检索结果-内蒙古大学图书馆

2018 3rd international conference on Education and Management Science(ICEMS 2018)

作者： Peng-bo BO Xiao-miao ZHANG Harbin Institute of Technology

Final Year Project（FYP） is an essential component in various programmes of college education. Topic selection for Final Year Project is one of the most important factors which have significant impacts on student training. In this paper, we discuss topic selection of Final Year Project in the discipline of computer science and computer software. We provide several typical topics in which an application software is designed and developed which make use of knowledges in image processing, computer graphics and data visualization. Software developing toolkits employed in these projects are discussed. The main points of these projects are explained in details and results are shown by pictures as well.

关键词： Final year project Student training College education computer graphics

来源：评论

学校读者我要写书评

暂无评论

HDR image Synthesis Based on Multi-exposure Color images

HDR Image Synthesis Based on Multi-exposure Color Images

引用

2011 3rd international Asia conference on Informatics in Control, Automation and Robotics (CAR 2011 LNEE 132)

作者： Hua Wang Jianzhong Cao Linao Tang Yao Tang Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences

In digital camera, it's difficult to exceed the dynamic range of 60～80d B because of the saturation current and background noise of CCD/CMOS image sensor in a single exposure image. In order to obtain more information and detail of a scene, we should extend its dynamic range, which was called HDR technology. Recent years, HDR imaging techniques have become the focus of much research because of their high theoretical and practical importance. By applying HDR techniques, the performance of different image processing and computer vision algorithms, information enhancement, and object and pattern recognition can also be improved. In this paper, a new tone reproduction algorithm is introduced, based on which may help to develop the hard-to-view or nonviewable features and details of color images. This method applies on multi-exposure images synthesis technique, where the red, green, and blue(RGB) color components of the pixels are separately handled. In the output, the corresponding(modified) color components are blended. As a result, a high quality HDR image is obtained, which contains almost the whole details and color information.

关键词： color image processing,high dynamic range(HDR) image,image enhancement,multi-exposure images synthesize

来源：评论

学校读者我要写书评

暂无评论

Optimizing RGB to Grayscale, Gaussian Blur and Sobel-Filter operations on FPGAs for reduced dynamic power consumption

Optimizing RGB to Grayscale, Gaussian Blur and Sobel-Filter ...

引用

Artificial Intelligence For Internet of Things (AIIoT), international conference on

作者： Nikhil Rout J Jean Jenifer Nesam School of Electronics Engineering (SENSE) Vellore Institute of Technology Chennai Campus Chennai India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

The conversion of pixels from their RGB to Grayscale formats is a crucial first step in numerous image Pre-processing, computer vision, and as highlighted here, edge detection modules. This paper presents an implementation of the Shift-Add Multiplication algorithm for efficient constant multiplications of the NTSC formula weights for RGB to Grayscale conversion on FPGAs. The proposed module is designed to be reconfigurable to both fixed-point and floating-point formats, providing flexibility in precision and resource utilization based on application requirements. Additionally, a Python script was developed to automate the generation of Verilog code for fractional constant multiplications, as proposed in this study. Pipelined modules for Gaussian Blur and the Sobel-Filter were also designed to enable the development of a complete real-time edge detection system on FPGAs. The findings reveal that Shift-Add algorithm based multiplier’s significantly reduce dynamic power consumption as compared to the use of the built-in DSP blocks on FPGA boards while performing constant multiplications for RGB to Grayscale conversion.

关键词： Power demand Codes image edge detection Heuristic algorithms Gray-scale Aerodynamics Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A scheme of long short-term memory (LSTM) -CNN features extraction and spatial relationship to anonymize image and video for Privacy-Preserving Human Activity Recognition of multiple sequences of data

A scheme of long short-term memory (LSTM) -CNN features extr...

引用

international Symposium on Artificial Intelligence and Signal processing (AISP)

作者： Kambala Vijaya Kumar Yalanati Ayyappa B Vinay Kumar Harikiran Jonnadula Yamini Tondepu Nusumu Sree Vidya Department of CSE P.V. P Siddhartha Institute of Technology-Vijayawada Andhra Pradesh India School of CSE VIT-AP University Amaravathi Andhra Pradesh India Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

Safeguarding security from stowed away pictures and recorded recordings is a significant social issue. To store information related picture or video data the arrangement of human movement can be recognized for examining the different issues of exercises. And yet guarantee that it doesn’t record the significant video or catch the activities of human it is abusing the security of human. This article presents a crucial way to deal with tackling such clashing undertakings: acknowledgment of human movement while utilizing just mysterious low-goal recordings (Example: lSx16). We are presenting the Deep learning, CNN, computer vision OpenCV worldview, the calculation making sense of the insignificant picture transformation and to make a few low-goals of profoundly goal informative recordings from video. Our ideas is concentrating on different kinds of sub-pixel changes that are streamlined for arranging exercises, which permits the study hall expert to utilize existing high-goal recordings by bringing a few LR preparing recordings adjusted for this issue. The commonsense result results are affirmed that the OpenCV in PC models can profit from movement acknowledgment from very human action recordings. In this paper we are seeing as the negligible of human exercises from the pictures or recordings taken from the different public where the high goal can be distinguished and getting the exceptionally low goal and protection can be stowed away from such pictures or recordings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curiosity-Driven Exploration Effectiveness on Various Environments 2019

Curiosity-Driven Exploration Effectiveness on Various Enviro...

引用

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

作者： Korawat Charoenpitaks Yachai Limpiyakorn Department of Computer Engineering Chulalongkorn University Bangkok Thailand

ISBN: (纸本)9781450376259

Hand Crafting Reward functions have never been scalable solutions for real world problems. The self-generated intrinsic rewards inspired by human curiosity may be one of scalable answers to solve sparse reward problem. The research thus investigated the effectiveness of some selected techniques based on the theory of curiosity-driven exploration. The Count-based, Prediction-based and other methods in total of six algorithms were experimented on various OpenAI gym environments. The results showed that the exploration algorithms have an impact on software agent in ability to find optimal solutions compared with the baseline in many cases. Still, there is no clear winner between the selected exploration methods and the best scalable exploration is not yet explored. The finding is that the added small intrinsic reward noise helps improve sample efficiency in the short run.

关键词： Curiosity Intrinsic Reward Exploration Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Formalin Detection in Fish Using Deep Neural Networks

Comparative Analysis of Formalin Detection in Fish Using Dee...

引用

international conference on Advancement in Electrical and Electronic Engineering (ICAEEE)

作者： Rashedul Islam Sabrin Islam Samiha Maisha Jeba Rakibul Hasan Dihan Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh

ISBN: (数字)9798350388282

ISBN: (纸本)9798350388299

For the people of Bangladesh, fish is a non-vegetarian and staple food. As Bangladesh is a riverine country, fish is available everywhere in our country. Fish rots easily. For this reason, the fish has to be preserved to fulfill people’s nutritional needs. To meet the needs of the people of Bangladesh, fish is collected from the rivers and sometimes imported for this vast population. While importing fish or taking it from one place of the country to another, unscrupulous traders mixed formalin to prevent the fish from rotting. Formalin is very harmful to the human body. It creates so many health problems like cancer, miscarriage, tumors, etc. So, it is essential to detect formalin fish and non-formalin fish. There is a need for a more dependable and automated method of formalin detection because current approaches rely on human senses and are prone to inaccuracy. Digital image processing has become a promising technology for fish formalin detection in recent years. In this paper, an intelligent application is proposed. This model can identify formalin and fresh fish based on the images of fish eyes. The capability of digital image processing to offer a quick and non-intrusive examination technique is one of the main advantages of formalin detection. Without damaging sample preparation, it can swiftly and accurately identify the presence of formalin by examining photographs of the fish. This is especially helpful in large-scale operations when it is impractical to inspect each fish manually. Digital image processing algorithms are more accurate and consistent because they are not influenced by human biases or subjective judgments like human senses are. The architecture we proposed is VGG-16, and we compare it with EfficientNet-B3. VGG-16, renowned for its simplicity and effectiveness in various computer vision tasks, achieved a notable accuracy of 94.44%.

关键词： Accuracy Pain Digital images Sociology Predictive models Fish Rivers

来源：评论

学校读者我要写书评

暂无评论

An Embedded Agricultural Products Quality Detecting System Based on image vision

An Embedded Agricultural Products Quality Detecting System B...

引用

2010 The 3rd international conference on Computational Intelligence and Industrial Application (PACIIA2010)

作者： Hongshe Dang,Jinguo Song,Qin Guo School of Electric and Information Engineering,Shaanxi University of Science and Technology,Xi'an 710021,China

Aiming at the problem that the structure of present agricultural products quality detection system is complicated and its high realization costs,through combining the embedded technology with machine vision technology,the embedded agricultural product quality detection system is realized at last based on ARM,accomplishing the function of agricultural products size,shape,and color and fault *** results show that this embedded system can get 94 percent of size and shape detecting accuracy and 83 percent or higher of color and default *** the system is low cost and would have a good prospect of application in agricultural product quality detecting and grading areas.

关键词： ARM embedded system quality detection

来源：评论

学校读者我要写书评

暂无评论

Early Stage Detection of Psoriasis Using Artificial Intelligence and image processing 3rd

Early Stage Detection of Psoriasis Using Artificial Intellig...

引用

3rd international conference on Soft Computing: Theories and Applications, SoCTA 2018

作者： Kalbande, D.R. Khopkar, Uday Sharma, Avinash Daftary, Neil Kokate, Yash Dmello, Royston Department of Computer Engineering Sardar Patel Institute of Technology Andheri Mumbai India Department of Dermatology Seth GS Medical College & KEM Hospital Parel Mumbai India Department of Computer Science & Engineering Maharishi Markandeshwar Engineering College AmbalaHaryana India

ISBN: (纸本)9789811507502

A large part of the Indian population comes below the poverty line. There are thousands of people living in poor sanitation areas. Owing to this, a majority of ailments prevail in such areas. People do not have access to good medical facilities and at times may not even have the awareness to visit a doctor at the correct time. This has been observed especially in the case of skin diseases where failure to get the correct diagnosis and treatment in time often results in dire consequences. With the growing surge of Artificial Intelligence (AI), it has been realized that AI can be helpful in the medical arena as well. Thus, an AI-based approach is proposed for the classification of a skin disease Psoriasis by making use of a multi-class machine learning classification algorithm. Psoriasis is a noncontagious, chronic skin condition that results in the formation of patches of thickened, scaling skin. This algorithm uses uploaded images from the users’ smartphone to give a probability estimate for Psoriasis. Over 60 medically validated images of Psoriasis, acquired from Department of Skin and V.D of Seth G.S. Medical College and KEM Hospital, Parel, Mumbai, were used as training data. It uses a Neural Network algorithm for training the symptoms. Using this training data, an accuracy of above 85% was obtained. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Self-supervised image Classification based on the Distances of Deep Feature Space 19

Self-supervised Image Classification based on the Distances ...

引用

Proceedings of the 3rd international conference on Video and image processing

作者： Zhuoxun He Ya Zhang Yanfeng Wang Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781450376822

Deep neural networks have demonstrated their effectiveness in computer vision, especially for image classification and detection. Mixup is recently proposed as a data augmentation scheme, which applies linear combination of two random training examples and corresponding targets. However, the linear assumption is inappropriate for training a non-linear model. In this paper, we propose a self-supervised method which requires the consistency of original and mixed images on feature space. Our work is motived by the semantic information is related to the relative position of features. To implement this idea effectively and efficiently, we perform two-stage of training procedure, i.e., running estimation of class centers of original data in feature space, and training deep neural networks with modified loss term of Mixup. Besides, the proposed approach is also compatible with other variants of Mixup. We validate our approach on two popular image classification datasets, CIFAR10 and CIFAR100 by a variety of advanced deep neural networks, and demonstrate consistent generalization improvements, sometimes significantly. We also conduct analytical experiments to evaluate the robustness of our method to hyperparameters.

关键词： Mixup Class center Self-supervision image classification

来源：评论

学校读者我要写书评

暂无评论

Representation of freshwater aquaculture fish behavior in low dissolved oxygen condition based on 3D computer vision

引用

MODERN PHYSICS LETTERS B 2018年第34-36期32卷

作者： Bao, Y. J. Ji, C. Y. Zhang, B. Gu, J. L. Changzhou Inst Technol Sch Elect & Photoelect Engn Changzhou 213032 Peoples R China Nanjing Agr Univ Coll Engn Nanjing 210031 Jiangsu Peoples R China

Dissolved oxygen (DO) plays an important role in industrialized freshwater aquaculture. Such deficiencies such as the high cost of water-quality monitoring system and the failure to accurately monitor or describe aquaculture water-quality existed in freshwater aquaculture water-quality monitoring system. Here, a kind of representation method applied to characterize industrialized aquaculture fish behavior in different degrees of DO deficiency is based on three-dimensional (3D) computer vision. 3D coordinate values of aquaculture fishes in water acquired from 3D computer vision Device by processing aquaculture fish image are applied to represent such parameters as the average activity and height of aquaculture fish in water. This method for representing different behaviors of industrialized freshwater aquaculture fish under the condition of anoxia is realized by using these parameters and combing with the experience of aquaculture. The results show that the representation of industrialized freshwater aquaculture fish based on 3D computer vision System can be applied to describe industrialized aquaculture fish behavior and effectively compensate for the shortfall spatial location of aquaculture fish unable to acquire from 2D monitoring system, which is helpful for the accurate and reasonable control of DO in aquaculture.

关键词： Fish behavior dissolved oxygen three-dimensional vision system

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：