paper-with-me

Papers

Superpixels and Polygons Using Simple Non-Iterative Clustering

2017-07-01 · CVPR 2017 7 · Radhakrishna Achanta, Sabine Susstrunk

We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringSuperpixels

Similar Papers 제목 키워드 기반

Resolution-independent meshes of super pixels

2019-10-29 · Vitaliy Kurlin, Philip Smith

The over-segmentation into superpixels is an important preprocessing step to smartly compress the input size and speed up higher level tasks. A superpixel was traditionally considered as a small cluster of square-based p…

ClusteringSegmentationSuperpixels

A Feature Clustering Approach Based on Histogram of Oriented Optical Flow and Superpixels

2018-02-28 · A. M. R. R. Bandara, L. Ranathunga, N. A. Abdullah

Visual feature clustering is one of the cost-effective approaches to segment objects in videos. However, the assumptions made for developing the existing algorithms prevent them from being used in situations like segment…

ClusteringOptical Flow EstimationSuperpixels

Peekaboo - Where are the Objects? Structure Adjusting Superpixels

2018-02-08 · Georg Maierhofer, Daniel Heydecker, Angelica I. Aviles-Rivero, Samar M. Alsaleh 외

This paper addresses the search for a fast and meaningful image segmentation in the context of $k$-means clustering. The proposed method builds on a widely-used local version of Lloyd's algorithm, called Simple Linear It…

ClusteringImage SegmentationSemantic SegmentationSuperpixels

Superpixel Pre-Segmentation of HER2 Slides for Efficient Annotation

2022-01-19 · Mathias Öttl, Jana Mönius, Christian Marzahl, Matthias Rübner 외

Supervised deep learning has shown state-of-the-art performance for medical image segmentation across different applications, including histopathology and cancer research; however, the manual annotation of such data is e…

ClusteringDenoisingImage SegmentationMedical Image Segmentation+3

Dynamic Spectral Residual Superpixels

2019-10-10 · Jianchao Zhang, Angelica I. Aviles-Rivero, Daniel Heydecker, Xiaosheng Zhuang 외

We consider the problem of segmenting an image into superpixels in the context of $k$-means clustering, in which we wish to decompose an image into local, homogeneous regions corresponding to the underlying objects. Our …

ClusteringSuperpixels