Deep Dropout Artificial Neural Networks for Recognising Digits and Characters in Natural Images

Erik Barrow, Chrisina Jayne, Mark Eastwood

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Recognising images using computers is a traditionally hard problem in computing, and one that becomes particularly difficult when these images are from the real world due to the large variations in them. This paper investigates the problem of recognising digits and characters in natural images using a deep neural network approach. The experiments explore the utilisation of a recently introduced dropout method which reduces overfitting. A number of different configuration networks are trained. It is found that the majority of networks give better accuracy when trained using the dropout method. This indicates that dropout is an effective method to improve training of deep neural networks on the application of recognising natural images of digits and characters.
Original languageEnglish
Title of host publicationNeural Information Processing
Subtitle of host publicationICONIP 2015
Number of pages9
ISBN (Electronic)9783319265612
Publication statusPublished - 15 Nov 2015
EventInternational Conference on Neural Information Processing - Istanbul, Turkey
Duration: 9 Nov 201512 Nov 2015

Publication series

Name Lecture Notes in Computer Science


ConferenceInternational Conference on Neural Information Processing
Abbreviated titleICONIP 2015

Fingerprint Dive into the research topics of 'Deep Dropout Artificial Neural Networks for Recognising Digits and Characters in Natural Images'. Together they form a unique fingerprint.

Cite this