Resolution Enhancement by AdaBoost

This paper proposes a learning scheme based still image super-resolution reconstruction algorithm. Superresolution reconstruction is proposed as a binary classification problem and can be solved by conditional class probability estimation. Assuming the probability takes the form of additive logistic regression function, AdaBoost algorithm is used to predict the probability. Experiments on face images validate the algorithm.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Bhaskar D. Rao, Junwen Wu, Mohan M. Trivedi
• Keywords: Adaboost Algorithm, Computer Vision, Conditional Class Probability, ICPR 2004, Super-resolution Reconstruction Algorithm