Automatic immunostaining vessel image filtering for visual search efficiency

Blood vessel abstraction is an important procedure for quantitative analysis of blood vessel densities determined by immunostaining the tumor cells. Due to the weak contrast of object boundaries and background clutter, it is difficult to identify the vessel and non-vessel region clearly. In this paper we present a novel algorithm to automatically abstract salient regions in blood vessel images using Gaussian perceptually color space for producing the detail and large-scale layer. The first component of Gaussian color model is used to represent the large-scale layer after bilateral filtering. The detail layer of salient region in the blood vessel image is obtained by normalizing the color of the color layer in the image. Using these two features, we can reconstruct the image using intensity-color coupling. The abstraction result is then processed by luminance quantization algorithm to provide both boundary and region information of blood vessel images. This proposed algorithm has been applied on a wide range of complex blood vessel images with promising results.