Skip to main content

Research Repository

Advanced Search

Local Resultant Gradient Vector Difference and Inpainting for 3D Text Detection in the Wild

Zhong, Dajian; Shivakumara, Palaiahnakote; Nandanwar, Lokesh; Pal, Umapada; Blumenstein, Michael; Lu, Yue

Local Resultant Gradient Vector Difference and Inpainting for 3D Text Detection in the Wild Thumbnail


Authors

Dajian Zhong

Lokesh Nandanwar

Umapada Pal

Michael Blumenstein

Yue Lu



Abstract

Three-dimensional (3D) text appearing in natural scene images is common due to 3D cameras and the capture of text from different angles, which presents new problems for text detection. This is because of the presence of depth information, shadows, and decorative characters in the images. In this work, we consider those images where 3D text appears with depth, as well as shadow information for text detection. We propose a novel method based on local resultant gradient vector difference (LRGVD), inpainting and a deep learning model for detecting 3D as well as two-dimensional (2D) texts in natural scene images. The boundary of components that are invariant to the above challenges is detected by exploring LRGVD. The LRGVD uses gradient magnitude and direction in a novel way for detecting the boundary of the components. Further, we propose an inpainting method in a new way for restoring the character background information using boundaries. For a given region and the input image, the inpainting method divides the whole image into planes and then propagates the values in the planes into the missing region based on posterior probabilities and neighboring information. This results in text regions with false positives. Then, the differential binarization network (DB-Net) is proposed for detecting text irrespective of orientation, background, 3D or 2D, etc. Experiments conducted on our 3D text images and standard datasets of natural scene text images, namely ICDAR 2019 MLT, ICDAR 2019 ArT, DAST1500, Total-Text and SCUT-CTW1500, show that the proposed method is effective in detecting 3D and 2D texts in the images.

Citation

Zhong, D., Shivakumara, P., Nandanwar, L., Pal, U., Blumenstein, M., & Lu, Y. (2022). Local Resultant Gradient Vector Difference and Inpainting for 3D Text Detection in the Wild. International Journal of Pattern Recognition and Artificial Intelligence, 36(8), Article 2253005. https://doi.org/10.1142/S0218001422530056

Journal Article Type Article
Acceptance Date Mar 22, 2022
Publication Date Jun 30, 2022
Deposit Date Nov 15, 2024
Publicly Available Date Nov 22, 2024
Journal International Journal of Pattern Recognition and Artificial Intelligence
Print ISSN 0218-0014
Publisher World Scientific Publishing
Peer Reviewed Peer Reviewed
Volume 36
Issue 8
Article Number 2253005
DOI https://doi.org/10.1142/S0218001422530056

Files





You might also like



Downloadable Citations