Application study on image recognition algorithm in visual service of deaf mute under complex environment
by Xiaoyi Yang; Qian Wu; Xinmei Deng
International Journal of Services Technology and Management (IJSTM), Vol. 25, No. 5/6, 2019

Abstract: In order to benefit the disadvantaged deaf people and eliminate the communication disorder between the hearing and deaf mute to get harmony and symbiosis really, the visual identification and service research of deaf people has been paid more and more attention by experts and scholars. The paper presented an improved advanced local binary pattern (ALBP) algorithm for face feature recognition. Aimed at being not ideal in recognition effect resulted in ignoring the contrast between the local image in traditional face feature recognition algorithm and discarding some important texture feature information, it first made the illumination normalisation pre-processing of face images under different illumination conditions to control the illumination changes in a certain range, then the improved local binary pattern (LBP) algorithm is used to map the contrast value of the local area pixels into an interval value, so that it made the image own the illumination invariance, thereupon then it could better identify the face features. The experimental results show that the presented ALBP algorithm can be better applied to the visual service system of the deaf.

Online publication date: Fri, 30-Aug-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Services Technology and Management (IJSTM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com