "titles": [ { "value": "Real -Time Text Detection and Recognition Based on Optical Character Recognition(OCR)", "type": "PrincipalTitle", "lang": "en" } ], "identifiers": [ { "type": "DOI", "value": "10.46243/jst.2024.v9.i4.pp1-10" } ], "agents": [ { "role": "author", "name": { "given": "", "family": "B.Avinash" }, "sequence": "first" }, { "role": "author", "name": { "given": "", "family": "Shaik.Ishrath Anjum" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Syed.Roohi" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Vibudi.Divya Priya" }, "sequence": "additional" }, { "role": "author", "name": { "given": "", "family": "Venicharla.Bhargavi" }, "sequence": "additional" }, { "role": "publisher", "name": { "org": "Longman Publishers" } } ], "dates": { "published": "2024-04-01", "date_type": "PublicationDate", "online": "2024-04-01" }, "language": "en", "container": { "type": "Journal", "titles": [ { "value": "Journal of Science & Technology", "type": "PrincipalTitle" } ], "identifiers": [ { "type": "ISSN", "value": "2456-5660", "medium": "electronic" } ], "volume": "09", "issue": "04", "pages": { "first": "1" } }, "links": [ { "url": "https://www.jst.org.in/index.php/pub/article/view/22", "return_type": "text/html", "primary": true }, { "url": "https://www.jst.org.in/index.php/pub/article/download/22/16", "purpose": "text-mining", "return_type": "application/pdf" }, { "url": "https://www.jst.org.in/index.php/pub/article/download/22/1376", "purpose": "text-mining", "return_type": "application/xml" }, { "url": "https://jst.org.in/index.php/pub/article/view/22/16", "purpose": "similarity-checking" } ], "abstract": { "value": "Text presented in videos includes vital information for content analysis, indexing, andretrieval of videos. Finding,verifying, and recognizing video text against complex backgroundsis a key technique for extracting this content. The existing system faces challenges ineffectively detecting and recognizing text content in images, limiting its applications to only images and recognizing text in English. This highlights the limitations of the CTPN network, which can only detect text in approximate horizontal directions. Additionally, the CRNN algorithm used for text recognition lacks efficiencyin handling occluded text, indicating the need for improvement in both text detection and recognitionunder complex backgrounds.Our proposed system suggests a method for text detection and recognition in real-time videos, and web cameras with enhanced multilingual support and converts any language text into English.Efficient handling of occluded text, Efficient handling of text orientations, variations of different fontstyles, sizes and text distortions using text detection tools such as the OpenCV. This tool extracts the region of interest of text in the video frames, implementing text detection throughOptical Character Recognition (OCR) and Pytesseract. OCR and Pytesseract extract text from video frames and pre-process frames for better recognition, enabling automated text extraction and analysis in videos. This approach offers a promising solution with much more better results than the existing method for detecting text in videos and web cameras.", "lang": "en" }, "license": { "url": "https://creativecommons.org/licenses/by/4.0/", "start": "2024-04-01", "applies_to": "vor" }, "references": [ { "key": "ref1", "unstructured": "Lecouat, B., Bober, M., & Laptev, I, “Realtime Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 120-135, 2023" }, { "key": "ref2", "doi": "10.1109/cvpr42600.2020.01213", "unstructured": "Chen, W., Li, H., & Zhang, T, “Towards Accurate Scene Text Recognition with Semantic Reasoning and Dynamic Graph Attention Networks,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Volume 7, pp. 210-225, 2022" }, { "key": "ref3", "doi": "10.1109/cvprw59228.2023.00594", "unstructured": "Luo, L., Wu, Y., & Zhang, C, “Real-time Video Text Detection and Recognition with Maskguided Fusion,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 180-195, 2023" }, { "key": "ref4", "unstructured": "Ren, Y., Zhang, Y., & Ren, L, “Fast and Accurate Real-time Text Detection and Recognition in Videos,” In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), volume 2, pp. 50-65, 2022" }, { "key": "ref5", "doi": "10.1109/icme.2015.7177461", "unstructured": "Wang, Z., Jin, L., & Li, W, “Deep Learning-based Real-time Text Recognition in Videos using Tesseract,” In Proceedings of the International Conference on Multimedia and Expo (ICME), volume 3, pp. 80-95, 2023" }, { "key": "ref6", "unstructured": "Yang, J., Wang, L., & Li, X, “Real-time Multilingual Scene Text Detection and Recognition,” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 6, pp. 180- 195, 2020" }, { "key": "ref7", "unstructured": "Zhu, X., Tian, X., & Shen, C, “Real-time Scene Text Detection with Differentiable Binarization,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 5, pp. 150-165, 2019" }, { "key": "ref8", "unstructured": "Liu, Z., Chen, S., & Shen, C, “Real-time Endto-End Text Detection and Recognition,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 4, pp. 120-135, 2018" }, { "key": "ref9", "doi": "10.1109/tpami.2016.2577031", "unstructured": "Ren, S., He, K., Girshick, R., Sun, J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), volume 28, pp. 91-99, 2015" }, { "key": "ref10", "doi": "10.1109/iccv.2017.322", "unstructured": "He, K., Gkioxari, G., Dollar, P., Girshick, R. “Mask R-CNN.” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 2, pp. 2980-2988, 2017" }, { "key": "ref11", "doi": "10.1609/aaai.v31i1.11196", "unstructured": "Liao, M., Shi, B., Bai, X., Wang, X., Liu, W. “TextBoxes: A Fast Text Detector with a Single Deep Neural Network.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 2, pp. 4165-4172, 2017" }, { "key": "ref12", "doi": "10.1109/cvpr.2017.283", "unstructured": "Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J. “EAST: An Efficient and Accurate Scene Text Detector.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 3, pp. 2642- 2651, 2017" }, { "key": "ref13", "doi": "10.1109/tpami.2016.2646371", "unstructured": "Shi, B., Bai, X., Yao, C. “An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), volume 39, issue 11, pp. 2298-2304, 2017" } ], "record": { "registrant": "Longman Publishers", "registered": "2026-08-27", "updated": "2026-09-20", "issue_number": 1, "source": "crossref-api", "source_agency": "Crossref (member 25296)" } }, "url_after": "https://www.jst.org.in/index.php/pub/article/view/22", "sha256_before": "c306f48456cce5de9daabc8b05263be1821dc79341cf186ec7af3913b7b61fe5", "sha256_after": "472d46513555b222ba21c7b4158f34d1ddf007c16f805794fd3f9906455d111b" } ] }