Search Results for author: Alessandro Bissacco

Found 6 papers, 3 papers with code

Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis

1 code implementation25 Oct 2023 Shangbang Long, Siyang Qin, Yasuhisa Fujii, Alessandro Bissacco, Michalis Raptis

We propose Hierarchical Text Spotter (HTS), a novel method for the joint task of word-level text spotting and geometric layout analysis.

Text Spotting

Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation

no code implementations4 May 2023 Renshen Wang, Yasuhisa Fujii, Alessandro Bissacco

Text reading order is a crucial aspect in the output of an OCR engine, with a large impact on downstream tasks.

Optical Character Recognition (OCR)

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.

Ranked #2 on Handwritten Text Recognition on IAM (using extra training data)

Handwritten Text Recognition Language Modelling

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) +3

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