Eye blink detection using CNN to detect drowsiness level in drivers for road safety

Title

Eye blink detection using CNN to detect drowsiness level in drivers for road safety

Creator

Vishesh P.; Raghavendra S.; Jankatti S.K.; Rekha V.

Description

Blinking is a regular bodily function and it is the semiautomatic fast closing of the eyelid. A specific blink is examined by dynamic folding of the eyelid. It is a vital function of the eye which helps in spread of tears across and eliminates irritants from the shallow of cornea. In this research work we made use of convolution neural network, the deep learning concepts and image processing to detect drowsiness level in drivers. To train the blink detection model the mobilenet V2 is used as base. The loss function used for training was RMSprop and the optimizer is binary cross entropy. The dlib facial landmark was exploited to perceive and pre-process the detected faces. The dataset used for the training model is selected from the Xiaoyang Tan of nanjing university of aeronautics and astronautics. Based on the experimental outcome the projected method achieves an accuracy of 97%. The prototype developed serves as a base for further development of this process to achieve better road safety. 2021 Institute of Advanced Engineering and Science. All rights reserved.

Source

Indonesian Journal of Electrical Engineering and Computer Science, Vol-22, No. 1, pp. 222-231.

Date

2021-01-01

Publisher

Institute of Advanced Engineering and Science

Subject

Convolution neural network; Cross entropy; Deep learning; Dlib; Eye blink; Mobilenet V2; RMSProp

Coverage

Vishesh P., Department of Computer Science and Engineering, CHRIST Deemed to be University, India; Raghavendra S., Department of Computer Science and Engineering, CHRIST Deemed to be University, India; Jankatti S.K., Department of Computer Science and Engineering, KSSEM, VTU, India; Rekha V., Department of Computer Science and Engineering, CHRIST Deemed to be University, India

Rights

All Open Access; Gold Open Access; Green Open Access

Relation

ISSN: 25024752

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.11591/ijeecs.v22.i1.pp159-167

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104192502&doi=10.11591%2fijeecs.v22.i1.pp159-167&partnerID=40&md5=dfd210eefc3173d59c0cd6f6b6295ffd