Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs Comp Stat

From object detection to text detection and recognition: A brief evolution history of optical character recognition

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract Text detection and recognition, which is also known as optical character recognition (OCR), is an active research area under quick development with a lot of exciting applications. Deep‐learning‐based methods represent the state‐of‐art of this area. However, these methods are largely deterministic: they give a deterministic output for each input. For both statisticians and general users, methods supporting uncertainty inference are of great appeal, leaving rich research opportunities to incorporate statistical models and methods with the established deep‐learning‐based approaches. In this paper, we provide a comprehensive review of the evolution history of research development on OCR with discussions on the statistical insights behind these developments and potential directions to enhance the current methods with statistical approaches. We hope this article can serve as a useful guidebook for statisticians who are seeking for a path toward edge‐cutting research in this exciting area. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning Data: Types and Structure > Image and Spatial Data
The architecture of a typical convolutional neural network (CNN) LeCun et al. (1998)
[ Normal View | Magnified View ]
Flowchart of the different strategies of text recognition: (a) methods based on the segmentation‐recognition strategy, (b) methods based on the sequence‐to‐sequence learning
[ Normal View | Magnified View ]
The architecture of key methods for long text detection
[ Normal View | Magnified View ]
The architecture of key segmentation‐based methods for object detection
[ Normal View | Magnified View ]
Proposal‐based versus segmentation‐based methods for detecting objects of arbitrary orientation and irregular boundary
[ Normal View | Magnified View ]
Selective search versus region proposal network
[ Normal View | Magnified View ]
The architecture of key proposal‐based methods for object detection
[ Normal View | Magnified View ]
The architecture of traditional methods for object detection
[ Normal View | Magnified View ]
An illustration of the attention mechanism in machine translation Luong et al. (2017)
[ Normal View | Magnified View ]
The architecture of recurrent neural network (RNN) and long‐short term memory (LSTM). The image comes from https://blog.csdn.net/zzulp/article/details/84971395
[ Normal View | Magnified View ]

Browse by Topic

Data: Types and Structure > Image and Spatial Data
Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts