Word spotting and recognition via a joint deep embedding of image and text

作者：

Highlights：

• An unified framework for word spotting and recognition.

• An end-to-end model for the joint embedding of handwritten word texts and images.

• Embedded via a convolution neural network (CNN) and a recurrent neural network (RNN).

• A word representation modeling character-level information.

摘要

•An unified framework for word spotting and recognition.•An end-to-end model for the joint embedding of handwritten word texts and images.•Embedded via a convolution neural network (CNN) and a recurrent neural network (RNN).•A word representation modeling character-level information.

论文关键词：Representation learning,Word image representation,Word text representation,Word spotting,Word recognition

论文评审过程：Received 15 February 2018, Revised 1 November 2018, Accepted 17 November 2018, Available online 20 November 2018, Version of Record 30 November 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.11.017