检索结果-内蒙古大学图书馆

International symposium on intelligence Information processing and Trusted Computing

作者： Zhang, Ruihong Yu, Zhichao Computer Department Huanggang Normal University Hubei 438000 China

ISBN: (纸本)9780769541969

The purpose of digital image scrambling technology is to put a meaningful image into a disordered one to enhance the resistance ability against illegal attacks so as to improve security. This paper proposes an image scrambling transformation method based on the idea of inverse transformation in finite integer domain. It includes gray transformation and position transformation. At the same time, it analyzes the security and the scrambling cycle of the proposed method. Experimental results show that the proposed method has a good scrambling effect and a long scrambling cycle;moreover, it is easy to realize. © 2010 ieee.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Object Detection in Satellite images Based on Active Learning Utilizing Visual Explanation 11

Object Detection in Satellite Images Based on Active Learnin...

引用

11th International symposium on image and signal processing and Analysis (ISPA)

作者： Uehara, Kazuki Nosato, Hirokazu Murakawa, Masahiro Sakanashi, Hidenori Natl Inst Adv Ind Sci & Technol Artificial Intelligence Res Ctr AIRC Tsukuba Ibaraki Japan

ISBN: (纸本)9781728131405

Convolutional neural networks (CNNs) have attracted much attention for object detection in satellite images. However, creating an annotated dataset requires a lot of time and user workload due to which the remote sensing domain has insufficient labeled datasets for training CNNs. We exploit an active learning (AL) framework for training CNNs with a small labeled dataset. AL obtains the training dataset by asking a human user to label the samples. For efficient AL, an intelligent query strategy is essential because the performance of a CNN depends on the collected dataset. Thus, in this study, we propose a query strategy to train CNNs effectively;this is done by choosing effective samples for training both the classifier and feature extractor. The strategy selects samples according to the gap between the classifier's prediction and visual explanation, which is the class discriminative part of an image derived from the extracted feature maps. Experimental result shows that a CNN trained with samples queried by our strategy had a 95% reduction in training samples requirement while maintaining 94% detection performance compared to a CNN trained with a complete dataset. Furthermore, the proposed strategy also reduced the required training samples by 30% compared to the conventional strategy to yield the same performance.

关键词： Active learning Visual explanation Annotation Object detection Satellite images

来源：评论

学校读者我要写书评

暂无评论

Developing a Multimodal System for Bee Object Detection and Health Assessment

引用

ieee ACCESS 2024年 12卷 158703-158713页

作者： Liang, Andrew Harker Sch San Jose CA 95124 USA

Honey bees pollinate about one-third of the world's food supply, but bee colonies have alarmingly declined by nearly 40% over the past decade due to several factors, including exposure to pesticides. Traditional methods for monitoring beehives, such as human inspections, are subjective, disruptive, and time-consuming. To address these limitations, artificial intelligence has been used to assess beehive health. However, previous studies have lacked an end-to-end solution and primarily relied on data from a single source, either bee images or sounds. This study introduces a unified system for bee object detection, which selectively processes data containing bees for health evaluation. Additionally, it utilizes a combination of visual and audio signals to analyze bee behaviors. A Cross-Attention-based Multimodal Neural Network (CAMNN) was developed to adaptively focus on key features from each type of signal for more accurate bee health assessment. The CAMNN achieved an overall accuracy of 93%, surpassing eight existing single-signal Convolutional Neural Networks and Recurrent Neural Networks. It outperformed the best image-based model by 33% and the top audio-based model by 15%. Furthermore, it improved prediction robustness, attaining an F1-score above 90% across all four evaluated health conditions. The study also showed that audio signals were more reliable than images for assessing bee health. By seamlessly integrating CAMNN with both image and sound data in a holistic bee health monitoring system, this approach provided a more efficient and non-invasive solution for the early detection of bee diseases and the preservation of bee colonies.

关键词： Feature extraction Monitoring Visualization computational modeling Annotations Accuracy Temperature sensors Deep learning Computer vision Bees algorithm artificial intelligence computer vision signal processing electronic beehive monitoring multimodal model cross-attention-based mechanism bee health assessment

来源：评论

学校读者我要写书评

暂无评论

image Regularization with Morphological Gradient Priors Using Optimal Structuring Elements for Each Pixel

Image Regularization with Morphological Gradient Priors Usin...

引用

International symposium on Intelligent signal processing and Communication Systems (lSPACS)

作者： Oohara, Shoya Oka, Hirotaka Muneyasu, Mitsuji Yoshida, Soh Nakashizuka, Makoto Kansai Univ Fac Engn Sci 3-3-35 Yamate Cho Suita Osaka 5648680 Japan Chiba Inst Technol Fac Engn 2-17-1 Tsudanuma Narashino Chiba 2750016 Japan

ISBN: (纸本)9781728130385

As an image prior for image restoration, the use of the sum of the morphological gradient for an image has been proposed. In this paper, we propose a method of optimizing the structuring element (SE) for each pixel, in particular, by greatly reducing the computational burden for optimization by adopting a new evaluation method for the SE in simulated annealing. By optimizing the SE for each pixel, edges of the image can be faithfully evaluated, and the improvement of restoration accuracy can be expected. An experimental result shows the effectiveness of the proposed method.

关键词： morphology morphological gradient total variation regularization image restoration simulated annealing

来源：评论

学校读者我要写书评

暂无评论

RGB image-Based Hand Pose Estimation: A Survey on Deep Learning Perspective 20

RGB Image-Based Hand Pose Estimation: A Survey on Deep Learn...

引用

20th CSI International symposium on Artificial intelligence and signal processing, AISP 2024

作者： Farjadi, Seyed Amirhossein Akbarzadeh-T, M.-R. Ghiasi-Shirazi, Kamaledin Ferdowsi University of Mashhad Center of Excellence on Soft Computing and Intelligent Information Processing Department of Computer Engineering Mashhad Iran Ferdowsi University of Mashhad Department of Computer Engineering Mashhad Iran

ISBN: (纸本)9798350383942

The pervasive integration of modern artificial intelligence into daily life necessitates robust human-computer interaction, underscored by advancements in computer technology. As the primary human tool, hand position, and orientation are vital for applications like virtual reality, with hand pose estimation playing a pivotal role. Despite the challenges inherent in RGB image-based estimation, the coalescence of extensive datasets, neural networks, and heightened computational capabilities has catalyzed the utilization of deep learning in visual tasks, particularly advancing hand pose estimation. This review exclusively centers on methodologies of RGB image-based approaches within the realm of hand pose estimation. The paper explores recent advancements in this category, providing a comprehensive analysis of outcomes and charting future directions. Organized around discussions on challenges, advancements, and future directions, this review aims to contribute to the ongoing discourse in the dynamic RGB image-based hand pose estimation field. By addressing unique challenges specific to this method, the paper offers insights that contribute to developing precise and robust hand pose estimation systems, impacting the broader landscape of computer vision and human-machine interaction. © 2024 ieee.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

An Interactive Genetic Algorithm-based image Sharpening System Considering User's Liking

An Interactive Genetic Algorithm-based Image Sharpening Syst...

引用

ieee symposium on computational intelligence for Engineering Solutions (CIES)

作者： Ueda, Yoshiaki Kuramoto, Yohei Kubota, Ryosuke Suetake, Noriaki Uchino, Eiji Ube Natl Coll Technol Adv Course Prod Syst Engn 2-14-1 Tokiwadai Ube Yamaguchi 7558555 Japan Yamaguchi Univ Grad Sch Sci & Engn Yamaguchi 7538512 Japan Ube Natl Coll Technol Dept Intelligent Syst Engn Ube Yamaguchi 7558555 Japan

ISBN: (纸本)9781467358514

Nowadays, digital images can be easily obtained, recorded and processed in accordance with the widespread use of digital cameras and personal computers. There is an image enhancement as one of most general image processing techniques. In the image enhancement, unsharp masking (UM) has been used widely because its algorithm is very simple and can produce good results. However, over-enhancement occurs in edge parts of the image. Additionally UM also is easy to generate artifacts such as jaggy and halo. To cope with these problems, the authors proposed the selective UM method based on the edge-preserved smoothing filter. However, the image quality obtained by our method depends on values of the enhancement parameters, and their optimal values vary according to user's liking. In this paper, we propose an image enhancement system considering the user's liking by using an interactive genetic algorithm (IGA). In the proposed system, the IGA optimizes the parameters of the image enhancement. Further, a new genetic operation is introduced in order to achieve the effective search in the IGA of the proposed system. Through the experiments using some images, the effectiveness of the proposed system is verified.

关键词： genetic algorithms image enhancement

来源：评论

学校读者我要写书评

暂无评论

A feature extraction method in face image for personal identification

A feature extraction method in face image for personal ident...

引用

ieee International symposium on computational intelligence in Robotics and Automation

作者： Takimoto, H Mitsukura, Y Fukumi, M Akamatsu, N Khosla, R Univ Tokushima Grad Sch Engn Tokushima 7708506 Japan

ISBN: (纸本)0780378660

Recently in the world, many researches of personal identification method using biometrics are widely done. Especially, personal identification using the face is used because of needless for physical contact. In this paper, we propose the new method to identify the personal using the SPCA and the NN. The SPCA has been proposed in order for the PCA to achieve high-speed processing. Moreover, the personal identification system needs to have not only ability to recognize registrant correctly but also ability to reject un-registrant certainly. Therefore, we perform simulation using un-registrant. Furthermore, we analyzed and examined about the individual feature in a face by using the GA and the SPCA. Then, in order to show the effectiveness of the proposed method, we show computer simulations by using the real image. From these results, we show the effectiveness.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Particle filter based on color feature with contour information adaptively integrated for object tracking

Particle filter based on color feature with contour informat...

引用

2011 4th International symposium on computational intelligence and Design, ISCID 2011

作者： Pu, Bing Zhou, Fugen Bai, Xiangzhi Beijing University of Aeronautics and Astronautics Image Processing Center Beijing 100191 China

ISBN: (纸本)9780769545004

particle filter is a probabilistic multi-hypothesis algorithm under the Bayesian framework. In order to establish a robust observing model, in this paper, a novel method which uses a more effective color feature with contour information integrated adaptively is proposed. Experimental results verified that, our approach was efficient. © 2011 ieee.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Robust line extraction based on repeated segment directions on image contours

Robust line extraction based on repeated segment directions ...

引用

ieee symposium on computational intelligence for Security and Defense Applications, CISDA 2009

作者： Montero, Andres Solis Nayak, Amiya Stojmenovic, Milos Zaguia, Nejib School of Information Technology and Engineering University of Ottawa Canada

ISBN: (纸本)9781424437641

This paper describes a new line segment detection and extraction algorithm for computer vision, image segmentation, and shape recognition applications. This is an important pre processing step in detecting, recognizing and classifying military hardware in images. This algorithm uses a compilation of different image processing steps such as normalization, Gaussian smooth, thresholding, and Laplace edge detection to extract edge contours from colour input images. Contours of each connected component are divided into short segments, which are classified by their orientation into nine discrete categories. Straight lines are recognized as the minimal number of such consecutive short segments with the same direction. This solution gives us a surprisingly more accurate, faster and simpler answer with fewer parameters than the widely used Hough Transform algorithm for detecting lines segments among any orientation and location inside images. Its easy implementation, simplicity, speed, the ability to divide an edge into straight line segments using the actual morphology of objects, inclusion of endpoint information, and the use of the OpenCV library are key features and advantages of this solution procedure. The algorithm was tested on several simple shape images as well as real pictures giving more accuracy than the actual procedures based in Hough Transform. This line detection algorithm is robust to image transformations such as rotation, scaling and translation, and to the selection of parameter values. © 2009 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Motion Control in image processing Applications 24

Orthogonal Motion Control in Image Processing Applications

引用

24th ieee International symposium on computational intelligence and Informatics, CINTI 2024

作者： Kovács, Bence László, Sajó-Bohus Beszédes, Bertalan Obuda University Alba Regia Faculty Székesfehérvár Hungary

ISBN: (纸本)9798350353433

The aim of my project is to offer an automation solution for examining solid-state passive detectors frequently used in particle physics. Since the detector surface often exceeds the field of view of microscopes, the implementation of a two-dimensional mobile platform is necessary. Additionally, processing the captured images provides information on the incident particle energy, direction and mass. Automation accelerates the examination process and reduces the human factor inherent in the analysis. © 2024 ieee.

关键词： examination acceleration human factor elimination image processing movable stage solid-state nuclear detectors

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：