Research Article
Reinforced AdaBoost Learning for Object Detection with Local Pattern Representations
Algorithm 1
Proposed update procedure of a classifier based on a reinforced Adaboost learning.
: Number of positive samples, : Number of negative samples | : LPR of ith positive sample, : LPR of ith negative sample | : labels (+1: positive, −1: negative) | (1) Initialize sample weights | | (2) For do | (a) Generate histograms of LPR from positive samples and negative samples | | | : indicator function that takes 1 if the argument is true and 0 otherwise | (b) Compute error rate | | (c) Select the best pixel location with the smallest error rate | | : the maximum number of pixel locations allowed | : the set of pixel locations already chosen before, | (d) Create a lookup table for the weak classifier of pixel location | , | | (e) Update the sample weights & Normalization | , | | (3) Obtain pixel classifier of a single pixel location x | | Constructed strong classifier | |
|