Search Results for author: Yasuhisa Fujii

Found 9 papers, 1 papers with code

Unified Line and Paragraph Detection by Graph Convolutional Networks

no code implementations17 Mar 2022 Shuang Liu, Renshen Wang, Michalis Raptis, Yasuhisa Fujii

We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem.

Rethinking Text Line Recognition Models

no code implementations15 Apr 2021 Daniel Hernandez Diaz, Siyang Qin, Reeve Ingle, Yasuhisa Fujii, Alessandro Bissacco

Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length, a requirement for universal line recognition.

Language Modelling

Post-OCR Paragraph Recognition by Graph Convolutional Networks

no code implementations29 Jan 2021 Renshen Wang, Yasuhisa Fujii, Ashok C. Popat

We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes.

Optical Character Recognition (OCR)

Towards Unconstrained End-to-End Text Spotting

no code implementations ICCV 2019 Siyang Qin, Alessandro Bissacco, Michalis Raptis, Yasuhisa Fujii, Ying Xiao

We propose an end-to-end trainable network that can simultaneously detect and recognize text of arbitrary shape, making substantial progress on the open problem of reading scene text of irregular shape.

Instance Segmentation Optical Character Recognition (OCR) +2

Sequence-to-Label Script Identification for Multilingual OCR

no code implementations15 Aug 2017 Yasuhisa Fujii, Karel Driesen, Jonathan Baccash, Ash Hurst, Ashok C. Popat

Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components, trained end-toend: Encoder and Summarizer.

Optical Character Recognition (OCR)

Cannot find the paper you are looking for? You can Submit a new open access paper.