Performance improvement in complex environment based on ensemble learning algorithm by combining 2D DNF weak classifier

The object detection method employing the 1D feature has benefit that the calculating speed is fast. However, detection accuracy and performance is low in complex background. Therefore, in this paper, we propose an ensemble learning algorithm that combines 1D feature classifier and 2D DNF cell classifier to improve the performance of object detection in single input image. The reason for selecting 2D DNF classifier is that the classifier is able to classify the object not categorized in traditional weak classifier. And we proposed method to choose the feature for reducing the time of learning. In the experiment, we select the haar-like feature as input of 1D feature, and prove the performance of algorithm for face data.