• Vibha R. Kamble
• P. S. Mohod

In today's world, with the increasing demand for high level security in devices and systems several techniques are developed. Face recognition from image is a widely used topic for biometric purpose . In many public places usually have CCTV cameras for capturing the videos and these cameras have their significant value for security purpose. In this paper a real-time method is proposed based on the diffusion speed. The diffusion speed of a single image is obtained to address this problem. Liveness detection is the key idea in surface properties between live and fake faces can be efficiently estimated. SVM classifier is proposed to define whether the given face is fake or not. The significant advantage of this method is that, as compared to previous approaches, it accurately identifies varied malicious attacks regardless of the medium of the image, e.g., paper or screen.

Spoofing, Diffusion speed, Local speed pattern, Local binary pattern, SVM classifier, Face liveliness detection.

"Real-Time and Non-Intrusive method based on the diffusion speed of single image", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.234-237, June-2019, Available :http://www.jetir.org/papers/JETIR1906617.pdf

"Real-Time and Non-Intrusive method based on the diffusion speed of single image", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp234-237, June-2019, Available at : http://www.jetir.org/papers/JETIR1906617.pdf