检索结果-内蒙古大学图书馆

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Laranjeira, Camila Mota, Virginia Fernandes dos Santos, Jefersson Alex Univ Fed Minas Gerais Comp Sci Dept Belo Horizonte MG Brazil Univ Fed Minas Gerais Colegio Tecn Belo Horizonte MG Brazil

ISBN: (纸本)9781665423540

Machine Learning bias is an issue with two main disadvantages. It compromises the quantitative performance of a system, and depending on the application, it may have a strong impact on society from an ethical viewpoint. In this work we inspect the literature on computer Vision focusing on human-centered applications such as computer-aided diagnosis and face recognition to outline several forms of bias, bringing study cases for a more thorough inspection of how this issue takes form in the field of machine learning applied to images. We conclude with proposals from the literature on how to solve, or at least minimize, the impacts of bias.

关键词： graphics Ethics computer vision Face recognition Focusing Machine learning Inspection

来源：评论

学校读者我要写书评

暂无评论

Partial Least Squares image Clustering 28

Partial Least Squares Image Clustering

引用

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Kloss, Ricardo Barbosa Cirne, Marcos Vinicius Mussel Silva, Samira Pedrini, Helio Schwartz, William Robson Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte MG Brazil Univ Estadual Campinas Inst Comp Campinas SP Brazil

ISBN: (纸本)9781467379625

Clustering techniques have been widely used in areas that handle massive amounts of data, such as statistics, information retrieval, data mining and image analysis. this work presents a novel image clustering method called Partial Least Square image Clustering (PLSIC), which employs a one-against-all Partial Least Squares classifier to find image clusters with low redundancy (each cluster represents different visual concept) and high purity (two visual concepts should not be in the same cluster). the main goal of the proposed approach is to find groups of images in an arbitrary set of unlabeled images to convey well defined visual concepts. As a case study, we evaluate the PLSIC to the video summarization problem by means of experiments with 50 videos from various genres of the Open Video Project, comparing summaries generated by the PLSIC with other video summarization approaches found in the literature. A experimental evaluation demonstrates that the proposed method can produce very satisfactory results.

关键词： image Clustering Partial Least Squares Video Summarization Shot Sampling

来源：评论

学校读者我要写书评

暂无评论

Non-local medians filter for joint Gaussian and impulsive image denoising 34

Non-local medians filter for joint Gaussian and impulsive im...

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Levada, Alexandre L. M. Univ Fed Sao Carlos Comp Dept Sao Carlos SP Brazil

ISBN: (纸本)9781665423540

image denoising concerns with the development of filters to remove or attenuate random perturbations in the observed data, but at the same time, preserving most of edges and fine details in the scene. One problem with joint additive Gaussian and impulsive noise degradation is that they are spread over all frequencies of the signal. Hence, the most effective filters for this kind of noise are implemented in the spatial domain. In this paper, we proposed a Non-Local Medians filter that combine the medians of every patch of a search window using two distinct similarity measures: the Euclidean distance and the Kullback-Leibler divergence between Gaussian densities estimated from the patches. Computational experiments with 25 images corrupted by joint Gaussian and impulsive noises show that the proposed method is capable of producing, on average, significant higher PSNR and SSIM than the combination of the median filter and the Non-Local Means filter applied independently.

关键词： graphics Degradation Additives Density measurement Perturbation methods image edge detection Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

An egg image noise model for digital visual counting processing 34

An egg image noise model for digital visual counting process...

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Ramirez Behaine, Carlos Alberto Ide, Jaime S. Univ Passo Fundo UPF Dept Elect Engn BR 285 BR-99052900 Passo Fundo RS Brazil Yale Univ Sch Med 34 Pk St New Haven CT 06519 USA

ISBN: (纸本)9781665423540

Contactless counting is a suitable technique for the measurement of fragile commodities, acting as a successful tool for industrial production control. Visual counting processing is one of the most common contactless methods for non-invasive measurements. However, the creation of accurate models for processing images in realistic scenarios is still challenging due to the existence of noise in optical sensors. this paper proposes an egg image noise model for digital visual counting processing that incorporates particular aspects of real images in such acquisition systems. the matching function is defined in hue saturation value (HSV) color space, and a classical nearest neighbor cluster classification is utilized for the counting. Validation experiments are executed with low and high diversity test images, and the performance of the proposed model is compared to existing methods. the matching function results suggest that the introduced egg image noise model is able to represent more accurately complex aspects of egg images in an industrial environment. the comparative results show that the proposed model significantly improves digital visual counting, in terms of egg counting errors, and outperforms in 9% the second best method.

关键词： Visualization image color analysis Production control Optical sensors Colored noise

来源：评论

学校读者我要写书评

暂无评论

Building structured lighting applications using low-cost cameras 30

Building structured lighting applications using low-cost cam...

引用

30th SIBGRAPI Conference on graphics, Patterns and images Tutorials (SIBGRAPI-T)

作者： Borsato, Frank H. Morimoto, Carlos H. Univ Tecnol Fed Parana Curitiba Parana Brazil Univ Sao Paulo Sao Paulo Brazil

ISBN: (纸本)9781538622193

Structured lighting is a computer vision technique that projects illumination patterns onto the scene to facilitate feature extraction from the captured images. the use of low-cost cameras is avoided not only due to their low image quality but mostly due to the lack of a synchronization mechanism for the illuminators. In this paper we propose a method to synchronize low-cost cameras and illuminators based on the dynamic estimation of the camera sensor exposure and number of lines. At the same time, the use of structured stroboscopic lighting is used to enhance the image quality. Starting with a coarse estimation of the sensor parameters, we developed computer vision algorithms that detect image artifacts created by the structured lighting when the illuminators are not correctly synchronized with the camera frames. the detected artifacts are used to refine the estimation of the sensor parameters and to adjust the firing of the illuminators until a clear picture is obtained. Our technique requires a simple external circuit to control the firing of the illuminators, that is adjusted by software, and allows virtually any modern digital camera to be used in structured lighting applications. We demonstrate the use of this technique in a fast 187 fps robust pupil detector that can be used for gaze interaction applications.

关键词： Cameras Lighting Synchronization Light sources Software image processing

来源：评论

学校读者我要写书评

暂无评论

GEOMETRIC TRANSFORMATION AND DATA ORGANIZATION IN DIGITAL image processing.

Proceedings of the International Symposium on Remote Sensing...

引用

Proceedings of the International symposium on Remote Sensing of Environment 1980年 159-177页

作者： Yang Shih-ren

In advanced digital image processing systems, geometric correction or transnformation is usually performed by an array processor. However, it is often difficult to perform geometric transformations in low cost minicomputer or microprocessor systems. the method described in this paper uses a special-purpose digital computing device to perform the geometric transformation in the process of transferring the image data in line scanning mode between the peripheral device and the computer. this method effectively reduces computing time and can be implemented in minicomputer systems. In this paper, an approach of automatic organization of the scanning-line image data into submatrices, and reconversion to recording-line format is also introduced.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

AFRIGRAPH: computer graphics in Africa

引用

computer graphics FORUM 2006年第4期25卷 697-698页

作者： Gain, J. E. Strasser, W. Univ Cape Town Collaborat Visual Comp Lab ZA-7925 Cape Town South Africa Univ Tubingen Wilhelm Schickard Inst Informat Graph Interakt Sy D-7400 Tubingen Germany

the article provides information on the Afrigraph organization in Africa. the purpose of Afrigraph is to help consolidate and promote the practice of relevant computer graphics in academia, arts and industry in Africa. Afrigraph has run a series of four international conferences in order to foster the computer graphics community in Africa and international cooperation. the organization held a graphics programming contst open to school pupils in Southern Africa as a new venture in 2006.

关键词： Associations, institutions, etc. International cooperation computer graphics Engineering graphics

来源：评论

学校读者我要写书评

暂无评论

BoCS: image retrieval using explicable methods 36

BoCS: Image retrieval using explicable methods

引用

36th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Silva, Endi D. C. Traina, Agma J. M. Univ Sao Paulo Sao Carlos SP Brazil

ISBN: (纸本)9798350338737;9798350338720

In recent years, image generation has been growing at a very fast pace, demanding specific systems for managing large image datasets. For example, we can mention the content-based image retrieval (CBIR) systems. Usually, they use a representation of feature vectors based on the images' visual content to store/retrieve them and to perform demanded queries. Currently, neural networks perform the task of generating image representations with great mastery. However, these networks usually create methods that are difficult to understand or to explain, which for some applications, such as medical decision-making systems, can be a significant disadvantage. thinking about the explainability aspect, in this work, we present a new technique based on the bag of visual words (BoVW) which, in addition to generating promising explainable methods, has long been the state of the art for generating image representations. the results showed that the presented method BoCS overcomes similar methods and still has the potential to be further explored.

关键词： image representation

来源：评论

学校读者我要写书评

暂无评论

Oriented image Foresting Transform Segmentation: Connectivity Constraints with Adjustable Width 29

Oriented Image Foresting Transform Segmentation: Connectivit...

引用

29th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Mansilla, Lucy A. C. Miranda, Paulo A. V. Univ Sao Paulo Dept Comp Sci BR-05508090 Sao Paulo SP Brazil

ISBN: (纸本)9781509035687

In this work, we extend a novel seed-based segmentation algorithm, which provides global optimum solutions according to a graph-cut measure, subject to high-level boundary constraints: the simultaneously handling of boundary polarity and connectivity constraints. the proposed method incorporates the connectivity constraint in the Oriented image Foresting Transform (OIFT), ensuring the generation of connected objects, but such that the connection between its internal seeds is guaranteed to have a user-controllable minimum width. In other frameworks, such as the min-cut/max-flow algorithm, the connectivity constraint is known to lead to NP-hard problems. In contrast, our method conserves the low complexity of the OIFT algorithm. In the experiments, we show improved results for the segmentation of thin and elongated objects, for the same amount of user interaction. Our dataset of natural images with true segmentation is publicly available to the community.

关键词： image segmentation connectivity constraints boundary polarity image foresting transform

来源：评论

学校读者我要写书评

暂无评论

Helical CT reconstruction from wide cone-beam angle data using ART 16

Helical CT reconstruction from wide cone-beam angle data usi...

引用

16th brazilian symposium on computer graphics and image processing

作者： Carvalho, BM Herman, GT CUNY Grad Ctr Doctoral Program Comp Sci New York NY 10036 USA

ISBN: (纸本)0769520324

We report on new results on the use of Algebraic Reconstruction Techniques (ART)for reconstructing from helical cone-beam computerized Tomography (CT) data. We investigate two variants of ART for this task: a standard one that considers a single ray in an iterative step and a block version which groups several cone-beam projections when calculating an iterative step. Both algorithms were implemented using modified Kaiser-Bessel window functions, also known as blobs, placed on the body-centered cubic (bcc) grid. the algorithms were used to reconstruct a modified 3D Shepp-Logan phantom from data collected for the PI-geometry for two different maximum cone-beam angles (+/-9.46degrees and +/-18.43degrees). Both scattering and quantum noise (for three different noise levels) were introduced to create noisy projections. the results presented here (for both noiseless and noisy data sets) point to the fact that, as opposed to filtered backprojection algorithms, the quality of the reconstructions produced by the ART methods does not suffer from the increase in the cone-beam angle.

关键词： Computed tomography image reconstruction Iterative algorithms Noise level Object detection Sensor arrays Subspace constraints X-ray detection X-ray detectors X-ray imaging

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：