Transform coding of image feature descriptors | Zendy

Vijay Chandrasekhar | Zendy; Gabriel Takacs | Zendy; David Chen | Zendy; Sam S. Tsai | Zendy; Jatinder Singh | Zendy; Bernd Girod | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Transform coding of image feature descriptors

Author(s) -

Vijay Chandrasekhar,

Gabriel Takacs,

David Chen,

Sam S. Tsai,

Jatinder Singh,

Bernd Girod

Publication year - 2008

Publication title -

proceedings of spie, the international society for optical engineering/proceedings of spie

Language(s) - English

Resource type - Conference proceedings

SCImago Journal Rank - 0.192

H-Index - 176

eISSN - 1996-756X

pISSN - 0277-786X

DOI - 10.1117/12.805982

Subject(s) - scale invariant feature transform , artificial intelligence , computer science , feature (linguistics) , computer vision , pattern recognition (psychology) , coding (social sciences) , image matching , matching (statistics) , data compression , feature matching , transform coding , image retrieval , feature extraction , image (mathematics) , mathematics , discrete cosine transform , philosophy , linguistics , statistics

We investigate transform coding to eciently store and transmit SIFT and SURF image descriptors. We show that image and feature matching algorithms are robust to significantly compressed features. We achieve near- perfect image matching and retrieval for both SIFT and SURF using »2 bits/dimension. When applied to SIFT and SURF, this provides a 16◊ compression relative to conventional floating point representation. We establish a strong correlation between MSE and matching error for feature points and images. Feature compression enables many application that may not otherwise be possible, especially on mobile devices.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research