A correlation-based algorithm for detecting linearly degraded objects using noisy training images

Victor Karnaukhov; Vitaly Kober

doi:10.1117/12.2319765

Translator Disclaimer

17 September 2018 A correlation-based algorithm for detecting linearly degraded objects using noisy training images

Victor Karnaukhov, Vitaly Kober

Author Affiliations +

Proceedings Volume 10752, Applications of Digital Image Processing XLI; 1075220 (2018) https://doi.org/10.1117/12.2319765
Event: SPIE Optical Engineering + Applications, 2018, San Diego, California, United States

Abstract

The paper deals with the design of a composite correlation filter from noisy training images for reliable recognition and localization of distorted targets embedded into cluttered linearly degraded and noisy scenes. We consider the nonoverlapping signal model for the input scene and additive noisy model for the reference. The impulse response of the obtained filter is a linear combination of generalized filters optimized with respect to the peak-to-output energy. The performance of the proposed composite correlation filter is analyzed in terms of discrimination capability and accuracy of target location when the reference objects and input scenes are degraded.

Citation Download Citation

Victor Karnaukhov and Vitaly Kober "A correlation-based algorithm for detecting linearly degraded objects using noisy training images", Proc. SPIE 10752, Applications of Digital Image Processing XLI, 1075220 (17 September 2018); https://doi.org/10.1117/12.2319765

ACCESS THE FULL ARTICLE