Physiological Measure of Drowsiness Using Image Processing Technique

Abstract

Every year, most of the accidents occur due to drowsiness of drivers which cause severe casualties. Drowsiness reduces the perception level and decision making capability of the driver which negatively affect the ability of the driver to control the vehicle. Proper attention must be paid towards reducing the accidents that occur due to driver drowsiness. Monitoring driver behavior is one of the best ways to prevent fatal accidents. Proposed model detects drowsiness condition of driver by analyzing his eye blink rate and yawning state. The shape and appearance feature to detect eye blink and yawning state is extracted using Histogram of Oriented Gradient (HOG) feature from detected face. Linear Support Vector Machine (SVM) is employed for classification in two stages. In the first stage, classifier is employed for eye blink detection and in the second stage the classifier is employed for yawning detection. The proposed work is implemented using MATLAB 2015a and detection rate was found to be 93%. The use of HOG feature for drowsiness detection makes the system robust to age, gender, small pose variations and real time implementation is made much easier.

Authors and Affiliations

Naveen Kumar H N, Dr. Jagadeesha S

Keywords

Related Articles

Optimization of Process Parameters of Green Sand Casting in Small Scale Foundry

In this research work present the design of experiment based approach which is adopted to obtain an optimal setting of moisture content, grain particle size and temperature of pouring metal related parameters of green s...

Alcohols as Alternative Fuels for Diesel Engines: A REVIEW

The fuel which is used in Internal Combustion engines meant for transportation applications will satisfy all the requirements of cost effectiveness, maximum thermal efficiency, excellent engine performance, and still re...

An Implementation of Cluster Head Algorithm with ACO and Leach Protocol in WSN for Transferring the Data

A wireless network is any type of computer network that uses wireless data connections for connecting network nodes. Wireless networking is a method by which homes, telecommunications networks and enterprise (business)...

Fingerprint Detection Using Minutiae Extraction

In biometric application, identification of real or fake fingerprint is important for security purpose. It is mainly for the concern of fingerprint safety in authentication system. Ploy-Doh, silicon or other artifacts a...

slugBit Error Rate Performance in Coherent Optical Systems

The probability of a transmitted bit error is generally termed as BER. It is calculated by the ratio of incorrectly transmitted bits to total transmitted bits. Regardless of the data destination, an optical transport sy...

Download PDF file
  • EP ID EP22411
  • DOI -
  • Views 203
  • Downloads 4

How To Cite

Naveen Kumar H N, Dr. Jagadeesha S (2016). Physiological Measure of Drowsiness Using Image Processing Technique. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 4(7), -. https://europub.co.uk./articles/-A-22411