BriefGPT.xyz
Nov, 2019
KISS: 场景文本识别简化
KISS: Keeping It Simple for Scene Text Recognition
HTML
PDF
Christian Bartz, Joseph Bethge, Haojin Yang, Christoph Meinel
TL;DR
本文提出了一个新的场景文本识别模型，该模型只由神经网络的现成组件构成，并仅使用公开的合成数据进行训练，在多个场景文本识别基准测试中达到了最先进或有竞争力的性能。
Abstract
Over the past few years, several new methods for
scene text recognition
have been proposed. Most of these methods propose novel building blocks for
neural networks
. These novel building blocks are specially tailo
→