检索结果-内蒙古大学图书馆

Review of the deep learning for food image processing

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 15-30页

作者： Chenrui Niu Xiayang Ying Gan Pei Menghan Hu Guangtao Zhai Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic EngineeringEast China Normal UniversityShanghai 200241China Department of General Surgery Pancreatic Disease CenterRuijin HospitalShanghai Jiaotong University School of MedicineShanghai 200025China Istitute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai 200240China

As deep learning techniques are increasingly applied with greater depth and sophistication in the food industry,the realm of food image processing has progressively emerged as a central focus of research *** work provides an overview of key practices in food image processing techniques,detailing common processing tasks including classification,recognition,detection,segmentation,and image retrieval,as well as outlining metrics for evaluating task performance and thoroughly examining existing food image datasets,along with specialized food-related *** terms of methodology,this work offers insight into the evolution of food image processing,tracing its development from traditional methods extracting low and intermediate-level features to advanced deep learning techniques for high-level feature extraction,along with some synergistic fusion of these *** is believed that these methods will play a significant role in practical application scenarios such as self-checkout systems,dietary health management,intelligent food service,disease etiology tracing,chronic disease management,and food safety ***,due to the complex content and various types of distortions in food images,further improvements in related methods are needed to meet the requirements of practical applications in the *** is believed that this study can help researchers to further understand the research in the field of food imaging and provide some contribution to the advancement of research in this field.

关键词： deep learning food image processing feature extraction dietary health

来源：评论

学校读者我要写书评

暂无评论

Adaptive dictionary learning for distributed compressive video sensing

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第4期6卷 141-149页

作者： Wu, Minghu Zhu, Xiuchang Gan, Zongliang Li, Xin Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China School of Electrical and Electronic Enginesering Hubei University of Technology Wuhan China

Compressive sensing (CS) is a new technique for data sampling and compression simultaneously. In this paper, we propose a novel distributed video coding algorithm with dynamic measurement rate allocation based on compressive sensing principles, where almost all computation burdens can be shifted to the decoder, resulting in a very low-complexity encoder. So the proposed algorithm can be useful in those video applications that require very low complex encoders. At the decoder, the compressed video can be efficiently reconstructed with adaptive dictionary learning. The simulation results show that the proposed algorithm outperforms the distributed compressive video sensing with non-adaptive learning local dictionary and global dictionary.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Ground-state properties of metal/organic-ferromagnet heterojunctions

引用

Physical Review B 2018年第23期98卷 235415-235415页

作者： Yuanyuan Miao Shuai Qiu Guangping Zhang Junfeng Ren Chuankui Wang Guichao Hu Shandong Province Key Laboratory of Medical Physics and Image Processing Technology School of Physics and Electronics Shandong Normal University Jinan 250100 China

Based on an Anderson-like model including the electron-lattice interaction and a Hubbard term, the ground-state properties of metal/organic-ferromagnet heterojunctions are investigated. Both the nonmagnetic and ferromagnetic metals are considered. The results reveal a picture of electron injection and the induced excitations in the organic ferromagnets, which is divided into two regimes with the increase of injected electrons: the first solitonlike interfacial state and the subsequent coexistence of the interfacial state and polaron states. The interfacial state is further explored by the shallow states and localized wave functions with the analysis of the molecular self-consistent Hamiltonian. In the case of the ferromagnetic metal, the effect of the magnetization orientation alignment between the metal and the organic ferromagnet is discussed, where the lowest injection barrier is found when the magnetization orientations of the two components are parallel. An injection-induced degradation of the magnetism of the organic ferromagnet is also obtained. This paper provides a basic understanding of the metal/organic-ferromagnet interface, which is essential for further spintronic study in organic ferromagnetic devices.

关键词： Peierls transition Polarons Spin injection Spin polarization Spintronics Ferromagnets Heterostructures Junctions Organic compounds Anderson impurity model

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Lossless Compression of Aurora Spectral images: A Spatial-Temporal-Spectral Joint Approach 17

Transformer-based Lossless Compression of Aurora Spectral Im...

引用

17th IEEE International Conference on Signal processing, ICSP 2024

作者： Cao, Xinlong Li, Jiaojiao Li, Yuanqing Yan, Jiapeng Zheng, Zhenxing Xi'an University of Posts & Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi'an710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an710121 China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi'an710121 China

ISBN: (纸本)9798350387384

Aurora spectral image lossless compression has seen significant advancements in recent years. However, most compression algorithms are based on traditional image compression techniques, focusing solely on spectral and spatial correlations without considering temporal correlations. To further enhance compression performance, this paper proposes a Transformer-based point-by-point prediction algorithm for auroral spectral images, which simultaneously uses spatial, spectral and temporal contexts for prediction. Our prediction network consists of two parts: an encoder and a decoder. The encoder is composed of the encoding unit of the original Transformer and is used to extract features from spatial, spectral and temporal contexts. The decoder consists of fully connected layers and is used for prediction. Experimental results show that the average bitrate of this method is reduced by 0.179 bpp compared with the JPEG2000 algorithm, and the average bitrate is reduced by 0.054 bpp compared with the online DPCM algorithm. © 2024 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Niobium telluride absorber for a mode-locked vector soliton fiber laser

引用

Science China(Physics,Mechanics & Astronomy) 2023年第5期66卷 130-138页

作者： XinXin Shang NanNan Xu Jia Guo Shuo Sun HuaNian Zhang SWageh Ahmed AAl-Ghamdi Han Zhang DengWang Li Shandong Province Key Laboratory of Medical Physics and Image Processing Technology Shandong Provincial Key Laboratory of Optics and Photonic DeviceSchool of Physics and ElectronicsShandong Normal UniversityJinan 250014China Institute of Microscale Optoelectronics Collaborative Innovation Center for Optoelectronic Science&TechnologyKey Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong ProvinceCollege of Physics and Optoelectronic EngineeringShenzhen Key Laboratory of Micro-Nano Photonic Information TechnologyGuangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)Shenzhen UniversityShenzhen 518060China School of Physics and Optoelectronic Engineering Shandong University of TechnologyZibo 255049China Department of Physics Faculty of ScienceKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Niobium telluride(NbTe_(2)),an emerging transition metal dichalcogenide material,has been theoretically predicted to have nonlinear absorption properties and excellent optical ***,only a few studies of the utilization of NbTe_(2)in ultrafast photonics have been *** this work,a NbTe_(2)-based saturable absorber(SA)was applied in an erbium-doped fiber as a mode-locked device,and a vector soliton based on NbTe_(2)was obtained for the first ***_(2)-PVA film SA was successfully prepared by the liquid-phase exfoliation and spin coating methods,with a modulation depth of up to 10.87%.The nonlinear absorption coefficient of NbTe_(2)-based SA film tested through the open-aperture Z-scan laser measurement is 0.62×10^(−11) m/W.A conventional soliton with a pulse duration of 858 fs was generated using NbTe_(2)-based SA,which was demonstrated to be a kind of polarization-locked vector soliton in further *** experimental results reveal the nonlinear optical properties of NbTe_(2)and broaden its applications in ultrafast photonic devices.

关键词： niobium telluride saturable absorber mode-locked pulse fiber laser

来源：评论

学校读者我要写书评

暂无评论

image Retrieval Based on Bit-Plane Distribution Feature

Image Retrieval Based on Bit-Plane Distribution Feature

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Zhao Shan Liu Jing School of Computer Science and technology Henan Polytechnic University Jiaozuo China Jiangsu Province Key Laboratory on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

Based on the analysis of color histogram for image retrieval, a new descriptor, bit-plane distribution feature (BPDF), is proposed in this paper. The image is firstly divided into eight bit-planes. Meantime, the Gray code of bit-planes is used to avoid the effect of changes in the intensity values on bit-planes. Then, according to the distribution of each bit-plane, a feature vector is constructed by the first four significant planes which contain most of the structural information of the image. Finally, the Mahalanobis distance is adopted to measure the similarity because of the correlation between the concerned vectors after designing a correlation-weighted matrix. Comparisons are conducted between BPDF and other descriptors. Experimental results show that the proposed method provides more significantly retrieval results than the traditional ones.

关键词： image retrieval Histograms Quantization Computer science image color analysis Reflective binary codes Fuzzy systems image processing image communication image analysis

来源：评论

学校读者我要写书评

暂无评论

Using Structural degradation and Parallax for reduced-reference quality assessment of 3D images

Using Structural degradation and Parallax for reduced-refere...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Qi Xu Guangtao Zhai Min Liu Ke Gu Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China

Owing to the thriving market of stereoscopic image based applications, efficient and effective 3D image quality assessment (IQA) techniques become colossally required these days. Consequently, we introduce a new reduced-reference (RR) stereoscopic image quality metric to meet this demand, through measuring Structural degradation and Saliency based Parallax compensation Model (SSPM). Experimental results on the LIVE 3D image Quality Database, including both symmetrically and asymmetrically distorted stereoscopic images in different categories and quality levels, are provided to justify the effectiveness of the proposed SSPM model as compared to some existing progressive and popular stereoscopic IQA approaches. Meanwhile, it deserves broad attentions that only four number pairs, extracted from original image, are required as the key feature to be sent to the receiver terminal, thus making this procedure also efficient.

关键词： Three-dimensional displays Stereo image processing Measurement image quality Databases Degradation Nonlinear distortion

来源：评论

学校读者我要写书评

暂无评论

Blind image quality assessment for noise

Blind image quality assessment for noise

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Min Liu Guangtao Zhai Zhenyu Zhang Yuntao Sun Ke Gu Xiaokang Yang Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai China

image denoising has been fanatically researched for a very long time in that it is a commonplace yet important subject. The task to testify the performance of different image de-noising methods always resorts to PSNR in the past, until the emergence of SSIM, a landmark image quality assessment (IQA) metric. Since then, a vast majority of IQA methods were introduced in terms of various kinds of models. But unfortunately, those IQA metrics are along with more or less deficiencies such as the requirement of original images, making them far less than the ideal approaches. To address this problem, in this paper we propose an effective and blind image quality assessment for noise (dubbed BIQAN) to approximate the human visual perception to noise. The BIQAN is realized with three important portions, namely the free energy based brain principle, image gradient extraction, and texture masking. We conduct and compare the proposed BIQAN and a large amount of existing IQA metrics on three largest and most popular image quality databases (LIVE, TID2013, CSIQ). Results of experiments prove that the BIQAN has acquired very encouraging performance, outperforming those competitors stated above.

关键词： Measurement image quality Quality assessment Indexes PSNR

来源：评论

学校读者我要写书评

暂无评论

Transclaw U-Net: Claw U-Net With Transformers for Medical image Segmentation 5

Transclaw U-Net: Claw U-Net With Transformers for Medical Im...

引用

5th International Conference on Information communication and Signal processing, ICICSP 2022

作者： Yao, Chang Hu, Menghan Li, Qingli Zhai, Guangtao Zhang, Xiao-Ping East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing Shanghai China Institute of Image Communication and Information Processing Shanghai Jiao Tong University Shanghai China Ryerson University Department of Electrical Computer and Biomedical Engineering Toronto Canada

ISBN: (纸本)9781665485890

In medical image analysis, the long-range spatial features are often not accurately obtained by the traditional convolutional neural networks. Hence, we propose a TransClaw U-Net network structure. The transformer part is added after three convolution operations to fuse shallow features extracted by convolution operations for maximally encoding the long-range spatial features between patches. The 'Claw' in TransClaw U-net means that we add the bottom upsampling part to retain the deepest feature information for detail segmentation. In addition, the modified three-channel global attention mechanism to blend the outputs of three channels (the encoding part, the bottom upsampling part and the decoding part) to effectively extract image contours. The experimental results on Synapse Multi-organ Segmentation Dataset show that TransClaw U-Net performs better than other networks. The results of ablation experiments prove the effectiveness of the three improved components of the network and influence of input image size and skip-connection numbers on network performance. The source code will be publicly available once the paper is accepted. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Separation of superimposed images with unknown motions using sparsity priors

Separation of superimposed images with unknown motions using...

引用

IEEE Visual communications and image processing (VCIP)

作者： Qing Yan Xiaokang Yang Yi Xu The Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai China

When people take photos through a transparent surface, it is ubiquitous that the images are superimposed with two source images, the transmitted layer and the reflected layer. In this paper, we utilize the sparsity priors over image color distribution and image gradients, and we realize the separation of such images by exploiting the diversity (relative motions of source images) in different snapshots. Our approach can estimate the motion even when layer image is quite faint, extract layer gradients when layer intensity is unchanged, and obtain a reliable separation by considering the gradients as limitations. The effectiveness of our approach is shown in experiments on both synthetic images and real world photos.

关键词： image color analysis Feature extraction Transforms Transmission line matrix methods Reliability PSNR Surface morphology

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：