Paper Title
A Novel Approach for Analysis of Image Segmentations Quality by Reference Segmentation Work Set

Analysis of image segmentation quality is a critical aspect for generating desirable segmented output and comparing merits of algorithms, among others. However, Dynamic analysis of segmented results is inherently challenging since image segmentation is an improper-posed problem. This paper presents a window work to Analysis segmentation quality using multiple labelled segmentations which are considered as references. For a segmentation to be analysed, we adaptively compose a reference segmentation using multiple labelled segmentations, which locally campares the input segments while preserving outline consistency. The Resolution of a given segmentation is calculated by its distance to the composed reference. A new workset of 200 images, where each one has 6 to 15 labeled segmentations, is designed for performance analysis of image segmentation. Furthermore, to samplised compare the proposed segmentation analysis algorithm with the state-of-the-art methods, a coincidence segmentation analysis workset is proposed. Extensive experiments are carried out to validate the proposed segmentation Analysis window work. Index Terms - image segmentation analysis, segmentation quality, image segmentation workset