Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
This work addresses efficient object detection for computer vision applications, but it appears incremental as it builds on existing cascade and decision tree methods.
The paper tackles visual object detection by using an ensemble of optimized decision trees with pixel intensity comparisons for fast processing, achieving encouraging results in face detection with practical value.
We describe a method for visual object detection based on an ensemble of optimized decision trees organized in a cascade of rejectors. The trees use pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast. Experimental analysis is provided through a face detection problem. The obtained results are encouraging and demonstrate that the method has practical value. Additionally, we analyse its sensitivity to noise and show how to perform fast rotation invariant object detection. Complete source code is provided at https://github.com/nenadmarkus/pico.