The Role of Optimum Connectivity in Image Segmentation: Can the Algorithm Learn Object Information During the Process?

Falcão, Alexandre X.; Bragantini, Jordão

doi:10.1007/978-3-030-14085-4_15

Cited by 7 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It relies on well-tested and robust algorithms such as the skeletonization method in [17,42] and the least-squares B-spline fitting algorithm [13]. In contrast to segmentation tasks [16], 3S-DMD does not require precise saliency maps. Any saliency map that encodes which image areas are more important and which less for an application at hand can be used.…”

Section: Discussionmentioning

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

Section: Discussionmentioning

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

show abstract

“…The author's dissertation contains the following articles: [14], [21], [22]. Other works [53], [54] were also developed in parallel but were not part of the dissertation.…”

Section: Publicationsmentioning

confidence: 99%

Interactive Image Segmentation: From Graph-based Algorithms to Feature-Space Annotation

Bragantini

Falcão

2022

Anais Estendidos Do XXXV Conference on Graphics, Patterns and Images (SIBGRAPI Estendido 2022)

View full text Add to dashboard Cite

In recent years, machine learning algorithms that solve problems from a collection of examples (i.e. labeled data), have grown to be the predominant approach for solving computer vision and image processing tasks. These algorithms’ performance is highly correlated with the abundance of examples and their quality, especially methods based on neural networks, which are significantly data-hungry. Notably, image segmentation annotation requires extensive effort to produce high-quality labeling due to the fine-scale of the units (pixels) and resorts to interactive methodologies to provide user assistance. Therefore, improving interactive image segmentation methodologies with the goal of improving data labeling problems is of paramount importance to advance applications of computer vision methods. With this in mind, we investigated the existing literature on interactive image segmentation, contributing to it by introducing novel algorithms that perform the segmentation from markers, contours, and finally proposing a new paradigm for image annotation at scale.

show abstract

Towards Interactive Image Segmentation by Dynamic and Iterative Spanning Forest

Barcelos

Belém

Miranda

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The Role of Optimum Connectivity in Image Segmentation: Can the Algorithm Learn Object Information During the Process?

Cited by 7 publications

References 37 publications

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

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

Interactive Image Segmentation: From Graph-based Algorithms to Feature-Space Annotation

Towards Interactive Image Segmentation by Dynamic and Iterative Spanning Forest

Contact Info

Product

Resources

About