Face Recognition from Images with High Pose Variations

Pose and illumination variations are still the most dominating and persistent challenges haunting face recognition, leading to various highly complex 2D and 3D model-based solutions. We present a novel transform vector quantization (TVQ) method which is fast and accurate and yet much less complex than conventional methods. TVQ offers a flexible and customizable way to capture the pose variations. Use of transform such as DCT helps compressing the image data to a small feature vector and judicious use of vector quantization helps to capture the various poses into compact codebooks. A statistical confidence measure based sequence analysis allows the TVQ method to accurately recognize a person in only 3-9 frames (less than ½ a second) from a video sequence of images with wide pose variations.

  • India

  • Bangalore
    Akaike Technologies Pvt. Ltd.
    11th Cross Rd, Indiranagar
    Bengaluru, Karnataka
    India 560038

  • Chennai
    Akaike Technologies Pvt. Ltd.
    4th Floor, E Block, IIT Madras Research Park
    Tharamani, Chennai
    India 600113

  • Join our team

  • Looking for a job opportunity?

  • Sign up for the newsletter

© Akaike Technologies Pvt. Ltd. and/or its associates and partners
We use cookies to give you the best experience.

Get in Touch