Deep learning based eye recognition framework for human identification using distantly acquired face images
In a new article researchers present a practical deep-learning-based eye recognition framework for human identification using distantly acquired face images in less controlled environments.
In the current era of technology, many of our social, financial, and official organizations rely on the accurate identification of humans. There is a wide range of real-life applications for human identification using distantly acquired face images.
Credit-card authentication, high-security surveillance, law enforcement activities, border-crossing control systems, office management, and the identification of suspects in crowds are a few practical examples of such applications. That is why it is an emerging research topic in biometric identification.
Biometrics cannot be borrowed, stolen, or forgotten, and forging is practically impossible. Therefore, biometric technology has proven to be the most secure and convenient identification and authentication technique.
There are various types of biometric techniques used for human identification. These involve fingerprints, palm prints, face, eye, iris and retina, voice recognition, handwriting, signature dynamics, keystroke dynamics, gait, the sound of steps, and gestures. Among these techniques, iris recognition is the most secure, because the human iris is the only externally visible and highly protected internal organ with its unique patterns.
Since the human iris is a small imaging target and distantly acquired images contain relatively more noise, it degrades image quality. Also, it is not an easy task to recognize the human iris from distantly acquired face images in less constrained environments.
Moreover, iris recognition requires the segmentation of the iris portion from the rest of the eye image, which imposes a further challenge for any iris recognition framework. Then again, increased demand for reliable and precise security technology requires the development of reliable human identification and authentication, especially in long-distance-based access control of secured areas or materials.
Considering all these scenarios, we might consider face recognition or eye recognition instead of iris recognition for human identification.
You can read more about the research above in the article:
Convolutional Neural Network based Eye Recognition from Distantly Acquired Face Images for Human Identification (IEEE Xplore Digital Library)
Kazi Shah Nawaz Ripon
Førsteamanuensis ved Avdeling for informasjonsteknologi