检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Valeriano, Leonel Cuevas Thomas, Jean-Baptiste Benoit, Alexandre Norwegian Colour and Visual Computing Laboratory NTNU Gjøvik Norway LISTIC Univ. Savoie Mont Blanc Annecy France

We compare a recent dehazing method based on deep learning, Dehazenet, with traditional state-of-the-art approaches, on benchmark data with reference. Dehazenet estimates the depth map from transmission factor on a single color image, which is used to inverse the Koschmieder model of imaging in the presence of haze. In this sense, the solution is still attached to the Koschmieder model. We demonstrate that the transmission is very well estimated by the network, but also that this method exhibits the same limitation than others due to the use of the same imaging model. Copyright © 2018, The Authors. All rights reserved.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Dehazing: Comparison and Analysis

Deep Learning for Dehazing: Comparison and Analysis

引用

colour and visual computing Symposium

作者： Leonel Cuevas Valeriano Jean-Baptiste Thomas Alexandre Benoit The Norwegian Colour and Visual Computing Laboratory NTNU Gjøvik Norway LISTIC Univ. Savoie Mont Blanc Annecy France

关键词： Image color analysis Estimation Atmospheric modeling Machine learning Databases Image restoration Cameras

来源：评论

学校读者我要写书评

暂无评论

Content-dependent adaptation in a soft proof matching experiment 22

Content-dependent adaptation in a soft proof matching experi...

引用

Color Imaging XXII: Displaying, Processing, Hardcopy, and Applications 2017

作者： High, Gregory Green, Phil Nussbaum, Peter Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and Technology Gjøvik Norway

A 'consistent colour appearance' is hard to achieve between different substrates or display systems. A chromatic adaptation transform or substrate adjustment strategy is typically used, but for this present paper a dynamically scaled ICC Media Relative transform was utilised. A soft-proofing system with a method of adjustment was used, allowing simultaneous viewing and adjustment of a reproduction colour image relative to a reference on different simulated substrates under P2 viewing conditions. The degree of adjustment was found to be highly correlated to the image content's lightness and to lesser extent its chromaticity, and was not consistent with the complete adaptation assumed by a media-relative rendering. Other aspects of the experimental setup, including accuracy, observer strategies, and the application of soft proofing for media relative adjustments are discussed. © 2017, Society for Imaging Science and Technology.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

引用

colour and visual computing Symposium

作者： Seyed Ali Amirshahi Stella X. Yu Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and Technology (NTNU) Gjøvik Norway UC Berkeley / ICSI Berkeley CA. USA

The following topics are dealt with: image colour analysis; image classification; feature extraction; learning (artificial intelligence); image enhancement; colour vision; cameras; object detection; medical image proc... 详细信息

关键词： Painting Histograms Feature extraction Weight measurement Image color analysis visualization

来源：评论

学校读者我要写书评

暂无评论

Assessment of Two Fast Multispectral Systems for Imaging of a Cultural Heritage Artifact - A Russian Icon

Assessment of Two Fast Multispectral Systems for Imaging of ...

引用

International IEEE Conference on Signal-Image Technologies and Internet-Based System

作者： Raju Shrestha Jon Yngve Hardeberg Department of Computer Science OsloMet - Oslo Metropolitan University Oslo Norway NTNU in Gj⊘vik Norwegian Colour and Visual Computing Laboratory Gj⊘vik Norway

ISBN: (纸本)9781538693865;9781538693858

As a part of the study of spectral object documentation in cultural heritage, performances of different spectral imaging systems from various institutions and research laboratories were assessed in a Round Robin Test. This paper presents results from our two fast multispectral imaging systems and compared their performances with reference measurements both spectrally and colorimetrically. Among various test objects used in the test, an antique Russian icon is used as a case study here, as imaging of this object possessed different challenges caused by its glossy painted and metallic gold areas with wide range of tones and colors. The results have shown that these systems can be simpler and cheaper alternatives with comparable results to complicated and highly costly hyperspectral imaging systems which are so far mainly used in the digitization of cultural heritage artifacts.

关键词： Cameras Multispectral imaging Cultural differences Hyperspectral imaging Image color analysis Lighting

来源：评论

学校读者我要写书评

暂无评论

Image quality assessment by comparing CNN features between images 14

Image quality assessment by comparing CNN features between i...

引用

Image Quality and System Performance XIV, IQSP 2017

作者： Amirshahi, Seyed Ali Pedersen, Marius Yu, Stella X. Berkeley United States Norwegian Colour and Visual Computing Laboratory NTNU - Norwegian University of Science and Technology Gjøvik Norway

Finding an objective image quality metric that matches the subjective quality has always been a challenging task. We propose a new full reference image quality metric based on features extracted from Convolutional Neural Networks (CNNs). Using a pre-trained AlexNet model, we extract feature maps of the test and reference images at multiple layers, and compare their feature similarity at each layer. Such similarity scores are then pooled across layers to obtain an overall quality value. Experimental results on four state-of-the-art databases show that our metric is either on par or outperforms 10 other state-of-the-art metrics, demonstrating that CNN features at multiple levels are superior to handcrafted features used in most image quality metrics in capturing aspects that matter for discriminative perception. © 2016 Society for Imaging Science and Technology.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Image quality metrics for the evaluation and optimization of capsule video endoscopy enhancement techniques 25

Image quality metrics for the evaluation and optimization of...

引用

25th Color and Imaging Conference: Color Science and Engineering Systems, Technologies, and Applications, CIC 2017

作者： Pedersen, Marius Cherepkova, Olga Mohammed, Ahmed Norwegian Colour and Visual Computing Laboratory Department of Computer Science Norwegian University of Science and Technology Gjøvik2815 Norway

ISBN: (纸本)9780892083282

Capsule endoscopy, using a wireless camera to capture the digestive track, is becoming a popular alternative to traditional colonoscopy. The images obtained from a capsule have lower quality compared to traditional colonoscopy, and high-quality images are required by medical doctors in order to set an accurate diagnosis. Over the last years several enhancement techniques have been proposed to improve the quality of capsule images. In order to verify that the capsule images have the required diagnostic quality some kind of quality assessment is required. In this work, the authors evaluate state-of-the-art no-reference image quality metrics for capsule video endoscopy. Furthermore, they use the best performing metric to optimize one of the capsule video endoscopy enhancement methods and validate through subjective experiment. © 2017 Society for Imaging Science and Technology.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Old Man in Warnemüunde (1907) colouring palette: A case study on the use of hyperspectral imaging for pigment identification 25

Old Man in Warnemüunde (1907) colouring palette: A case stu...

引用

25th Color and Imaging Conference: Color Science and Engineering Systems, Technologies, and Applications, CIC 2017

作者： Deborah, Hilda George, Sony Hardeberg, Jon Y. Ferrer, Jin Strand Sandu, Irina C.A. Norwegian Colour and Visual Computing Laboratory Department of Computer Science NTNU-Norwegian University of Science and Technology Gjøvik Norway Munch Museum Oslo Norway

ISBN: (纸本)9780892083282

The paper presents results from hyperspectral identification of the colouring palette used by Edvard Munch in a canvas painting entitled "Old Man in Warnemünde". The painting is part of a collection at the Munch Museum in Oslo. A collaboration between the Conservation Department of the Munch Museum and the Norwegian colour and visual computing laboratory from NTNU has allowed to analyze several points of the painting by means of hyperspectral imaging and identify thus the pigments present. The hyperspectral pigment identification involves a use of two pigment databases (Kremer and ENST) which were created using different binding media. Some results from the hyperspectral analysis were also validated through elemental analysis by means of XRF. The pigment identification method employs the shape component of spectral Kullback-Leibler pseudo-divergence function, instead of the widely-used but inaccurate spectral angle mapper. In addition to the interest of this pigment analysis for conservation practice of this particular painting, an important contribution of this paper is the validation of hyperspectral imaging and processing methods for pigment identification.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Semantic analysis of (reflectional) visual symmetry: A human-centred computational model for declarative explainability

arXiv

引用

arXiv 2018年

作者： Suchan, Jakob Bhatt, Mehul Varadarajan, Srikrishna Seyed Ali Amirshahi Yu, Stella CoDesign Lab EU Cognitive Vision Vision Orebro University University of Bremen Germany Norwegian Colour and Visual Computing Laboratory Norwegian University of Science and Technology ICSI Vision Group UC Berkeley United States

We present a computational model for the semantic interpretation of symmetry in naturalistic scenes. Key features include a human-centred representation, and a declarative, explainable interpretation model supporting deep semantic question-answering founded on an integration of methods in knowledge representation and deep learning based computer vision. In the backdrop of the visual arts, we showcase the framework's capability to generate human-centred, queryable, relational structures, also evaluating the framework with an empirical study on the human perception of visual symmetry. Our framework represents and is driven by the application of foundational, integrated Vision and Knowledge Representation and Reasoning methods for applications in the arts, and the psychological and social sciences. Copyright © 2018, The Authors. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

An adaptive combination of dark and bright channel priors for single image Dehazing 25

An adaptive combination of dark and bright channel priors fo...

引用

25th Color and Imaging Conference: Color Science and Engineering Systems, Technologies, and Applications, CIC 2017

作者： De Dravo, Vincent Whannou El Khoury, Jessica Thomas, Jean Baptiste Mansouri, Alamin Hardeberg, Jon Yngve Norwegian Colour and Visual Computing Laboratory NTNU Gjøvik Norway Le2i FRE CNRS 2005 Université Bourgogne Franche-Comté Dijon France

ISBN: (纸本)9780892083282

Dehazing methods based on prior assumptions derived from statistical image properties fail when these properties do not hold. This is most likely to happen when the scene contains large bright areas, such as snow and sky, due to the ambiguity between the airlight and the depth information. This is the case for the popular dehazing method Dark Channel Prior. In order to improve its performance, the authors propose to combine it with the recent multiscale STRESS, which serves to estimate Bright Channel Prior. visual and quantitative evaluations show that this method outperforms Dark Channel Prior and competes with the most robust dehazing methods, since it separates bright and dark areas and therefore reduces the color cast in very bright regions. © 2017 Society for Imaging Science and Technology.

关键词： Demulsification

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：