Multi-nature hierarchical approach for natural image segmentation with pattern refinement feedback

A hierarchical learning method for segmenting natural images is proposed in this paper. This approach combines the perceptual information of three natures – colour, texture, and homogeneity – in order to segment natural colour images. These low-level features are extracted using a multiple scale neural architecture we previously proven in [1] and [20]. Present approach incorporates the human knowledge to a hierarchical categorisation process, where the features of the three natures are independently categorised. The final segmentation is achieved through pattern refinement cycles. The approach is compared to other two significant natural scene segmentation methods, achieving better results in a global evaluation. These comparisons are performed using the Berkeley Segmentation Dataset.