Object detection using homogeneous probability redistribution of histograms

The goal of this paper is to provide a robust method to detect objects with a minimum training and processing power required in smart environments. We introduce an object detection method based on redistribution of probabilities in training data. The system can be used for finding location and type of near objects. After training the system with some images, a lookup-table will be created containing probabilities of color occurrences for objects. The redistribution algorithm enables us to calculate these numbers for colors that may be seen with small changes in lighting conditions. This will help the system to detect objects in different working environments.