Adaptive Haar-like classifier for eye status detection under non-ideal lighting conditions

Abstract

The paper introduces a novel methodology to enhance the accuracy, performance and effectiveness of Haar-like classifiers, especially for complicated lighting conditions. Performing a statistical intensity analysis on input image sequences, the technique provides a very fast and robust eye-status detection via a low-resolution VGA camera, without application of any infrared illumination or image enhancement. We report about a test for driver monitoring under real-world conditions also featuring challenging lighting conditions such as 'very bright' at daytime or 'very dark' or 'artificial lighting' at night. An adaptive Haar classifier adjusts the detection parameters according to dynamic level-based intensity measurements in given regions of interest. Experimental results and performance evaluation on various datasets show a higher detection rate compared to standard Viola-Jones classifiers.