Proposal presentation - Health diagnostic by face images

LOGO

LITERATURE REVIEW PROPOSAL

JAMES COOK AUSTRALIA INSTITUTE OF HIGHER LEARNING

In SINGAPORE

Health diagnostic by analysing face images using mobile devices

Instructor : Insu Song

Student : Ho Thi Hoang YenEmail: [email protected]

Content

Topic introduction

Research problem

Background & Motive

Plans

Hồ Thị Hoàng Yến (jc13139122)

Death every year : 56 millions people (2012) Sickness cause : 68%

YES , WE CAN

Þ WHY ? Þ Because it was “TOO LATE”

Þ Can we decrease those number ?

What’s happening in real life ?

Every sickness has a start point , when everything is very simple to heal (necrotic wound, pneumonia,..)

Patients who arrived to the hospital within the “golden hour” of an injury or a sickness would be able to heal completely.

Example: If ischemic stroke patients arrive to hospital Emergency Departments (EDs) within 60 minutes, the illness will be cured completely.

What’s happening in real life ?

How to know when is your sickness golden hour while you cannot visit the hospital all the time ?

Many researchers have spent years on the solution and one of the answers is “Facial analysis” – Health diagnostic by analysing face images using mobile devices.

What’s happening in real life ?

On the medical side, it is totally possible to soon discover your health problems through facial analysis.

Is it possible ?

Process & Problems

Server side : Build a

symptoms data warehouse

Client side : Take face

image

Analysis the photo if there is any symptom

(server or client)

BUT, there is still a long way from concept to application, we have to face many problems, example:- How fast the analysis can be with a huge database while the database

becomes bigger and bigger by time?- Where should the database locate? On the cloud and receive the

request from the client then process OR on the client side and need to be updated all the time?

- Will people agree to share their personal sensitive information as photos and health condition?

Process & Problems

In this research, I’ll focus on privacy problem.

Solution

Will people agree to share their personal sensitive information as photos and health condition ?

=> Make it become anonymous information

Solution:- Convert the photos into a different form that only

computer can understand: a structured model ( ex: Hidden Markov Model or Haar-like Feature method,.. )

Plans

Week 1 : Choosing topic & research problems Week 2 : Research from articles related to the problem Week 3 : Prepare a proposal presentation Week 4 – 10 : Research for solutions & writing report. After week 10 : Review & Update. Next 3 years : Solve almost all the major problems one

after another in this topic , public a mobile health diagnostic program.

Further goal : Predict future coming diseases & solutions

References

http://www.cdc.gov/ Blow, O., Magliore, L., Claridge, J. A., Butler, K., & Young, J. S.

(1999). The golden hour and the silver day: detection and correction of occult hypoperfusion within 24 hours improves outcome from major trauma. Journal of Trauma and Acute Care Surgery, 47(5), 964.

Nefian, A. V., & Hayes III, M. H. (1998). Hidden markov models for face recognition. choice, 1, 6.

Mita, T., Kaneko, T., & Hori, O. (2005). Joint haar-like features for face detection.

DeMyer, W., Zeman, W., & Palmer, C. G. (1964). The face predicts the brain: diagnostic significance of median facial anomalies for holoprosencephaly (arhinencephaly). Pediatrics, 34(2), 256-263.

LOGO

Hồ Thị Hoàng Yến (jc13139122)