Li and Cheung and Chin et al. [17 19] proposed several lip segmentation methods based on grayscale images, while Talea and Yaghmaie [20], Kim et al. [21], Hulbert and Poggio [22], Canzlerm and Dziurzyk [23], and Leung et al. [24] adopted methods using color images directly.
Quantitative analysis of oncological positron emission tomography (PET) studies, e.g. for response assessment, target definition for radiotherapy and glycolytic tumour volume measurements, usually involves delineation of tumour boundaries and several tumour segmentation methods have been reported [ 1– 3].
Several document image segmentation methods have been proposed, with the best known being X-Y projection [34], run length smoothing algorithm (RLSA) [35], component grouping [36], scale-space analysis [37], Voronoi tessellation [38], and the Hough transform [39].
The segmentation results of the proposed method and several other PolSAR image segmentation methods are given in Figure 4.
In [4 6], several PolSAR image object segmentation methods based on the classical snake model [5] were proposed.
The first evaluation is performed to quantitatively compare our method with several traditional unsupervised object segmentation methods [8 10] which are only applicable in this setting.
Several well-known interactive-based segmentation methods have been extended to solve co-segmentation problem.
The efficiency of the segmentation method was the ultimate goal for us because existing advanced segmentation methods run several tens of minutes for a dataset.
However, there are several disadvantages on level set based segmentation methods.
The proposed model has been compared with several other state-of-the-art segmentation methods; our implementation is efficient and achieves comparable or better sensitivity and specificity in genomic segmentation.
