arXiv 0806.39282008-06-24cs.CV

Conceptualization of seeded region growing by pixels aggregation. Part 3: a wide range of algorithms

Vincent Tariel

英文摘要：

In the two previous papers of this serie, we have created a library, called Population, dedicated to seeded region growing by pixels aggregation and we have proposed different growing processes to get a partition with or without a boundary region to divide the other regions or to get a partition invariant about the seeded region initialisation order. Using this work, we implement some algorithms belonging to the field of SRGPA using this library and these growing processes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Conceptualization of seeded region growing by pixels aggregation. Part 1: the framework

Adams and Bishop have proposed in 1994 a novel region growing algorithm called seeded region growing by pixels aggregation (SRGPA). This paper introduces a framework to implement an algorithm using SRGPA. This framework is built around two concepts: localization and organization of applied action. This conceptualization gives a quick implementation of algorithms, a direct translation between the mathematical idea and the numerical implementation, and an improvement of algorithms efficiency.

2008-06-24cs.CV

Conceptualization of seeded region growing by pixels aggregation. Part 2: how to localize a final partition invariant about the seeded region initialisation order

In the previous paper, we have conceptualized the localization and the organization of seeded region growing by pixels aggregation (SRGPA) but we do not give the issue when there is a collision between two distinct regions during the growing process. In this paper, we propose two implementations to manage two classical growing processes: one without a boundary region region to divide the other regions and another with. Unfortunately, as noticed by Mehnert and Jakway (1997), this partition depends on the seeded region initialisation order (SRIO). We propose a growing process, invariant about SR…

2008-06-24cs.CV

Conceptualization of seeded region growing by pixels aggregation. Part 4: Simple, generic and robust extraction of grains in granular materials obtained by X-ray tomography

This paper proposes a simple, generic and robust method to extract the grains from experimental tridimensionnal images of granular materials obtained by X-ray tomography. This extraction has two steps: segmentation and splitting. For the segmentation step, if there is a sufficient contrast between the different components, a classical threshold procedure followed by a succession of morphological filters can be applied. If not, and if the boundary needs to be localized precisely, a watershed transformation controlled by labels is applied. The basement of this transformation is to localize a lab…

2008-07-23cs.CV

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

Peking University（北京大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）；Dalian University of Technology（大连理工大学）；Tsinghua University（清华大学）

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions …

2023-03-30cs.CV