Blurry edge detection and sharpness measure using color line model with K-means clustering

We propose a scheme to detect blurry edge and compute sharpness measure. The key is color line model which models a pixel color is the linear mixture of two dominant colors in small patch. K-means clustering with principal component analysis is exploited to classify colors into two groups. Dominant color is defined as average color of group. Subsequently, weighting of color is computed. In this work, weighting is available for blurry edge detection, and color difference between synthesized color and original color is available for sharpness measure. The proposed scheme has better performance in blurry edge detection and sharpness measurement.