检索结果-内蒙古大学图书馆

Multi-scale region composition of hierarchical image segmentation

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第43-44期79卷 32833-32855页

作者： Peng, Bo Al-Huda, Zaid Xie, Zhuyang Wu, Xi Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Natl Engn Lab Integrated Transportat Big Data App Chengdu Peoples R China Chengdu Univ Informat Technol Sch Comp Sci Chengdu 610225 Peoples R China

hierarchical image segmentation is a prominent trend in the literature as a way to improve the segmentation quality. Generally, meaningful objects in an image are described by segments from different scales. Thus, one may spend extra effort on searching for the best representation of objects in the hierarchical segmentation result. In this paper, a novel algorithm is proposed to optimally select the segmentation scale, which leads to a composite segmentation as the output. To this end, the quality of regions from different scales of the hierarchical segmentation is evaluated. Then, a graphical model is constructed as a set of nodes. The weights among nodes are computed according to the segmentation quality of regions in multiple levels. In order to optimize the labeling of each node in the graph, the composition process is performed twice with two sampling intervals. Comprehensive experiments are conducted on different datasets for popular hierarchical image segmentation algorithms. The results show that the output of the proposed algorithm can improve the quality of hierarchical segmentation in a single scale at a low cost of computation.

关键词： hierarchical image segmentation segmentation evaluation Graphical model Scale selection

来源：评论

学校读者我要写书评

暂无评论

Optimal Scale of hierarchical image segmentation with Scribbles Guidance for Weakly Supervised Semantic segmentation

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2021年第10期35卷

作者： Al-Huda, Zaid Zhai, Donghai Yang, Yan Algburi, Riyadh Nazar Ali Southwest Jiaotong Univ Sch Comp & Artificial Intelligent Chengdu 610031 Sichuan Peoples R China Southwest Jiaotong Univ Sch Mech Engn Chengdu 610031 Sichuan Peoples R China

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is 69.3% mIoU.

关键词： Deep convolutional neural networks graphical model hierarchical image segmentation semantic segmentation weakly supervised segmentation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Scale-Aware Realignments of hierarchical image segmentation 23rd

Evaluation of Scale-Aware Realignments of Hierarchical Image...

引用

23rd Iberoamerican Congress on Pattern Recognition (CIARP)

作者： Adao, Milena M. Ferzoli Guimaraes, Silvio Jamil Patrocinio, Zenilton K. G., Jr. Pontificia Univ Catolica Minas Gerais Comp Sci Dept Belo Horizonte MG Brazil

ISBN: (纸本)9783030134686;9783030134693

A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects may appear at different scales due to their size or to their distance from the camera. One possible solution to cope with that is to realign the hierarchy such that every region containing an object is at the same level (or scale). In this work, we explore the use of regression to predict the best scale value for given region, which is then used to realign the entire hierarchy. Experimental results are presented for two different segmentation methods;along with an analysis of the adoption of different combination of mid-level features to describe regions.

关键词： hierarchical image segmentation Alignment of hierarchy Regression Random forest Neural network

来源：评论

学校读者我要写书评

暂无评论

hierarchical image segmentation Based on Iterative Contraction and Merging

引用

IEEE TRANSACTIONS ON image PROCESSING 2017年第5期26卷 2246-2260页

作者： Syu, Jia-Hao Wang, Sheng-Jyh Wang, Li-Chun Natl Chiao Tung Univ Commun Engn Dept Hsinchu 30010 Taiwan Natl Chiao Tung Univ Elect Engn Dept Hsinchu 30010 Taiwan

In this paper, we propose a new framework for hierarchical image segmentation based on iterative contraction and merging. In the proposed framework, we treat the hierarchical image segmentation problem as a sequel of optimization problems, with each optimization process being realized by a contraction-and-merging process to identify and merge the most similar data pairs at the current resolution. At the beginning, we perform pixel-based contraction and merging to quickly combine image pixels into initial region-elements with visually indistinguishable intra-region color difference. After that, we iteratively perform region-based contraction and merging to group adjacent regions into larger ones to progressively form a segmentation dendrogram for hierarchical segmentation. Comparing with the state-of-the-art techniques, the proposed algorithm can not only produce high-quality segmentation results in a more efficient way, but also keep a lot of boundary details in the segmentation results.

关键词： Affinity matrix contraction process hierarchical image segmentation

来源：评论

学校读者我要写书评

暂无评论

hierarchical image segmentation Relying on a Likelihood Ratio Test 18th

Hierarchical Image Segmentation Relying on a Likelihood Rati...

引用

18th International Conference on image Analysis and Processing (ICIAP)

作者： Guimaraes, Silvio Jamil F. do Patrocinio, Zenilton Kleber G., Jr. Kenmochi, Yukiko Cousty, Jean Najman, Laurent PUC Minas ICEI DCC VIPLAB Belo Horizonte MG Brazil Univ Paris Est LIGM ESIEE Paris CNRS Champs Sur Marne France

ISBN: (纸本)9783319232348;9783319232331

hierarchical image segmentation provides a set of image segmentations at different detail levels in which coarser details levels can be produced by simple merges of regions from segmentations at finer detail levels. However, many image segmentation algorithms relying on similarity measures lead to no hierarchy. One of interesting similarity measures is a likelihood ratio, in which each region is modelled by a Gaussian distribution to approximate the cue distributions. In this work, we propose a hierarchical graph-based image segmentation inspired by this likelihood ratio test. Furthermore, we study how the inclusion of hierarchical property have influenced the computation of quality measures in the original method. Quantitative and qualitative assessments of the method on three well known image databases show efficiency.

关键词： hierarchical image segmentation Graph-based method Statistical properties

来源：评论

学校读者我要写书评

暂无评论

Re-ranking of the Merging Order for hierarchical image segmentation 20th

Re-ranking of the Merging Order for Hierarchical Image Segme...

引用

20th Iberoamerican Congress on Pattern Recognition (CIARP)

作者： do Patrocinio, Zenilton Kleber G., Jr. Guimaraes, Silvio Jamil F. Pontificia Univ Catolica Minas Gerais Belo Horizonte MG Brazil

ISBN: (纸本)9783319257518;9783319257501

hierarchical image segmentation provides a set of image segmentations at different detail levels in which coarser detail levels can be produced from merges of regions belonging to finer detail levels. However, similarity measures adopted by hierarchical image segmentation methods do not always consider the homogeneity of the combined components. In this work, we propose a hierarchical graph-based image segmentation using a new similarity measure based on the variability of the merged components which is responsible for the re-ranking of the merging order that was originally established by the minimum spanning tree. Furthermore, we study how the inclusion of this characteristic has influenced the quality measures. Experiments have shown the superior performance of the proposed method on three well known image databases, and its robustness to noise was also demonstrated.

关键词： hierarchical image segmentation Graph-based method Similarity measure Region-merging criterion

来源：评论

学校读者我要写书评

暂无评论

An Improved NAMLab image segmentation Algorithm Based on the Earth Moving Distance and the CIEDE2000 Color Difference Formula 1

引用

18th International Conference on Intelligent Computing (ICIC)

作者： Zheng, Yunping Xu, Yuan Qiu, Shengjie Li, Wenqiang Zhong, Guichuang Chen, Mingyi Sarem, Mudar South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China Gen Org Remote Sensing Damascus Syria

ISBN: (数字)9783031138706

ISBN: (纸本)9783031138706;9783031138690

How to effectively segment an image into the non-overlapping sub-regions and make the segmentation results conform to the perception of the human vision have always been a key issue in the field of computer vision. Extensive studies have proved that the CIEDE2000 formula is the most consistent method with the color space distribution for objects recognized by human perspective. The representation system of the NAMLab algorithm ignored the differences of the pixels at different positions of a region, and produced information loss in the process of dimensionality reduction. Therefore, in this paper, we propose an improved NAMLab algorithm based on the Earth Moving Distance (EMD) and the CIEDE2000 color difference formula. First, a K-means clustering is performed on the Lab features of all the pixels in the region in order to obtain the region color feature histogram. Then, the CIEDE2000 formula is used to calculate the differences between the cluster centers of the adjacent region color histograms. Finally, the EMD algorithm is used to calculate the color similarity among regions. When compared with the state-of-the-art algorithms, the experimental results presented in this paper demonstrate that the proposed algorithm has better segmentation performance, and the obtained segmentation results are more in line with the perception of the human vision.

关键词： hierarchical image segmentation image representation Non-symmetry and Anti-packing pattern representation Model (NAM) CIEDE2000 Earth Moving Distance (EMD)

来源：评论

学校读者我要写书评

暂无评论

A Novel Semantic segmentation Algorithm for RGB-D images Based on Non-Symmetry and Anti-Packing Pattern Representation Model

引用

IEEE ACCESS 2023年 11卷 36290-36299页

作者： Zheng, Yunping Xu, Yuan Qiu, Shengjie Li, Wenqiang Zhong, Guichuang Sarem, Mudar South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Gen Org Remote Sensing Damascus Syria

With the rapid development of deep learning technology, the accuracy of image semantic segmentation tasks has been greatly improved. However, indoor RGB-D semantic segmentation remains a challenging problem because of the complexity of indoor environments. The emergence of depth sensors makes depth information gradually used to improve the effect of semantic segmentation. The splicing of weights such as between the RGB features and the depth features which are used as the input features of the neural network can effectively improve the accuracy of the indoor semantic segmentation tasks. Most previous researches focused on improving the performance of semantic segmentation by adjusting the structure of convolutional neural network. These researches have either added attention mechanism or performed data augmentation on input features, but they didn't make full use of the boundary information and the texture information of the original RGB image. In this paper, we propose a semantic segmentation algorithm for RGB-D images based on Non-symmetry and Anti-packing pattern representation Model (NAM). The core idea of the proposed algorithm is to take the channel-wise concatenation of pre-segmentation labels provided by the traditional hierarchical image segmentation and RGB-D features as the input of the neural network so as to guide the semantic segmentation tasks. The extensive experiments are conducted on the popular indoor RGB-D semantic segmentation datasets. When compared with the state-of-art algorithms, the experimental results presented in this paper show that our proposed method has improved the performance of image semantic segmentation networks on several popular neural network architectures.

关键词： Semantic segmentation Deep learning Neural networks Semantics image color analysis Feature extraction hierarchical image segmentation image representation NAM RGB-D and semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning to realign hierarchy for image segmentation

引用

PATTERN RECOGNITION LETTERS 2020年 133卷 287-294页

作者： Adao, Milena M. Guimaraes, Silvio Jamil F. Patrocinio Jr, Zenilton K. G. Pontificia Univ Catolica Minas Gerais Comp Sci Dept Belo Horizonte MG Brazil

A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects (or even parts of the same object) may appear at different scales due to their size differences or to their distinct distances from the camera. One possible solution to cope with that is to realign the hierarchy such that every region containing an object (or its parts) is at the same level. In this work, we have explored the use of regression models to predict score values for regions belonging to a hierarchy of partitions, which are used to realign it. We have also proposed a new score calculation and a new assessment strategy considering all user-defined segmentations that exist in the ground-truth. Experimental results have pointed out that the use of new proposed score was able to improve final segmentation results. (C) 2020 Elsevier B.V. All rights reserved.

关键词： hierarchical image segmentation Alignment of hierarchy Regression Random forest Neural network

来源：评论

学校读者我要写书评

暂无评论

Salient object detection based on hierarchical segmentation and objectness-guided

引用

JOURNAL OF ELECTRONIC IMAGING 2024年第1期33卷 013001-013001页

作者： Shang, Jinxia Li, Runxin Liu, Yun Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming Peoples R China Yunnan Key Lab Comp Technol Applicat Kunming Peoples R China Southwest Univ Coll Artificial Intelligence Chongqing Peoples R China

Unsupervised salient object detection aims to automatically detect important or attractive target objects in the scene without any user annotation. Compared to fully supervised, it can save a lot of manpower and resources invested in pixel-level annotation. However, the performance of existing unsupervised methods is still far from satisfactory because of the interference of complex backgrounds and the lack of knowledge in the semantic layer of scene objects. To solve these challenging problems, in this paper, we propose a new bottom-up method to better highlight the integral salient object region by exploiting the co-occurrence of saliency and objectness properties. Specifically, saliency estimation effectively utilizes low-level visual features based on high-quality hierarchical image segmentation (convolutional oriented boundaries). The objectness scoring is mainly obtained through the improved object proposals mapping map. Experiment results demonstrate that the proposed method can efficiently remove the interference of non-salient objects and complex background while preserving more salient object regions.

关键词： hierarchical image segmentation salient object object proposals

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：