An efficient graph reduction framework for interactive texture segmentation

摘要

The performance of graph cut based interactive object segmentation approach depends highly on the size of the image. For high-resolution images, it requires an unacceptable amount of storage and time and becomes even more complex when the image has textural contents. In this work, we present an efficient approach to graph cut based texture segmentation by extracting texture features and reducing the overall size of the graph. To extract texture features, Non-decimated Complex Wavelet Transform (NDCWT) is employed whose sub-bands present the texture attributes at different scales and orientations. Moreover, to deal with the huge computational burdens caused by large images, we consider partitioning of the image area where the image is divided into equal-sized non-overlapping blocks and each such block is mapped to a node in the graph. This will not only reduce the size of the graph but also expedite the optimization process significantly. To achieve pixel level accuracy without using any boundary editing, the blocks lying on the boundary are identified and the final segmentation is obtained by applying the standard graph cut on the pixels of such blocks. Thus our approach is able to retain full resolution accuracy with minimal user interaction as opposed to the pre-segmentation or super-pixel based graph cut approaches. Experiments have been conducted on various gray scale as well as color texture images from Brodatz, Berkeley and MSRC datasets which reveal that the proposed approach not only reduces the segmentation time and memory consumption but also improves segmentation accuracy significantly.