Adaptive RGB Color Lexicographical Ordering Framework Using Statistical Parameters From the Color Component Histogram

In image filtering, the classical lexicographical ordering is a popular method that cannot be directly applied for ordering colors in RGB color images. This is due to the fact that each color has similar importance and no order can be defined trivially a priori. In this work we propose an adaptive color lexicographical ordering framework for RGB color images where a color pixel is transformed into a real number. This transformation is weighted by statistical parameters from each color component histogram and used as the main component for color comparison. This approach seeks to avoid the arbitrariness since the order of the color component priorities is defined by the information extracted from the image itself. The proposed approach was tested by applying a median filter to reduce noise and a morphological approach to local contrast enhancement. In noise reduction, we compare our method with classical ordering techniques on images with different noise levels. Results show that our proposal outperformed the state-of-the art methods according to the Mean Absolute Error (MAE) measure, especially in those scenarios with higher noise levels. In contrast enhancement, the proposed framework outperformed the classical lexicographical ordering method according to Contrast Improvement Ratio (CIR) metric, especially when increasing the contrast factor. Our proposal generates less distortion than the state-of-the art methods ordering.