Publication:
Multi-Script Text Detection from Image Using FRCNN

dc.contributor.affiliationDA-IICT, Gandhinagar
dc.contributor.authorGoswami, Mukesh M
dc.contributor.authorDadiya, Nidhi J
dc.contributor.authorGoswami, Tanvi
dc.contributor.authorMitra, Suman
dc.date.accessioned2025-08-01T13:09:27Z
dc.date.issued01-06-2021
dc.description.abstractTextual information is the most common type of way by which we can determine what text/texts we are looking for. In order to retrieve text from images the first and foremost step is text detection from the image. Text detection has a wide range of applications such as translation, smart car driving system, information retrieval, indexing of multimedia archives, sign board reading, and countless. Multilingual text detection from images adds an extra complication to a computer vision problem. As India is a multilingual country and therefore multi-script texts can be found almost everywhere. A multi-script text differs in terms of formats, strokes, width, and height. Also, universal features for such an environment are unknown and difficult to determine as well. Therefore, detecting multi-script text from images is an important yet unsolved problem. In this work, we proposed a faster RCNN-based method for detecting English, Hindi, and Gujarati text from Images. Faster RCNN is the state-of-the-art approach for object detection. As it works for objects which are of large size and texts are of smaller size, the parameters are tuned to meet the objective of multi-script text detection. The dataset is created by collecting images as there is no standard dataset available that includes English, Gujarati, and Hindi texts in the public domain.
dc.identifier.citationMukesh M Goswami, Nidhi J Dadiya, Mitra, Suman K and Tanvi Goswami, "Multi-Script Text Detection from Image Using FRCNN," International Journal of Asian Language Processing, vol. 31, no. 2, World Scientific, ISSN : 2424-791X, pp. 2250003, Jun. 2021 doi: 10.1142/S2717554522500035
dc.identifier.doi10.1142/S2717554522500035
dc.identifier.urihttps://ir.daiict.ac.in/handle/dau.ir/1940
dc.language.isoen
dc.publisherWorld Scientific
dc.relation.ispartofseriesVol. 31; No. 2
dc.source International Journal of Asian Language Processing
dc.source.urihttps://www.worldscientific.com/doi/abs/10.1142/S2717554522500035
dc.titleMulti-Script Text Detection from Image Using FRCNN
dspace.entity.typePublication
relation.isAuthorOfPublicationb322e974-da13-4eae-b8b0-f1f8fec5a4c2
relation.isAuthorOfPublication.latestForDiscoveryb322e974-da13-4eae-b8b0-f1f8fec5a4c2

Files

Collections