检索结果-内蒙古大学图书馆

image parsing: Unifying segmentation, detection, and recognition

INTERNATIONAL JOURNAL OF COMPUTER VISION 2005年第2期63卷 113-140页

作者： Tu, ZW Chen, XG Yuille, AL Zhu, SC Univ Calif Los Angeles Dept Stat Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Psychol Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90095 USA

In this paper we present a Bayesian framework for parsing images into their constituent visual patterns. The parsing algorithm optimizes the posterior probability and outputs a scene representation as a "parsing graph", in a spirit similar to parsing sentences in speech and natural language. The algorithm constructs the parsing graph and re-configures it dynamically using a set of moves, which are mostly reversible Markov chain jumps. This computational framework integrates two popular inference approaches-generative (top-down) methods and discriminative (bottom-up) methods. The former formulates the posterior probability in terms of generative models for images defined by likelihood functions and priors. The latter computes discriminative probabilities based on a sequence (cascade) of bottom-up tests/filters. In our Markov chain algorithm design, the posterior probability, defined by the generative models, is the invariant (target) probability for the Markov chain, and the discriminative probabilities are used to construct proposal probabilities to drive the Markov chain. Intuitively, the bottom-up discriminative probabilities activate top-down generative models. In this paper, we focus on two types of visual patterns-generic visual patterns, such as texture and shading, and object patterns including human faces and text. These types of patterns compete and cooperate to explain the image and so image parsing unifies image segmentation, object detection, and recognition of we use generic visual patterns only then image parsing will correspond to image segmentation (Tu and Zhu, 2002. IEEE Trans. PAM1, 24(5):657-673). We illustrate our algorithm on natural images of complex city scenes and show examples where image segmentation can be improved by allowing object specific knowledge to disambiguate low-level segmentation cues, and conversely where object detection can be improved by using generic visual patterns to explain away shadows and occlusions.

关键词： image parsing image segmentation object detection object recognition data driven Markov Chain Monte Carlo AdaBoost

来源：评论

学校读者我要写书评

暂无评论

image parsing by loopy dynamic programming

引用

NEUROCOMPUTING 2014年 145卷 240-249页

作者： Zhang, Shizhou Wang, Jinjun Gong, Yihong Zhang, Shun Zhang, Xinzi Lan, Xuguang Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China

The image parsing process gives labels to image regions, as well as information including shape, semantics and context. Although it is one of the most important features in the human visual system, automatic image parsing using computer vision techniques remains difficult due to computational issue. In this paper we introduce a novel method to address this limitation. Our system models an image as a set of regions and uses a novel hypotheses generation algorithm to get possible image parsing solutions for final re-scoring. Our proposed hypotheses generation algorithm, called Loopy Dynamic Programming (LDP), handles large search space efficiently and gives good parsing hypotheses for testing. With such capacity, we are able to apply more precise and complex image models to achieve better performance. In addition, our system can perform image segmentation, detection and classification simultaneously. Experimental results using Pascal VOC 2007 dataset show that the proposed technique achieves very promising performance in all the three tasks. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Loopy dynamic programming image parsing Segmentation Detection Classification

来源：评论

学校读者我要写书评

暂无评论

Learning deep representations for semantic image parsing： a comprehensive overview

引用

Frontiers of Computer Science 2018年第5期12卷 840-857页

作者： Lili HUANG Jiefeng PENG Ruimao ZHANG Guanbin LI Liang LIN School of Data and Computer Science Sun Yat-sen University Guangzhou 510006 China

Semantic image parsing, which refers to the pro- cess of decomposing images into semantic regions and constructing the structure representation of the input, has re- cently aroused widespread interest in the field of computer vision. The recent application of deep representation learning has driven this field into a new stage of development. In this paper, we summarize three aspects of the progress of research on semantic image parsing, i.e., category-level semantic segmentation, instance-level semantic segmentation, and beyond segmentation. Specifically, we first review the general frameworks for each task and introduce the relevant variants. The advantages and limitations of each method are also discussed. Moreover, we present a comprehensive comparison of different benchmark datasets and evaluation metrics. Finally, we explore the future trends and challenges of semantic image parsing.

关键词： semantic image segmentation deep learning onvolutional neural networks image parsing

来源：评论

学校读者我要写书评

暂无评论

image parsing: Unifying segmentation, detection, and recognition

Image parsing: Unifying segmentation, detection, and recogni...

引用

9th IEEE International Conference on Computer Vision

ISBN: (纸本)0769519504

关键词： image parsing image segmentation object detection object recognition data driven Markov Chain Monte Carlo AdaBoost

来源：评论

学校读者我要写书评

暂无评论

image parsing with Superpixels and Gray image analysis 11

Image Parsing with Superpixels and Gray Image analysis

引用

11th International Symposium on Computational Intelligence and Design (ISCID)

作者： Yang, Feng Ma, Zheng Xie, Mei Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Sichuan Peoples R China Wenzhou Med Univ Sch Informat & Engn Wenzhou Peoples R China

ISBN: (纸本)9781538685273

This paper presents an effective system with the aim of solving the problem of image parsing. In order to make full use of information and characteristics in the input image(colored), the gray image is calculated from the color image, and the superpixels of both the gray image and the color one are obtained. After feature extraction, the features abstracted from color image and gray image are fused together to construct the final features. Then, the likelihood ratio scores of the input image and the similar images in the retrieval set are calculated according to these final features and the final labeling result are obtained through MRF analysis. The effectiveness of the proposed system is tested on the public dataset of SIFT Flow and experimental result shows that the proposed method in this paper is efficient.

关键词： image parsing image segmentation image representation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Nonparametric image parsing

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2015年第10期25卷 1565-1575页

作者： Nguyen, Tam V. Lu, Canyi Sepulveda, Jose Yan, Shuicheng Singapore Polytech Dept Technol Innovat & Enterprise Singapore 139651 Singapore Natl Univ Singapore Dept Elect & Comp Engn Singapore 119077 Singapore

In this paper, we present an adaptive nonparametric solution to the image parsing task, namely, annotating each image pixel with its corresponding category label. For a given test image, first, a locality-aware retrieval set is extracted from the training data based on superpixel matching similarities, which are augmented with feature extraction for better differentiation of local superpixels. Then, the category of each superpixel is initialized by the majority vote of the k-nearest-neighbor superpixels in the retrieval set. Instead of fixing k as in traditional nonparametric approaches, here, we propose a novel adaptive nonparametric approach that determines the sample-specific k for each test image. In particular, k is adaptively set to be the number of the fewest nearest superpixels that the images in the retrieval set can use to get the best category prediction. Finally, the initial superpixel labels are further refined by contextual smoothing. Extensive experiments on challenging data sets demonstrate the superiority of the new solution over other state-of-the-art nonparametric solutions.

关键词： Adaptive nonparametric method image parsing scene understanding

来源：评论

学校读者我要写书评

暂无评论

Relationship aware context adaptive deep learning for image parsing

引用

INFORMATION SCIENCES 2022年 607卷 506-518页

作者： Azam, Basim Mandal, Ranju Verma, Brijesh Cent Queensland Univ Ctr Intelligent Syst Brisbane Australia

The formation of deep learning architectures is challenged in several aspects, among the major and fundamental steps to develop an effective image parsing network is feature selection. In addition, the exploration of context information in such frameworks is also of prime importance. In this research, a novel architecture that utilizes distinctive feature selection algorithm, and the context adaptive information is proposed. The feature selec-tion algorithm defines the idea of exploring relationship aware information to minimize the similarity among features and select an affluent and optimum set of feature represen-tations. The efficacy of proposed framework is analyzed using several benchmark datasets including Stanford Background, CamVid and MSRC v2. The proposed framework achieves 93.8%, 91.8% and 96.1% global pixel segmentation accuracy on the benchmark datasets respectively. Furthermore, we present a comprehensive comparative analysis with state -of-the-art techniques in the literature. The analysis reveals meaningful refinements in terms of segmentation accuracy.(c) 2022 Elsevier Inc. All rights reserved.

关键词： image parsing Feature selection Semantic segmentation Deep learning

来源：评论

学校读者我要写书评

暂无评论

From image parsing to Painterly Rendering

引用

ACM TRANSACTIONS ON GRAPHICS 2009年第1期29卷 1–11页

作者： Zeng, Kun Zhao, Mingtian Xiong, Caiming Zhu, Song-Chun Lotus Hill Inst Ezhou Hubei Province Peoples R China Univ Calif Los Angeles Dept Phys Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Stat Los Angeles CA 90095 USA

We present a semantics-driven approach for stroke-based painterly rendering, based on recent image parsing techniques [Tu et al. 2005;Tu and Zhu 2006] in computer vision. image parsing integrates segmentation for regions, sketching for curves, and recognition for object categories. In an interactive manner, we decompose an input image into a hierarchy of its constituent components in a parse tree representation with occlusion relations among the nodes in the tree. To paint the image, we build a brush dictionary containing a large set (760) of brush examples of four shape/appearance categories, which are collected from professional artists, then we select appropriate brushes from the dictionary and place them on the canvas guided by the image semantics included in the parse tree, with each image component and layer painted in various styles. During this process, the scene and object categories also determine the color blending and shading strategies for inhomogeneous synthesis of image details. Compared with previous methods, this approach benefits from richer meaningful image semantic information, which leads to better simulation of painting techniques of artists using the high-quality brush dictionary. We have tested our approach on a large number (hundreds) of images and it produced satisfactory painterly effects.

关键词： Algorithms Human Factors image parsing nonphotorealistic rendering orientation field painterly rendering primal sketch

来源：评论

学校读者我要写书评

暂无评论

A crowding multi-objective genetic algorithm for image parsing

引用

NEURAL COMPUTING & APPLICATIONS 2016年第8期27卷 2217-2227页

作者： Joseph, Ferdin Joe John Auwatanamongkol, Surapong Natl Inst Dev Adm Grad Sch Appl Stat Dept Comp Sci Bangkok Thailand

image parsing is a process of understanding the contents of an image. The process normally involves labeling pixels or superpixels of a given image with classes of objects that may exist in the image. The accuracy of such labeling for the existing methodologies still needs to be improved. The parsing method needs to be able to identify multiple instances of objects of different classes and sizes. In our previous work, a novel feature representation for an instance of objects in an image was proposed for object recognition and image parsing. The feature representation consists of the histogram vector of 2 g of visual word ids of the two successive clockwise neighbors of any superpixels in the object instance and the shape vector of the instance. Using the feature representation, the instance can be classified with very high accuracy by the per class support vector machines (SVMs). A multi-objective genetic algorithm is also proposed to find a subset of image segments that would best constitute an instance for a class of objects, i.e., maximizing the SVM classification score and the size of the instance. However, the genetic algorithm can only identify a single instance for each class of objects, despite the fact that many instances of the same class may exist. In this paper, a crowding genetic algorithm is used instead to search for multiple optimal solutions and help alleviate this deficiency. The experimental results show that this crowding genetic algorithm performs better than the previously proposed method as well as the existing methodologies, in terms of class-wise and pixel-wise accuracy. The qualitative results also clearly show that this method can effectively identify multiple object instances existing in a given image.

关键词： image parsing Scene parsing Genetic algorithm Crowding

来源：评论

学校读者我要写书评

暂无评论

Graphonomy: Universal image parsing via Graph Reasoning and Transfer

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第5期44卷 2504-2518页

作者： Lin, Liang Gao, Yiming Gong, Ke Wang, Meng Liang, Xiaodan Sun Yat Sen Univ Guangzhou 510006 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China Minist Educ Engn Res Ctr Adv Comp Engn Software Guangzhou Peoples R China Hefei Univ Technol Hefei 230000 Peoples R China

Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (*** discrepant label granularity) without extensive re-training. Learning a single universal parsing model by unifying label annotations from different domains or at various levels of granularity is a crucial but rarely addressed topic. This poses many fundamental learning challenges, *** underlying semantic structures among different label granularity or mining label correlation across relevant tasks. To address these challenges, we propose a graph reasoning and transfer learning framework, named "Graphonomy," which incorporates human knowledge and label taxonomy into the intermediate graph representation learning beyond local convolutions. In particular, Graphonomy learns the global and structured semantic coherency in multiple domains via semantic-aware graph reasoning and transfer, enforcing the mutual benefits of the parsing across domains (*** datasets or co-related tasks). The Graphonomy includes two iterated modules: Intra-Graph Reasoning and Inter-Graph Transfer modules. The former extracts the semantic graph in each domain to improve the feature representation learning by propagating information with the graph;the latter exploits the dependencies among the graphs from different domains for bidirectional knowledge transfer. We apply Graphonomy to two relevant but different image understanding research topics: human parsing and panoptic segmentation, and show Graphonomy can handle both of them well via a standard pipeline against current state-of-the-art approaches. Moreover, some extra benefit of our framework is demonstrated, e.g., generating the human parsing at various levels of granularity by unifying annotations across different datasets.

关键词： Semantics Task analysis Cognition Feature extraction Annotations image segmentation Faces image parsing knowledge reasoning transfer learning panoptic segmentation

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：