A Facial-Expression Monitoring System for Improved Healthcare in Smart Cities

ABSTRACT:

Human facial expressions change with different states of health; therefore, a facial-expression recognition system can be beneficial to a healthcare framework. In this paper, a facial-expression recognition system is proposed to improve the service of the healthcare in a smart city. The proposed system applies a bandlet transform to a face image to extract sub-bands. Then, a weighted, center-symmetric local binary pattern is applied to each sub-band block by block. The CS-LBP histograms of the blocks are concatenated to produce a feature vector of the face image. An optional feature-selection technique selects the most dominant features, which are then fed into two classifiers: a Gaussian mixture model and a support vector machine. The scores of these classifiers are fused by weight to produce a confidence score, which is used to make decisions about the facial expression’s type. Several experiments are performed using a large set of data to validate the proposed system. Experimental results show that the proposed system can recognize facial expressions with 99.95% accuracy.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

In existing system, researchers used a stationary wavelet transform to extract features for facial expression recognition, in both spectral and spatial domains.
Feature dimensionality reduction was done by applying discrete cosine transform.
A feed forward neural network trained through a back propagation algorithm was used as a classifier.
The JAFFE database, the CK database, and a local dataset MS-Kinect were used to attain an average recognition rate of 98.83%, 96.61% and 94.28%, respectively.

DISADVANTAGES OF EXISTING SYSTEM:

The rate of accuracy is less.

PROPOSED SYSTEM:

The facial-expression system proposed in this paper differs from those reported earlier in the sense that the proposed system is specifically designed for a healthcare framework in Smart Cities. The contributions of our present work are as follows:

A bandlet transform and a local binary pattern (LBP) were used to extract features from facial images;
The spatial information of facial expressions is preserved by using a block-based, center-symmetric LBP (CS-LBP); and
The scores of two classifiers, namely the Gaussian mixture model (GMM) and the support vector machine (SVM), are fused with a confidence score.

ADVANTAGES OF PROPOSED SYSTEM:

The proposed facial-expression recognition system can be used in a smart healthcare framework. With this system, registered doctors and caregivers can constantly monitor patients’ feelings remotely and take appropriate actions as required.
The system can also give stakeholders automatic feedback from patients without needing to ask them for feedback.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium Dual Core.

Hard Disk : 120 GB.

Monitor : 15’’ LED

Input Devices : Keyboard, Mouse

Ram : 1GB.

SOFTWARE REQUIREMENTS:

Operating system : Windows 7.
Coding Language : MATLAB
Tool : MATLAB R2013A

REFERENCE:

GHULAM MUHAMMAD1,2, MANSOUR ALSULAIMAN1,2, SYED UMAR AMIN1,2, AHMED GHONEIM3, AND MOHAMMED F. ALHAMID3, “A Facial-Expression Monitoring System for Improved Healthcare in Smart Cities”, IEEE ACCESS, 2017.

Matlab IEEE Projects

A Facial-Expression Monitoring System for Improved Healthcare in Smart Cities