Research on Preventing Unauthorized Face Image Detection
| Project/Area Number |
26540048
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Multimedia database
|
|---|
| Research Institution | National Institute of Informatics |
|---|
Principal Investigator |
Echizen Isao 国立情報学研究所, コンテンツ科学研究系, 教授 (30462188)
|
|---|
| Project Period (FY) |
2014-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | プライバシー保護 / 顔認識 |
|---|
| Outline of Final Research Achievements |
A method is proposed for preventing unauthorized face image revelation through unintentional capture of facial images. Methods such as covering the face and painting particular patterns on the face effectively prevent detection of facial images but hinder face-to-face communication. The proposed method overcomes this problem through the use of a device worn on the face that corrupts the Haar-like features through the use of light absorbing materials, which makes faces in captured images mostly undetectable. The device is similar in appearance to a pair of eyeglasses, so face-to-face communication is only slightly hindered, and it does not need a power supply. Testing of a prototype “PrivacyVisor” showed that captured facial images are sufficiently corrupted to prevent unauthorized face image revelation by face detection.
|
Report
(3 results)
Research Products
(2 results)
