Focus-and-Context Skeleton-based Image Simplification using Saliency Maps

Wang, Jieying; Joao, Leonardo de Melo; Falcão, Alexandre X.; Kosinka, Jiří; Telea, Alexandru

doi:10.5220/0010193400450055

Cited by 3 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the SDMD method comprehensively, we need to create a benchmark involving multiple image types. Indeed, as earlier work using CDMD to represent images has shown [ 3 , 35 ], MAT-based image representations work best for images consisting of relatively large shapes overlaid on a smooth background. This is not surprising given that MATs were also originally found to be most effective for the analysis (and representation) of shapes [ 7 ].…”

Section: Resultsmentioning

confidence: 99%

“…To find a good trade-off between Q and CR, we fix, in turn, three of the four free parameters L ,

, and

to empirically-determined values and vary the fourth parameter over its allowable range via uniform sampling. This method is also applied in [ 3 ] and [ 35 ] and is much simpler and faster than the usual hyper-parameter grid-search used, e.g., in machine learning [ 43 ].…”

Section: Resultsmentioning

confidence: 99%

“…This has a high redundancy, preventing high compression. Later, saliency-based CDMD [ 35 ] improved this by using the YCbCr color space given that YCbCr can give better subjective quality than RGB due to its perceptual similarities to human vision [ 36 , 37 ]. However, this method used the same compression parameters for the three channels.…”

Section: Sdmd Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Spline-Based Dense Medial Descriptors for Lossy Image Compression

2021

Self Cite

View full text Add to dashboard Cite

Medial descriptors are of significant interest for image simplification, representation, manipulation, and compression. On the other hand, B-splines are well-known tools for specifying smooth curves in computer graphics and geometric design. In this paper, we integrate the two by modeling medial descriptors with stable and accurate B-splines for image compression. Representing medial descriptors with B-splines can not only greatly improve compression but is also an effective vector representation of raster images. A comprehensive evaluation shows that our Spline-based Dense Medial Descriptors (SDMD) method achieves much higher compression ratios at similar or even better quality to the well-known JPEG technique. We illustrate our approach with applications in generating super-resolution images and salient feature preserving image compression.

show abstract

Section: Resultsmentioning

confidence: 99%

“…To find a good trade-off between Q and CR, we fix, in turn, three of the four free parameters L ,

, and

Section: Resultsmentioning

confidence: 99%

Section: Sdmd Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Spline-Based Dense Medial Descriptors for Lossy Image Compression

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…As stated above, an important limitation of SDMD is that it simplifies an image globally. Our earlier work, Spatial Saliency DMD (SSDMD) [49], addressed this by simplifying the DMD MAT's using a spatial saliency map. We next present both SSDMD and our new method, 3S-DMD, which improves SSDMD in several respects.…”

Section: Proposed 3s-dmd Methodsmentioning

confidence: 99%

“…Improving Quality: DMD simplifies an image globally, making it hard to preserve fine details in some areas while strongly simplifying the image in other areas. The SSDMD method [49] addressed this by adding a saliency map to DMD, allowing users to specify different spatial simplification levels over an image. SSDMD delivers higher local quality than DMD (as specified by the saliency map) but has two key limitations.…”

Section: Introductionmentioning

confidence: 99%

Spline-Based Dense Medial Descriptors for Image Simplification Using Saliency Maps

Wang

João

Falcão

et al. 2023

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

Medial descriptors have attracted increasing interest in image representation, simplification, and compression. Recently, such descriptors have been separately used to (a) increase the local quality of representing salient features in an image and (b) globally compress an entire image via a B-spline encoding. To date, the two desiderates, (a) high local quality and (b) high overall compression of images, have not been addressed by a single medial method. We achieve this integration by presenting Spatial Saliency Spline Dense Medial Descriptors (3S-DMD) for saliency-aware image simplification-and-compression. Our method significantly improves the trade-off between compression and image quality of earlier medial-based methods while keeping perceptually salient features. We also demonstrate the added-value of user-designed, as compared to automaticallycomputed, saliency maps. We show that our method achieves both higher compression and better quality than JPEG for a broad range of images and, for specific image types, yields higher compression and similar quality than JPEG 2000.

show abstract