检索结果-内蒙古大学图书馆

3rd International conference on Signal processing and Communication (ICPSC)

作者： Malini, T. Narmatha, M. Nandhini, M. Megha, T. D. Kumar, Nandha A. Sri Krishna Coll Engn & Technol Dept Elect & Elect Engn Coimbatore Tamil Nadu India

ISBN: (纸本)9781665428644

Use of the best quality Cereals and pulses are very important for the satisfactory production of a good crop, food processing and also essential for the exporting markets. Based on the purity and quality of cereals and pulses, they are graded. In this project, we use LabVIEW for digital image processing techniques for testing the shape and size of various cereals and pulses. Also, the presence of dust and stone particles is identified. According to the level of quality, the Cereals and pulses are classified into three categories which are shown in three indicators (Green-1st grade, yellow-2nd grade, red-3rd grade). This will be helpful to increase the speed, accuracy and decrease the time of testing. The wetness of cereals and pulses is determined for long time storage. For this moisture level is given to LabVIEW with the help of Arduino as a DAQ. The moisture alert buzzer is triggered by LabVIEW.

关键词： Quality image processing LabVIEW IMAQ Classification Moisture

来源：评论

学校读者我要写书评

暂无评论

Sandformer: CNN and Transformer under Gated Fusion for Sand Dust image Restoration

Sandformer: CNN and Transformer under Gated Fusion for Sand ...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jun Shi Bingcai Wei Gang Zhou Liye Zhang School of Information Science and Engineering Xinjiang University College of Computer Science and Technology Shandong University of Technology

Although Convolutional Neural Networks (CNN) have made good progress in image restoration, the intrinsic equivalence and locality of convolutions still constrain further improvements in image quality. Recent vision transformer and selfattention have achieved promising results on various computer vision tasks. However, directly utilizing Transformer for image restoration is a challenging task. In this paper, we introduce an effective hybrid architecture for sand image restoration tasks, which leverages local features from CNN and long-range dependencies captured by transformer to improve the results further. We propose an efficient hybrid structure for sand dust image restoration to solve the feature inconsistency issue between Transformer and CNN. The framework complements each representation by modulating features from the CNN-based and Transformer-based branches rather than simply adding or concatenating features. Experiments demonstrate that SandFormer achieves significant performance improvements in synthetic and real dust scenes compared to previous sand image restoration methods.

关键词： image quality Logic gates Signal processing Transformers visual effects image restoration Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Matting Anything

Matting Anything

引用

ieee Computer Society conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Jiachen Li Jitesh Jain Humphrey Shi SHI Labs @ Georgia Tech & Oregon & UIUC Picsart AI Research (PAIR)

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In this paper, we propose the Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance. MAM offers several significant advantages over previous specialized image matting networks: (i) MAM is capable of dealing with various types of image matting, including semantic, instance, and referring image matting with only a single model; (ii) MAM leverages the feature maps from the Segment Anything Model (SAM) [22] and adopts a lightweight Mask-to-Matte (M2M) module to predict the alpha matte through iterative refinement, which has only 2.7 million trainable parameters. (iii) By incorporating SAM, MAM simplifies the user intervention required for the interactive use of image matting from the trimap to the box, point, or text prompt. We evaluate the performance of MAM on various image matting benchmarks, and the experimental results demonstrate that MAM achieves comparable performance to the state-of-the-art specialized image matting models under different metrics on each benchmark. Overall, MAM shows superior generalization ability and can effectively handle various image matting tasks with fewer parameters, making it a practical solution for unified image matting. Our code and models are open-sourced at https://***/SHI-Labs/Matting-Anything.

关键词： Measurement Machine-to-machine communications image segmentation visualization Semantics Benchmark testing Predictive models

来源：评论

学校读者我要写书评

暂无评论

U-SAM: Upgrade Segment Anything Model With Semantic-Aware and Memory-Efficient

U-SAM: Upgrade Segment Anything Model With Semantic-Aware an...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xiaofeng Jin Jie Hu Jianghang Lin Shengchuan Zhang Liujuan Cao Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University P.R. China Learning and Vision Lab National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Segment Anything Model (SAM) has achieved remarkable success in the field of class-agnostic image segmentation by utilizing points or boxes as prompts. However, we identify two significant limitations when compared to traditional image segmentation models: (1) Trained in a category-agnostic interactive segmentation manner, SAM lacks the ability to discern object granularity and semantics, rendering it ineffective for traditional instance, semantic, and panoptic segmentation tasks. (2) SAM’s inefficient use of instance-independent visual features and tokens necessitates maintaining unique features and tokens for each instance, leading to excessive GPU memory consumption and diminished segmentation efficiency. To address these issues, we propose the Universal Segment Anything Model (U-SAM), a semantic-aware and memory-efficient segmentation model designed to perform both promptable and traditional segmentation tasks within a compact and unified framework. Specifically, U-SAM enhances SAM by integrating the Multi-Scale Semantic-Aware image Encoder (S2IE), thus providing multi-scale semantic features for achieving traditional image segmentation tasks. Additionally, U-SAM is equipped with a Twin Token Mask Decoder (T2MD) which reduces GPU memory overhead by substituting replicated visual features with replicated tokens. Extensive experiments across interactive, instance, semantic, and panoptic segmentation demonstrate U-SAM’s promising results. Notably, U-SAM is 9× smaller and 10× faster than SAM, showing strong performance in zero-shot segmentation. Moreover, U-SAM surpasses the SOTA object-prompter-based model, RSPrompter, by achieving a 6.2% increase in PQ, operating 14× faster, and cutting training memory usage by 61%.

关键词： Training image segmentation visualization Semantics Graphics processing units Signal processing Rendering (computer graphics) Decoding Object recognition Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Recognition Algorithm of Case images Based on Convolutional Neural Network

Research on Automatic Recognition Algorithm of Case Images B...

引用

Data Science and Computer Application (ICDSCA), ieee International conference on

作者： Yue Li Kunying Li Qin Li China National Petroleum Corporation Beijing China Petro China Reseach Institute of Petroleum Exploration and Development Beijing China

ISBN: (数字)9798350368239

ISBN: (纸本)9798350368246

This paper proposes a novel multi-modal fusion framework for automatic classification and key information extraction of legal case documents and scene photos. Firstly, the powerful image feature extraction ability of Convolutional Neural Network (CNN) was used to extract the visual features from the case pictures. Subsequently, Transformer models are introduced to process case text information to capture long-distance dependencies and contextual relationships. In order to integrate image and text information and further improve the recognition accuracy, we use XGBoost algorithm to build a classifier based on the output features of CNN and Transformer. With its high efficiency and powerful learning ability, it can effectively deal with high-dimensional feature space. The method accurately classifies the case images and achieves superior performance in the task of automatic classification of case images, which provides a new technical path for judicial image processing.

关键词： Deep learning visualization image recognition Accuracy Law Feature extraction Transformers Classification algorithms Convolutional neural networks Context modeling

来源：评论

学校读者我要写书评

暂无评论

Intelligent Grimm - Open-ended visual Storytelling via Latent Diffusion Models

Intelligent Grimm - Open-ended Visual Storytelling via Laten...

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chang Liu Haoning Wu Yujie Zhong Xiaoyun Zhang Yanfeng Wang Weidi Xie Coop. Medianet Innovation Center Shanghai Jiao Tong University China Shanghai AI Laboratory China Meituan Inc. China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently. In this work, we focus on a novel, yet challenging task of generating a co-herent image sequence based on a given storyline, denoted as open-ended visual storytelling. We make the following three contributions: (i) to fulfill the task of visual sto-rytelling, we propose a learning-based auto-regressive im-age generation model, termed as Story Gen, with a novel vision-language context module, that enables to generate the current frame by conditioning on the corresponding text prompt and preceding image-caption pairs; (ii) to ad-dress the data shortage of visual storytelling, we collect paired image-text sequences by sourcing from online videos and open-source E-books, establishing processing pipeline for constructing a large-scale dataset with diverse characters, storylines, and artistic styles, named StorySalon; (iii) Quantitative experiments and human evaluations have vali-dated the superiority of our StoryGen, where we show it can generalize to unseen characters without any optimization, and generate image sequences with coherent content and consistent character. Code, dataset, and models are avail-able at https://***/StoryGen_Webpage/. “Mirror mirror on the wall, who's the fairest of them all?” -Grimms' Fairy Tales

关键词： visualization Electronic publishing Computational modeling Pipelines Text to image image sequences Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for image Captioning: Opportunities, Challenges and Future Potential

引用

ieee Access 2024年 1-1页

作者： Jamil, Azhar Saif-Ur-Rehman Mahmood, Khalid Villar, Monica Gracia Prola, Thomas Diez, Isabel De La Torre Samad, Md Abdus Ashraf, Imran Department of Computer Science Barani Institute of Information Technology PMAS-Arid Agriculture University Rawalpindi Pakistan Department of Computer Science University Institute of Information Technology PMAS-Arid Agriculture University Rawalpindi Pakistan Institute of Computing and Information Technology Gomal University D.I.Khan Pakistan Universidad Europea del Atlántico. Isabel Torres 21 Santander Spain Department of Signal Theory Communications and Telematics Engineering Unviersity of Valladolid Paseo de Belén 15 Valladolid Spain Department of Information and Communication Engineering Yeungnam University Gyeongsan Republic of Korea

Generative intelligence relies heavily on the integration of vision and language. Much of the research has focused on image captioning, which involves describing images with meaningful sentences. Typically, when generating sentences that describe the visual content, a language model and a vision encoder are commonly employed. Because of the incorporation of object areas, properties, multi-modal connections, attentive techniques, and early fusion approaches like bidirectional encoder representations from transformers (BERT), these components have experienced substantial advancements over the years. This research offers a reference to the body of literature, identifies emerging trends in an area that blends computer vision as well as natural language processing in order to maximize their complementary effects, and identifies the most significant technological improvements in architectures employed for image captioning. It also discusses various problem variants and open challenges. This comparison allows for an objective assessment of different techniques, architectures, and training strategies by identifying the most significant technical innovations, and offers valuable insights into the current landscape of image captioning research. Authors

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cognitive Architecture Based Spectrum Sharing between 4G LTE-Advanced Network and TV Band

Cognitive Architecture Based Spectrum Sharing between 4G LTE...

引用

International conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Hashim Elshafie Naoufel Kraiem Rashid A. Saeed K Saleem A Shahid Khan Mosab Hamdan College of Computer Science King Khalid University Al Farah Abha Saudi Arabia College of Computers and Information Technology(CIT) Taif University Taif Saudi Arabia Center of Excellence in Information Assurance (CoEIA) King Saud University Riyadh Saudi Arabia Faculty of Computer Science and IT Universiti Malaysia Sarawak Kota Samarahan Sarawak Malaysia Walton Institute for Information and Communication Systems Science South East Technological University Waterford Ireland

ISBN: (数字)9798350351484

ISBN: (纸本)9798350351491

There is now a barrier in place because to the exponential increase in demand for faster wireless communications to meet the needs of more applications. There are almost no remaining frequency bands to allot for new systems since the spectral resources are running low. Based on a geographic TV database, this article presents the prospective approach sharing concerns between LTE-Advanced and TV band. The enabling technology will work with LTE-Advanced devices to address the TV band’s under used

关键词： Wireless communication TV Databases image processing White spaces Long Term Evolution

来源：评论

学校读者我要写书评

暂无评论

Exploiting Self-Supervised Constraints in image Super-Resolution

Exploiting Self-Supervised Constraints in image Super-Resolu...

引用

ieee International conference on Multimedia and Expo (ICME)

作者： Gang Wu Junjun Jiang Kui Jiang Xianming Liu Faculty of Computing Harbin Institute of Technology Harbin China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR. SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability. The proposed SSC-SR framework works as a plug-and-play paradigm and can be easily applied to existing SR models. Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR. In addition, extensive ablation studies corroborate the effectiveness of each component in our SSC-SR framework. Codes are available at https://***/Aitical/SSCSR.

关键词： Training visualization Uncertainty Codes Superresolution Self-supervised learning Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Design of Noise Robust Open-Set Radio Frequency Fingerprint Identification Method

Design of Noise Robust Open-Set Radio Frequency Fingerprint ...

引用

ieee conference on Computer communications Workshops, INFOCOM Wksps

作者： Min Wang Linning Peng Lingnan Xie Junqing Zhang Ming Liu Hua Fu School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China Department of Electrical Engineering and Electronics University of Liverpool Liverpool United Kingdom Beijing Key Lab of Transportation Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

Radio frequency fingerprint (RFF) identification (RFFI) is a promising technique for device authentication at the physical layer of the communication stacks. However, practical challenges, particularly in low signal-to-noise ratio (SNR) scenar-ios, and the lack of comprehensive studies on open-set recognition hinder the widespread application of RFFI. This paper presents an unsupervised open-set RFF identification algorithm designed to address the robustness challenges associated with low SNR. Our approach integrates the Noise2Noise method for de noising, drawing inspiration from its successful applications in image and speech processing. The proposed framework utilizes an image-based autoencoder (AE) to extract features from the differential constellation trace figure (DCTF) of the signals after Noise2Noise denoising. The open-set recognition task is performed by cosine distance measurement. We carried out extensive experimental evaluation involving 18 ZigBee devices and a USRP software-defined radio platform. Our proposed method can achieve a gain up to 25% under low SNRs.

关键词： Performance evaluation Accuracy Zigbee Fingerprint recognition Feature extraction Task analysis Speech processing

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：