New photographic forensics help identify faces from reflections in eyes

Advertisement
By Press Trust of India | Updated: 27 December 2013 19:07 IST

Scientists have developed a new technique which can recover the faces of bystanders from reflections in the eyes of photographic subjects, a development that could help identify criminals.

As the most commonly photographed objects are faces, there is potential in mining detailed facial images for hidden information, researchers said.

Advertisement

Until now, photographers might reasonably have assumed that their own face was absent from the image. But research, led by Dr Rob Jenkins from University of York overturns this assumption.

By zooming in on high-resolution passport-style photographs, Jenkins and co-researcher, Christie Kerr from the University of Glasgow were able to recover the faces of bystanders from reflections in the eyes of photographic subjects.

Advertisement

The recovered bystander images could be identified accurately by observers, despite their low resolution.

To establish whether these bystanders could be identified from the reflection images, the researchers presented them as stimuli in a face-matching task.

Advertisement

Observers who were unfamiliar with the bystanders' faces performed at 71 percent accuracy while participants who were familiar with the faces performed at 84 percent accuracy.

In a test of spontaneous recognition, observers could reliably name a familiar face from an eye reflection image.

Advertisement

"The pupil of the eye is like a black mirror. To enhance the image, you have to zoom in and adjust the contrast. A face image that is recovered from a reflection in the subject's eye is about 30,000 times smaller than the subject's face. Our findings thus highlight the remarkable robustness of human face recognition, as well as the untapped potential of high-resolution photography," Jenkins said.

The researchers say that in crimes in which the victims are photographed, such as hostage taking or child sex abuse, reflections in the eyes of the photographic subject could help to identify perpetrators.

Images of people retrieved from cameras seized as evidence during criminal investigations may be used to piece together networks of associates or to link individuals to particular locations.

The study was published in the journal PLOS ONE.

 

Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.

Advertisement

Related Stories

Popular Mobile Brands
  1. These OnePlus Smartphones Could Receive the ColorOS 17 Update in India
  2. Redmi Note 17 Pro Max Listed on NBTC Website Ahead of Imminent Launch
  3. Dell Alienware 16X Aurora Launched in India Alongside Alienware Area-51 Series
  4. Google's Fitbit Air Spotted on Amazon India Ahead of Official Launch
  5. iOS 27 Beta Code Reportedly Reveals a Key Detail About the Foldable iPhone
  6. OnePlus N6x Design, Colour Options Teased Ahead of India Launch
  7. Tecno Camon 50 Ultra 5G Sale Begins in India Today
  1. OnePlus N6x Design, Colour Options Teased in New Marketing Material Ahead of Imminent Launch in India
  2. OnePlus 11, Nord 4, and Newer Models Tipped to Receive the Android 17-Based ColorOS 17 Update in India
  3. Redmi Note 17 Pro Max Appears on Thailand's NBTC Certification Database, Might Launch Soon
  4. Apple’s First Foldable iPhone Reportedly Appears in iOS 27 Beta Code With a Multi-Battery Setup
  5. X for Android App Undergoes Major Design Overhaul, Enhanced Performance and Reliability
  6. Samsung Galaxy Buds Able to Reportedly Skip Galaxy Unpacked Launch; Could Debut in October
  7. Dell Alienware 16X Aurora, Alienware 16 Area-51 and Alienware 18 Area-51 Launched in India: Price, Specifications
  8. Samsung Galaxy A55, Galaxy A35 One UI 9 Test Builds Reportedly Spotted Ahead of Android 17 Rollout
  9. Xiaomi Pad 9 Could Launch Soon With a Bigger Battery, Certification Listing Suggests: Expected Specifications
  10. Redmi 17 4G EPREL Certification Listing Gives an Early Look at Its Specifications
Download Our Apps
Available in Hindi
© Copyright Red Pixels Ventures Limited 2026. All rights reserved.