检索结果-内蒙古大学图书馆

Prediction of breast cancer metastasis by deep learning pathology

IET image processing 2023年第2期17卷 533-543页

作者： Lu, Yuanyue Zhang, Jun Liu, Xueyu Zhang, Zhihong Li, Wangxing Zhou, Xiaoshuang Li, Rongshan Shanxi Med Univ Clin Med Coll 5 Shanxi Prov Peoples Hosp Taiyuan Peoples R China Shanxi Kidney Dis Inst Taiyuan Peoples R China Taiyuan Univ Technol Coll Data Sci Taiyuan Peoples R China Taiyuan Univ Technol Coll Software Taiyuan Peoples R China

With the rapid development of social economy, the incidence of breast cancer is increasing year by year. Whether there is lymph node metastasis in frozen tissue sections during breast cancer surgery is of tremendous priority for breast cancer surgical decision-making. Therefore, it is very significant to diagnose the pathological sections of breast cancer quickly and accurately. In this study, a model which can quickly fine segmentation of lesion regions in high-resolution breast cancer pathology sections is proposed. Firstly, pathology sections are processed by pre-processing module;Secondly, the main lesion region in pathology sections can be quickly recognized by recognition module;Thirdly, the fine segmentation of lesion region can be accomplished by segmentation module. The dataset is selected from two medical institutions to evaluate the proposed model;it achieved the average recognition precision of 0.936 for region of interest in high-resolution pathology section, with an F1-score of 0.787;and the dice for lesion region segmentation is 0.8517. The proposed model outperforms several similar works, which can effectively improve the speed and precision of pathologist's diagnosis for high-resolution breast cancer pathology sections.

关键词： Biology and medical computing image segmentation frozen tissue sections pathological sections medical image processing Optical and laser radiation (medical uses) main lesion region patient diagnosis Optical and laser radiation (biomedical imaging/measurement) Patient care and treatment Neural nets deep learning pathology Medical and biomedical uses of fields, radiations, and radioactivity biomedical optical imaging Optical, image and video signal processing computer vision and image processing techniques cancer deep learning (artificial intelligence) image recognition surgery breast cancer surgery gynaecology breast cancer metastasis high-resolution pathology section lesion region segmentation fine segmentation biological organs Patient diagnostic methods and instrumentation high-resolution breast cancer pathology sections health physics tumours breast cancer surgical decision-making Biomedical measurement and imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of road traffic signs from natural scene images based on pixel vector and central projected shape feature

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2012年第3期6卷 282-291页

作者： Zhang, K. Sheng, Y. Li, J. Nanjing Normal Univ Key Lab Virtual Geog Environm Minist Educ Nanjing 210046 Jiangsu Peoples R China

Considering the problem of automatic information acquisition in the field of intelligent transportation system (ITS), a new approach for detection of road traffic sign from natural scene images is proposed in this study. The adaptive colour segmentation based on pixel vector is firstly used to segment colour image into binary image and stand out traffic sign regions, which can reduce the influence of lighting conditions on image segmentation. Secondly, to improve the ability of shape identification during traffic sign detection, central projection transformation (CPT) is used to compute shape feature vectors of different candidate regions, and this shape feature is input to the probabilistic neural networks (PNN) to discriminate true traffic signs from candidates. The proposed approach is applied to many natural images. Experimental results show that the proposed method can effectively detect road traffic signs from natural scene images.

关键词： Traffic engineering computing Neural computing techniques colour image segmentation probability data acquisition image colour analysis neural nets binary image adaptive colour segmentation computer vision and image processing techniques lighting conditions pixel vector PNN shape identification natural scene images Optical, image and video signal processing image segmentation natural scenes road traffic sign automatic detection central projected shape feature central projection transformation object detection feature extraction ITS intelligent transportation system probabilistic neural networks automatic information acquisition CPT shape feature vectors road traffic Other topics in statistics automated highways

来源：评论

学校读者我要写书评

暂无评论

Visual sensitivity-based low-bit-rate image compression algorithm

引用

IET image processing 2012年第7期6卷 910-918页

作者： Xia, Q. Li, X. Zhuo, L. Lam, K. M. Beijing Univ Technol Signal & Informat Proc Lab Beijing Peoples R China Hong Kong Polytech Univ Dept Elect & Informat Engn Ctr Signal Proc Kowloon Hong Kong Peoples R China

In this study, the authors present a visual sensitivity-based low-bit-rate image compression algorithm. The authors algorithm combines both visual sensitivity and compression techniques so that a higher compression rate, with satisfactory visual quality, can be achieved. In the coding process, the input image is divided into blocks, and each block is classified as an edge block (EB), a textural block (TB) or a flat block (FB). For EBs, which are most important to the subjective quality of decoded images, the standard Joint Photographic Experts Group (JPEG) coding scheme with a tolerant quantisation step is employed so as to restrict the blocking artefacts caused by the quantisation error to an acceptable level. For FBs, a skipping scheme is employed on blocks in the compression process so as to save the bits. The coding of the skip blocks, identified by the skipping scheme, will make reference to the reconstructed regions of the image in the encoding process. Owing to the masking effects of the human visual system on high-frequency textures, standard JPEG compression coding with a greater quantisation step is employed on the down-scaled version of non-skip blocks and TBs. Experimental results show the superior performance of our method in terms of both compression efficiency and visual quality.

关键词： blocking artefacts edge block classification textural block classification visual sensitivity-based low-bit-rate image compression algorithm data compression image reconstruction Joint Photographic Experts Group computer vision and image processing techniques image and video coding image coding standard JPEG compression coding skipping scheme quantisation (signal) visual quality image classification high-frequency textures image reconstruction regions image texture block codes skip block coding flat block classification quantisation error JPEG coding scheme

来源：评论

学校读者我要写书评

暂无评论

image-based facial recognition in the domain of high-order polynomial one-way mapping

引用

IET image processing 2008年第3期2卷 139-149页

作者： Dabbah, M. A. Woo, W. L. Dlay, S. S. Newcastle Univ Newcastle Upon Tyne NE1 7RU Tyne & Wear England

The authors present a secure facial recognition system. The biometric data are transformed to the cancellable domain using high-order polynomial functions and co-occurrence matrices. The proposed method has provided both high-recognition accuracy and biometric data protection. Protection of data relies on the polynomial functions, where the new reissued cancellable biometric can be obtained by changing the polynomial parameters. Besides the protection of data, the reconstructed co-occurrence matrices also contributed to the accuracy enhancement. Hadamard product is used to reconstruct the new measure and has shown high flexibility in proving a new relationship between two independent covariance matrices. The proposed cancellable biometric is treated in the same manner as the original biometric data, which enables replacement of original data by the novel cancellable algorithm with no change to the authentication system. The two-dimensional principal component analysis recognition algorithm is used at the authentication stage. Results have shown high non-reversibility of data with improved accuracy over the original data and raised the performance recognition rate to 97%.

关键词： Hadamard product Algebra two-dimensional principal component analysis cooccurrence matrices image recognition face recognition computer vision and image processing techniques covariance matrices high-order polynomial one-way mapping principal component analysis biometric data protection Interpolation and function approximation (numerical analysis) high-order polynomial functions polynomials Other topics in statistics image-based facial recognition high-recognition accuracy biometrics (access control)

来源：评论

学校读者我要写书评

暂无评论

Frequency-domain weighted-least-squares design of quadratic interpolators

引用

IET SIGNAL processing 2010年第1期4卷 102-111页

作者： Deng, T. -B. Toho Univ Dept Informat Sci Fac Sci Chiba 2748510 Japan

Existing finite-support interpolators are derived from continuities in the time-domain. In this study, the authors optimally design a quadratic interpolator using two second-degree piecewise polynomials in the frequency-domain. The optimal coefficients of the piecewise polynomials are found by minimising the weighted least-squares error between the ideal and actual frequency responses of the quadratic interpolator subject to a few constraints. Adjusting the weighting functions in different frequency bands can yield accurate frequency response in a specified passband and even can ignore 'don't care' bands so that various quadratic interpolators can be designed for interpolating various discrete signals containing different frequency components. One-dimensional and two-dimensional examples have shown that the quadratic interpolator can achieve much higher interpolation accuracy than the existing interpolators for wide-band signals, and various images have been tested to verify that the quadratic interpolator can achieve comparable interpolation accuracy as the Catmull-Rom cubic for narrow-band signals (images), but the computational complexity can be reduced to about 70%. Therefore both narrow-band and wide-band signals can be interpolated with high accuracy.

关键词： piecewise polynomials computer vision and image processing techniques interpolation wideband signals frequency-domain weighted-least-squares design quadratic interpolators Interpolation and function approximation (numerical analysis) second-degree piecewise polynomials computational complexity Optical, image and video signal processing least squares approximations discrete signals finite-support interpolators image processing Catmull-Rom cubic

来源：评论

学校读者我要写书评

暂无评论

image colourisation using graph-based semi-supervised learning

引用

IET image processing 2009年第3期3卷 115-120页

作者： Liu, B. -B. Lu, Z. -M. Sun Yat Sen Univ Sch Informat Sci & Technol Guangzhou 510275 Guangdong Peoples R China

A novel colourisation algorithm using graph-based semi-supervised learning (SSL) is presented. We show that the assumption of the colourisation problem is consistent with the fundamental of graph-based SSL methods. Satisfactory results are obtained in the experiments that validate the proposed algorithm. To reduce the time and memory requirements when dealing with large scale images, we further propose a two-stage speedup approach. Comparative results show that the computation complexity is dramatically reduced.

关键词： graph-based semi-supervised learning learning (artificial intelligence) computer vision and image processing techniques Knowledge engineering techniques graph theory Combinatorial mathematics two-stage speedup approach image colourisation algorithm Optical, image and video signal processing image colour analysis SSL method

来源：评论

学校读者我要写书评

暂无评论

Driver activity recognition using spatial-temporal graph convolutional LSTM networks with attention mechanism

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第2期15卷 297-307页

作者： Pan, Chaopeng Cao, Haotian Zhang, Weiwei Song, Xiaolin Li, Mingjun Hunan Univ State Key Lab Adv Design & Mfg Vehicle Body Changsha Peoples R China Shanghai Univ Engn Sci Coll Automot Engn Shanghai Peoples R China

Driver activity engagement while driving plays a vital role that leads to negative outcomes of driving safety. To reduce traffic accidents and ensure driving safety, real-time driver activity recognition architecture is proposed in this study. Specifically, a total of eight kinds of common driving-related activities are identified, which include the normal driving, left or right checking, texting, answering the phone, using media, drinking, and picking up objects. Raw experiment videos are collected via onboard monocular cameras, which are used for the upper body skeleton information extraction of the driver. Then, the graph convolutional networks (GCN) are constructed for spatial structure feature reasoning in a single frame, which is consecutively followed by long short-term memory (LSTM) networks for temporal motion feature learning within the sequence. Moreover, the attention mechanism is further utilised to emphasise the keyframes to select discriminative sequential information. Finally, a large-scale driver activity dataset, consisting of both naturalistic driving data and simulative driving data, is collected for model training and evaluations. Experimental results show that the general recall ratio of those eight driving-related activities reaches up to 88.8% and the real-time recognition efficiency can reach up to 24 fps, which would satisfy the real-time requirements of engineering applications.

关键词： Optical, image and video signal processing image recognition computer vision and image processing techniques Video signal processing Traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Context-based biometric key generation for Iris

引用

IET computer vision 2011年第6期5卷 389-397页

作者： Rathgeb, C. Uhl, A. Salzburg Univ Multimedia Signal Proc & Secur Lab Dept Comp Sci A-5020 Salzburg Austria

In this study, a generic treatment of how to generate biometric keys from binary biometric templates is presented. A context-based analysis of iris biometric feature vectors based on which stable biometric keys are extracted is proposed. Most reliable bits in binary iris codes are detected and utilised to construct keys from fuzzy biometric data. The proposed key-generation scheme is adapted to diverse iris biometric feature extraction algorithms, evaluated on a comprehensive database and compared against existing iris biometric cryptosystems. In addition, the scheme is extended to provide fully revocable biometric keys, long enough to be applied in generic cryptosystems. Experimental results confirm the soundness of the approach.

关键词： iris biometric feature vectors context-based biometric key generation key-generation scheme iris biometric cryptosystems iris biometric feature extraction algorithms image recognition fuzzy biometric data context-based analysis computer vision and image processing techniques iris recognition feature extraction

来源：评论

学校读者我要写书评

暂无评论

3D inverse synthetic aperture radar image quality improvement using sparse signal representation

引用

IET RADAR SONAR AND NAVIGATION 2023年第3期17卷 388-407页

作者： Mehrpooya, Ali Karbasi, Seyed Mohammad Nazari, Milad Abbasi, Zahra Nayebi, Mohammad Mahdi Sharif Univ Technol Dept Elect Engn Tehran Iran Malek Ashtar Univ Technol Dept Elect Engn Tehran Iran

Generalisation of one-dimensional dictionary learning (1DDL) algorithms to Multidimensional (MD) mode and its utilisation in MD data applications, increases the speed and reduces the computational complexity. An example of such an application is 3D inverse synthetic aperture radar (ISAR) image reconstruction and noise reduction. In this study, in addition to MD mode generalisation, the formulation structure of the multidimensional dictionary learning (MDDL) problem is discussed followed by two novel algorithms to solve it. The first one is based on the K-singular value decomposition algorithm for 1DDL, which uses alternating minimisation and singular value decomposition. The second algorithm is the extension of the sequential generalisation of K-means 1DDL algorithm to the MD mode. Moreover, the MD tensor denoising method based on the MDDL algorithm (MDDL-ALG) is proposed. As an application, the proposed method is used to denoise the 3D ISAR image. The numerical simulations reveal that the proposed methods, in addition to reducing the memory consumption and the computational complexity, also enjoy higher convergence rate in comparison to 1D algorithms. Specifically, convergence speed of MD algorithms, depending on the training data size, is up to at least 10 times faster than the equivalent 1D counterparts. As revealed through the simulations, the amount of signal to noise ratio recovered by the proposed methods is almost 2 dB higher than the case using a pre-designed dictionary for denoising. Moreover, it outperforms about 10 dB over the case with the conventional 3D-IFFT method for image construction.

关键词： noise reduction Optimisation techniques Signal processing and detection 3D inverse synthetic aperture radar image quality improvement Radar equipment, systems and applications MDDL algorithm formulation structure Algebra MDDL-ALG minimisation synthetic aperture radar MD tensor denoising method image construction singular value decomposition multidimensional mode Radar theory radar imaging Optical, image and video signal processing computer vision and image processing techniques image denoising MD data applications sequential generalisation multidimensional dictionary learning problem MD mode generalisation 1DDL algorithm 3D ISAR image reconstruction convergence speed 3D-IFFT method signal representation 3D inverse synthetic aperture radar image reconstruction Interpolation and function approximation (numerical analysis) MD algorithms one-dimensional dictionary learning algorithms sparse signal representation equivalent 1D counterparts pre-designed dictionary image reconstruction K-singular value decomposition algorithm training data size fast Fourier transforms computational complexity

来源：评论

学校读者我要写书评

暂无评论

Algorithm to decompose three-dimensional complex structures at the necks: tested on snow structures

引用

IET image processing 2011年第2期5卷 132-140页

作者： Theile, T. Schneebeli, M. WSL Inst Snow & Avalanche Res SLF CH-7260 Davos Switzerland

The separation of overlapping particles in three-dimensional images is an image processing task with many fields of application. However, commonly used image processing algorithms have difficulties to identify the single particles and their connections in certain structures. Here the authors present an alternative algorithm for part decomposition, which performs better on some structures than common algorithms. This algorithm is a special case of part decomposition, as it decomposes a structure at the necks into single particles. The necks are detected based on their characteristic negative Gaussian curvature. The algorithm itself consists of three steps: cutting at negative Gaussian curvature, region growing and intersecting plane minimisation. The authors tested the performance of the algorithm by comparison with two state-of-the-art algorithms for part decomposition, the watershed and a skeleton-based algorithm on strongly differing geometries, taken from natural snow samples. The two test algorithms are known for having difficulties to decompose certain structures. As the new algorithm uses a different characteristic to decompose the structure, the new algorithm is a good alternative to the existing algorithms. The new algorithm decomposes 72% of the reference structure correctly. This is a better performance than by the two other algorithms.

关键词： snow structures structural engineering computing Mechanical engineering applications of IT three-dimensional images image processing snow negative Gaussian curvature computer vision and image processing techniques decompose three-dimensional complex structures Mechanical structures skeleton-based algorithm Optical, image and video signal processing Civil and mechanical engineering computing overlapping particles

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：