Saliency Detection via Manifold Ranking Based on Robust Foreground

Detecting Salient Image Objects Using Color Histogram Clustering for Region Granularity

“…In contrast, DGL and DRFI improved their performances for this category of images. The deformed smoothness constraint-based manifold ranking approach used by the DGL method has helped to improve performance for this image category compared to other manifold ranking-based methods such as MR. As stated in [7], results obtained for MR have demonstrated poor performance on complex background images when compared to other categories of images. The SIM again scored the lowest performance on this category of images.…”

“…However, we have also compared our method with seven deep-learning-based top-down methods because they are central to a lot of high-end innovations in recent times. Center prior, color dissimilarity, spatial distance COV [98] Local color contrast, center prior SUN [100] The local intensity and color features, feature space MRBF [7] Boundary connectivity, foreground prior Region by SLIC algorithm DCLC [36] Diffusion-based using manifold ranking, compactness local contrast, center prior MCVS [44] Background prior, foreground prior, and contrast features CSV [56] Global color spatial distribution, object position prior HDCT [67] Learning-based approach, global and local color contrast features, location, histogram, texture, and shape features FCB [68] Foreground and background cues, center prior MC [80] Boundary prior, graph-based, Markov random walk MR [83] Boundary prior, graph-based manifold ranking DGL [84] Graph-based, boundary prior FBSS [94] Boundary, texture, color, and contrast priors DSR [106] Background prior MAP [108] Boundary prior, graph-based, Markov absorption probabilities BGFG [109] Background and foreground prior GR [113] Convex-hull-based center prior, contrast and smoothness prior, graph-based BPFS [140] Global color contrast, background prior, and foreground seeds RPC [66] Color contrast, center prior Regions by graph-based segmentation DRFI [85] Color and texture contrast features, backgrounds features CNS [70] Surroundedness and global color contrast cues Regional histogram of color name space) SIM [75] Center In this study, we run the source codes of the methods of AC, BGFG, CNS, DCLC, DGL, DRFI, GB, GMR, HDCT, IT, MAP, MR, and RPC with their default parameters. The implementations of salient object detection methods in [63] with default parameters were employed to obtain the saliency maps of CA, COV, DSR, FES, GR, MC, SEG, SeR, SR, SUN, and SWD.…”

“…The string of different methods has been applied in the literature to construct a group of pixels that is more attracted by salient regions than individual pixels [46,66]. The methods include fixed-size patches or blocks [25,[97][98][99][100] graph-based segmentation [66,85], mean-shift [101] and simple linear iterative clustering (SLIC) superpixels algorithm [4,7,36,68,79,102]. A Bayesian framework was developed to integrate bottomup saliency and top-down knowledge for saliency computation by extracting features of patches [100].…”

“…Salient object detection is an arduous open research problem aimed at retrieving the most conspicuous visually distinct foreground information from an image in a manner reminiscent of the human vision system [1][2][3][4][5][6][7][8]. It is a challenging task because human vision is difficult to mimic by automated systems.…”

“…These saliency detection methods have extensively used different visual rarities to separate foreground and background regions in images. The visual rarities include color prior [3,48,49], contrast prior [32,50], brightness prior [11,51], background prior [33,52], boundary prior [4,53], center prior [13,54], shape prior [55], context prior [25], object position prior [56], and connectivity prior [7,44,53,57]. However, despite the development of several methods for salient object detection, there are still intrinsic challenges with different categories of images.…”