检索结果-内蒙古大学图书馆

Proceedings of the 3rd international conference on Graphics and Signal processing

作者： Tanjina Piash Proma Md.Zakir Hossan M.Ashraful Amin Computer Science & Engineering Independent University Bangladesh

ISBN: (纸本)9781450371469

People of hazy or blurred vision or the elderly people finds it way too challenging just to identify the pills if they are out of the box or packet. And various pills of various shapes, size, texture, color comes with a diverse set of medicinal components. It creates confusion among pills of same color and shape to identify based on a specific texture. For visually impaired people, even if they configure the shape of the pill, the color information and the texts imprinted on the pill remains unknown to them. In this paper, the splitting processes of a dataset according to the number of colors and the texts imprinted on the pills, will be described. Initially the color information were extracted by segmenting pill region from pill image and then some statistical measurements i.e. Kurtosis and skewness, are calculated for probability distributions generated from the image histograms. Thus figuring out the how many colors the pill surface consists of. For the text recognition, the probable text region is detected for an error free text detection. For high quality image data, the reference images from NLM Rx image database has been utilized. The overall accuracy of the proposed system for number of color determination is 95.6% and text recognition accuracy is 81.32%.

关键词： Medical Imaging Pill image Color determination Kurtosis Skewness Text segmentation Text recognition

来源：评论

学校读者我要写书评

暂无评论

Digital Watermarking Algorithm for 2D Vector Graphics 2019

Digital Watermarking Algorithm for 2D Vector Graphics

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Yue Ding Jianrong Wang Xiang Ying School of computer software College of intelligence and computing Tianjin University Tianjin China School of Computer Science and Technology College of intelligence and computing Tianjin University Tianjin China

ISBN: (纸本)9781450376259

At present, digital watermark technology has been relatively mature in the security protection of images, video, audio and other fields, and has achieved many successful applications. In contrast, there are relatively few watermarking methods for vector graphics copyright protection. We propose a digital watermarking algorithm for the vector graphics drawn by the spline. Firstly, we grab the color values of vector graphics and construct a color matrix. Then DWT decomposition and Slant transformation are performed on the color matrix. Finally, the watermark image is embedded in the low frequency component of the color matrix. Experimental results show that not only the watermark information is successfully hidden to the vector graphics, but also the algorithm can effectively resist object modification attacks.

关键词： Spline Curve Digital Watermarking Copyright Protection

来源：评论

学校读者我要写书评

暂无评论

Detecting Protuberant Saliency from a Depth image 2019

Detecting Protuberant Saliency from a Depth Image

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Yuseok Ban Agency for Defense Development Republic of Korea

ISBN: (纸本)9781450376259

The visual attention of a human enables quick perception of noticeable regions in an image. The research on the models of visual attention has been actively studied for decades in the computer vision areas. For example, detecting visual saliency in a scene allows to estimate which details humans find interesting in advance to understand the scene. This also forms the important basis of a variety of latter tasks related to visual detection and tracking. By virtue of increasing diffusion of low-cost 3D sensors, many studies have been proposed to examine how to incorporate 3D information into visual attention models. Despite many advantages of depth data, relatively few studies on the visual attention of a depth image have delved into how to fully exploit the structural information of depth perception based on depth data itself. In this paper, Protuberant saliency is proposed to effectively detect the saliency in a depth image. The proposed approach explores the inherent protuberance information encoded in a depth structure. The fixation of a human eye in a depth scene is directly estimated by Protuberant saliency. It is robust to the isometric deformation and varying orientation of a depth region. The experimental results show that the rotation invariant and flexible architecture of Protuberant saliency produces the effectiveness against those challenging conditions.

关键词： Saliency Detection Depth image Protuberant

来源：评论

学校读者我要写书评

暂无评论

HRIPCB: a challenging dataset for PCB defects detection and classification

引用

JOURNAL OF ENGINEERING-JOE 2020年第13期2020卷 303-309页

作者： Huang, Weibo Wei, Peng Zhang, Manhua Liu, Hong Peking Univ Shenzhen Grad Sch Key Lab Machine Percept Shenzhen Peoples R China Shenzhen Skyworth RGB Elect Co Ltd Shenzhen Peoples R China

To cope with the difficulties in inspection and classification of defects in printed circuit board (PCB), many methods have been proposed in previous work. However, few of them publish their datasets before, which hinders the introduction and comparison of new methods. In this study, HRIPCB, a synthesised PCB dataset that contains 1386 images with 6 kinds of defects is proposed for the use of detection, classification and registration tasks. Besides, a reference-based method is adopted to inspect and an end-to-end convolutional neural network is trained to classify the defects, which are collectively referred to as the RBCNN approach. Unlike conventional approaches that require pixel-by-pixel processing, the RBCNN method proposed in this study firstly locates the defects and then classifies them by deep neural networks, which shows superior performance on the dataset.

关键词： image registration computer vision image recognition inspection object detection neural nets printed circuits RBCNN method deep neural networks HRIPCB challenging dataset PCB defects detection inspection printed circuit board synthesised PCB dataset 6 kinds classification registration tasks reference-based method end-to-end convolutional neural network RBCNN approach pixel-by-pixel processing

来源：评论

学校读者我要写书评

暂无评论

Intelligent System to Classify Peanuts Varieties Using K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM) 3rd

Intelligent System to Classify Peanuts Varieties Using K-Nea...

引用

3rd international conference on Advanced Informatics for Computing Research (ICAICR)

作者： Narendra, V. G. Hegde, K. Govardhan Manipal Acad Higher Educ Manipal Inst Technol Comp Sci & Engn Manipal 576104 India

ISBN: (纸本)9789811501081;9789811501074

In the world, India is the second biggest producer of peanuts or groundnuts, and it is also our country's major oilseed crop. In India, the existing peanuts crop varieties are GAUG-1, Kuber, Amber, PG-1, BG-1, T-64, GAUG-10, BG-2, Chandra, Kadri-2, Chitra, Kadri-3, Prakash, T-28, Kaushal, etc. Presently, peanuts are having only 75-80% of India's average market value. Because, the peanuts kernel quality assessment, as well as identifying varieties, are done manually by skilled labors, which leads costly. In this research, an affordable method is proposed to assess the peanuts kernel quality and identifying the different varieties quickly with undamaged, repeatability with low cost, and accurately with high distinguishing rate. Also, to meet the quality of peanuts kernel as per the international market standards and to increase the income of the former. The proposed system relies on computer vision and machine learning. The obtained overall accuracies were K-nearest neighbors (93.33%) and Support vector machine (93.82%). These percentages are discriminating peanuts variety as the best predictive model.

关键词： Peanuts K-Nearest Neighbors Support vector machine computer vision image processing

来源：评论

学校读者我要写书评

暂无评论

GAN-based End-to-End Unsupervised image Registration for RGB-Infrared image

GAN-based End-to-End Unsupervised Image Registration for RGB...

引用

international conference on Intelligent Autonomous Systems (ICoIAS)

作者： Kanti Kumari Ganapathy Krishnamurthi Indian Institute of Technology Madras Chennai India

ISBN: (数字)9781728160788

ISBN: (纸本)9781728160795

image registration is a pre-processing step used in various computer vision applications. This paper presents an unsupervised image registration for a given pair of RGB and infrared images, with the RGB image used as the reference for infrared. This method exploits the GAN architecture with a spatial transformer module, to synthesize the transformed image using an unsupervised loss criterion. This loss used for error backpropagation taken as a linear combination of adversarial loss; Mean Squared Error (MSE) loss between the input RGB image and image synthesized by the generator; KL divergence loss between the IR image and the synthesized image; and another MSE loss estimated using features maps extracted from pretrained VGG-16. The adversarial loss forces the generator to output an IR like image, with the input IR image and the generated IR image labelled as real and fake respectively. The other three losses are backpropagated through the generator network to learn the transformation as well as to preserve the structure and resolution of the generated image. This unsupervised learning process is stopped after a specified number of iterations based on a validation set. A supervised method has also been developed for comparison with the presented method. The SSIM and PSNR values estimated between predicted registered image and its ground truth has been used as evaluation criteria. The unsupervised method has scored 0.8351±0.06 and 35.2723±0.68 for SSIM and PSNR respectively, while supervised scored as 0.7620±0.08 and 15.8978±2.21.

关键词： Generators image registration Feature extraction Training Computational modeling Gallium nitride computer architecture

来源：评论

学校读者我要写书评

暂无评论

Research on vision-based Autonomous Landing of Unmanned Aerial Vehicle

Research on Vision-based Autonomous Landing of Unmanned Aeri...

引用

IEEE international conference on Automation, Electronics and Electrical Engineering (AUTEEE)

作者： Run Ye Chao Tao Bin Yan Ting Yang School of Automation Engineering University of Electronic Science and Technology of China Chengdu P. R. China

ISBN: (数字)9781728198279

ISBN: (纸本)9781728181585

In order to ensure that the Unmanned Aerial Vehicle (UAV) achieves a safe and accurate landing under special conditions such as GPS signal interference, an autonomous landing method based on computer vision is proposed. Firstly, the projection model of the airborne camera is established, and the camera's internal parameter matrix is obtained by camera calibration. Then, the “H” landing target pattern is designed to reduce the complexity of image processing, and the white backing disc is added to make the background easier to the segment. Then the pose estimation model is established and combined with the coordinate information of the feature points to complete the pose calculation. Finally, the actual flight data of the UAV is compared with the pose estimation data, and the maximum error of the position and attitude estimation values is 0. 52m and 6.22°, which can basically meet the landing requirements of the UAV, and the feasibility of the method is proved.

关键词： Feature extraction Cameras Unmanned aerial vehicles Shape Visualization Radio navigation Global navigation satellite system

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2020年 1022 AISC卷 v-vi页

作者： Chaudhuri, Bidyut B. Nakagawa, Masaki Khanna, Pritee Kumar, Sanjeev Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Techno India University Kolkata India Department of Advanced Information Technology and Computer Sciences Tokyo Institute of Agriculture and Technology Koganei Tokyo Japan Department of Computer Science Indian Institute of Information Technology Design and Manufacturing Jabalpur Jabalpur Madhya Pradesh India Department of Mathematics Indian Institute of Technology Roorkee Roorkee Uttarakhand India

来源：评论

学校读者我要写书评

暂无评论

Impact of Font on computer Recognition of License Plates on Automobiles 2019

Impact of Font on Computer Recognition of License Plates on ...

引用

Proceedings of the 3rd international conference on vision, image and Signal processing

作者： Rabiah Al-qudah Ching Y. Suen Computer Science Concordia University Montreal QC Canada Computer Science Concordia University Montreal QC Canada

ISBN: (纸本)9781450376259

The chosen font type in the license plate (LP) plays a vital role in the recognition phase in computer-based operations. Some fonts are challenging for humans to read; however, other fonts are challenging for computer systems to recognize. Here, we present two sets of results for font evaluation: font anatomy results, and recognition results for commercial products. For anatomy results, two typical LP fonts are considered: Mandatory, and Driver Gothic. Moreover, we evaluate the effect of these fonts in context for two datasets using two commercial products: OpenALPR and Plate Recognizer. The font anatomy results revealed some important confusion cases and some quality features of both fonts. The obtained results show that the Driver font has less severe confusion cases than the Mandatory font.

关键词： Recognition Font analysis License plate Error analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus images Using Deep Learning and image Augmentation 1

引用

3rd IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 international Cross-Domain conference for Machine Learning and Knowledge Extraction (CD-MAKE)

作者： Rahim, Sarni Suhaila Palade, Vasile Almakky, Ibrahim Holzinger, Andreas Coventry Univ Fac Engn Environm & Comp Priory St Coventry CV1 5FB W Midlands England Univ Teknikal Malaysia Melaka Fac Informat & Commun Technol Durian Tunggal 76100 Melaka Malaysia Med Univ Graz Inst Med Informat Stat & Documentat Graz Austria

ISBN: (数字)9783030297268

ISBN: (纸本)9783030297268;9783030297251

Diabetic retinopathy is a significant complication of diabetes, produced by high blood sugar level, which causes damage to the retina. Effective diabetic retinopathy screening is required because diabetic retinopathy does not show any symptoms in the initial stages, and can cause blindness if it is not diagnosed and treated promptly. This paper presents a novel diabetic retinopathy automatic detection in retinal images by implementing efficient image processing and deep learning techniques. Besides diabetic retinopathy detection, the developed system integrates a novel detection of maculopathy into one detection system. Maculopathy is the damage to the macula, the eye part that is responsible for central vision. Therefore, the combined detection of diabetic retinopathy and maculopathy is essential for an effective screening of diabetic retinopathy. The paper investigates the capability of image pre-processing techniques based on data augmentation as well as deep learning for diabetic retinopathy and maculopathy detection. computer-assisted clinical decisionmaking is inevitably transforming the diabetic retinopathy detection and management today, which is crucial for clinicians and patients alike. Therefore, a high degree of accuracy, with which computer algorithms can detect the diabetic retinopathy and maculopathy, is absolutely necessary.

关键词： Diabetic Retinopathy Maculopathy Eye screening Colour fundus images image processing Data augmentation Deep learning

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：