检索结果-内蒙古大学图书馆

Evaluation of suturing performance in general surgery and ocular microsurgery by combining computer vision-based software and distributed fiber optic strain sensors: a proof-of-concept

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2020年第8期15卷 1359-1367页

作者： Handelman, Amir Keshet, Yariv Livny, Eitan Barkan, Refael Nahum, Yoav Tepper, Ronnie Holon Inst Technol Fac Engn Dept Elect Engn Holon Israel Clalit Hlth Serv Simultech Ctr Med Simulat Meir Hosp Med Ctr Kefar Sava Israel Rabin Med Ctr Dept Ophthalmol Petah Tiqwa Israel Tel Aviv Univ Sackler Fac Med Tel Aviv Israel

Purpose Improper suturing may cause an inadequate wound healing process and wound dehiscence as well as infection and even graft rejection in case of corneal transplantation. Hence, training surgeons in correct suturing procedures and objectively assessing their surgical skills is desirable. methods Two complementary methods for assessment of suturing skills in two medical fields (general surgery and ocular microsurgery) were demonstrated. Suturing quality is assessed by computer vision software. Evaluation of stitching flow of operation is based on measuring strain induced in an optical fiber that is placed in proximity to the wound and parallel thereto and is pressed and passed by wound stitches. Results Our software generated a score for suturing outcome in both general surgery and ocular microsurgery when the stitching was done on a patch. Every trainee received a score in the range 0-100 that describes his/her performance. Strain values were recognized when using a patch in general surgery and a rubber patch in ocular microsurgery, but were less distinct in (disqualified) human cornea. Conclusions We proved a concept of an objective scoring method (based on various image processing algorithms) for assessment of suturing performance. It was also shown that fiber optic strain sensors are sensitive to the flow of stitching operation on a patch but are less sensitive to the flow of stitching operation on a human cornea. By combining these two methods, we can comprehensively evaluate the suturing performance objectively.

关键词： Sutures Fiber optic sensors Computer vision Ocular microsurgery Surgical education

来源：评论

学校读者我要写书评

暂无评论

Monitoring gait events by image processing 24

Monitoring gait events by image processing

引用

24th KES International conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2020

作者： Young, Jeffery Simic, Milena Simic, Milan School of Engineering RMIT University Melbourne3083 Australia Faculty of Health Sciences University of Sydney Sydney2141 Australia

This paper presents a novel methodology in measuring Foot Progression Angle (FPA) and other gait parameters, using digital image processing, based on body and foot speeds. Measurements of body parts' movement speeds allow identification of gait events such as initial contact, mid stance and Flat Foot Phase (FFP). Algorithms were developed to segment FFP based on the motion patterns and their relationships. Digital data and graphic presentation results are generated synchronously from the same optic device. This could allow clinicians to confirm results of the both data sets. New methodology requires participant to walk along a 10-meter flat walkway, at self-selected speed, wearing comfortable shoes. Measurement set-up involves a mobile-phone camera, attached to a torso-mounted strap, pointing downwards, a walkway with parallel straight lines outlining progression direction, and printed strips placed along the long axis of the foot. Several methods were evaluated to find the best way to detect initial contact, flat foot and mid stance phases. Our new methodology may present a solution for mobile gait analysis, which could be used at home, or community / outdoor environment, basically outside of the sophisticated well equipped and expensive labs. © 2020 The Authors. Published by Elsevier B.V.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Underwater image Enhancement based on Dehazing and Color Correction 17

Underwater Image Enhancement based on Dehazing and Color Cor...

引用

IEEE Int Conf on parallel and distributed processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking (ISPA/BDCloud/SocialCom/SustainCom)

作者： Li, Hanyu Zhuang, Peixian Wang, Wei Li, Jingjing Nanjing Univ Informat Sci & Technol Nanjing Peoples R China

ISBN: (纸本)9781728143286

Clear and clean underwater images can provide valuable information, which are crucial for developing, exploring, and protecting the underwater resources. However, the raw underwater image seldom fulfills the requirements concerning the underwater research due to the serious image degradation. To enhance single underwater image, we propose an effective and new method combined on the dehazing and color correction algorithm. First, we obtain the dehazed image by a fusion dehazing method calculated on the difference between maximum green-blue dark channels and maximum red dark channel, and the top 0.1% bright pixels in green-blue dark channels. Second, we obtain the enhanced image via the color restoration method corresponding to the human visual system. Finally, we use an efficient and simple weight fusion strategy to incorporate the dehazed image and the enhanced image for yielding the final high quality underwater image. Subjective assessment demonstrates that our method can remove haze, correct color cast, improve image brightness, and preserve image naturalness. The enhanced results obtain the highest values in terms of entropy, average gradient, UCIQE, UIQM, and CCF, which is superior to several existing underwater enhancement methods. Moreover, our method can improve other degraded image quality, such as low-light image and haze image, and can benefit the application tests, such as key points matching and edge detection.

关键词： Single underwater image enhancement image dehazing retinex color correction

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on Data Management, Analytics and Innovation, ICDMAI 2019

3rd International Conference on Data Management, Analytics a...

引用

3rd International conference on Data Management, Analytics and Innovation, ICDMAI 2019

ISBN: (纸本)9789813299481

The proceedings contain 35 papers. The special focus in this conference is on Data Management, Analytics and Innovation. The topics include: Automated Scheduling of Hostel Room Allocation Using Genetic Algorithm;Evaluation of ASTER TIR Data-Based Lithological Indices in Parts of Madhya Pradesh and Chhattisgarh State, India;Analyzing Linear Relationships of LST with NDVI and MNDISI Using Various Resolution Levels of Landsat 8 OLI and TIRS Data;automatic Robot processing Using Speech Recognition System;banking and FinTech (Financial Technology) Embraced with IoT Device;GRNN++: A parallel and distributed Version of GRNN Under Apache Spark for Big Data Regression;an Entropy-Based Technique for conferences Ranking;MapReduce mRMR: Random Forests-Based Email Spam Classification in distributed Environment;the Impact of Sustainable Development Report Disclosure on Tax Planning in Thailand;ASK Approach: A Pre-migration Approach for Legacy Application Migration to Cloud;clustering and Labeling Auction Fraud Data;big Data Security Challenges and Preventive Solutions;role and Challenges of Unstructured Big Data in Healthcare;zip Zap Data—A Framework for ‘Personal Data Preservation’;a Systematic Mapping Study of Cloud Large-Scale Foundation—Big Data, IoT, and Real-Time Analytics;studies on Radar imageries of Thundercloud by image processing Technique;PURAN: Word Prediction System for Punjabi Language News;Implementation of hDE-HTS Optimized T2FPID Controller in Solar-Thermal System;Design of Sigma-Delta Converter Using 65 nm CMOS Technology for Nerves Organization in Brain Machine Interface;Performance Comparison of Machine Learning Techniques for Epilepsy Classification and Detection in EEG Signal;novel Approach for Plant Disease Detection Based on Textural Feature Analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Machine Intelligence and Signal processing, MISP 2019

2nd International Conference on Machine Intelligence and Sig...

引用

2nd International conference on Machine Intelligence and Signal processing, MISP 2019

ISBN: (纸本)9789811513657

The proceedings contain 36 papers. The special focus in this conference is on Machine Intelligence and Signal processing. The topics include: Real-time RADAR and LIDAR sensor fusion for automated driving;generalizing streaming pipeline design for big data;Adaptive fast composite splitting algorithm for MR image reconstruction;extraction of technical and non-technical skills for optimal project-team allocation;modified flower pollination algorithm for optimal power flow in transmission congestion;Intelligent condition monitoring of a CI engine using machine learning and artificial neural networks;bacterial foraging optimization in non-identical parallel batch processing machines;healthcare information retrieval based on neutrosophic logic;Convolutional neural network long short-term memory (CNN + LSTM) for histopathology cancer image classification;a novel approach for music recommendation system using matrix factorization technique;forecasting with multivariate fuzzy time series: A statistical approach;nature-inspired algorithm-based feature optimization for epilepsy detection;a combined machine-learning approach for accurate screening and early detection of chronic kidney disease;backpropagation and self-organizing map neural network methods for identifying types of eggplant fruit;head pose prediction while tracking lost in a head-mounted display;recommendation to group of users using the relevance concept;ACA: Attention-based context-aware answer selection system;dense and partial correspondence in non-parametric scene parsing;audio surveillance system;mopsa: Multiple output prediction for scalability and accuracy;Generation of image captions using VGG and resnet CNN models cascaded with RNN approach;impact of cluster sampling on the classification of landsat 8 remote sensing imagery;deep neural networks for out-of-sample classification of nonlinear manifolds;FPGA implementation of LDPC decoder.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polarmask-Tracker: Lightweight Multi-Object Tracking and Segmentation Model for Edge Device

Polarmask-Tracker: Lightweight Multi-Object Tracking and Seg...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Xiaoyun Dong Zhenchao Ouyang Zeling Guo Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems Hangzhou Innovation Institution Beihang University Binjiang China Sino-French Engineer School Beihang University Beijing China

The image or video input from the camera is one of the important data sources for unmanned vehicles to perceive the environment. However, the 2D/3D bounding box can only provide a very coarse approximation because one box often contains other targets and background. In order to solve the problem of precise target tracking and computing limitations of edge devices, this paper proposes Polarmask-Tracker, a lightweight segmentation-based multi-object tracking network for vehicular edge devices. Polarmask-Tracker extended the lightweight Polarmask segmentation head with tracking vector. The polar mask replaces the traditional mask prediction by regression of a group of fixed edge points in polar coordinate system, which can greatly optimize the computational complexity and regression difficulty of the mask. With an additional tracking vector branch generated based on mask, the model can learn tracking tasks in an end-to-end manner. Finally, we further accelerated the entire model based on TensorRT and achieve real-time tracking on mobile edge computing platform. Different from previous evaluations on the imageNet and COCO datasets, this study uses the KITTI tracking dataset to extend the instance segmentation task to segmentation tracking, also called MOTS. At the same time, the target scales captured from the autonomous vehicle camera are usually smaller, which also brings additional challenges. Evaluations on NVidia Jetson AGX show that the final Polarmask-Tracker can achieve 122.55 FPS, 46.57 mAP for mask segmentation, 56.418 HOTA for tracking.

关键词： image segmentation Target tracking Head Computational modeling Soft sensors Cameras Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Research on heterogeneous distributed fractal image compression algorithm based on parallel genetic algorithm and iterative function 4

Research on heterogeneous distributed fractal image compress...

引用

2019 4th International conference on Intelligent Computing and Signal processing, ICSP 2019

作者： Jian Ning, Han School of Computer Science Xi'An Shi You University Xi'an Shannxi710065 China

This paper briefly introduces the method and implementation of image compression of heterogeneous distributed genetic and iterative function system (IFS). Based on the traditional parallel genetic algorithm, a heterogeneous distributed model of parallel fractal image compression based on genetic algorithm is implemented, and the corresponding complex model design scheme is put forward. The results show that the algorithm has better search ability, its comprehensive performance such as signal-to-noise ratio/compression time is further improved, the decoding image is similar to the original image, and has high image quality effect. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel fusion method based on dynamic threshold neural P systems and nonsubsampled contourlet transform for multi-modality medical images

引用

SIGNAL processing 2021年 178卷 107793-107793页

作者： Li, Bo Peng, Hong Wang, Jun Xihua Univ Sch Comp & Software Engn Chengdu 610039 Sichuan Peoples R China Xihua Univ Sch Elect Engn & Elect Informat Chengdu 610039 Peoples R China

Dynamic threshold neural P systems (DTNP systems) are a distributed parallel computing model with an interesting mechanism involving the cooperative spiking of neurons in a local region. In this paper, this mechanism is combined with the nonsubsampled contourlet transform (NSCT) to develop a novel fusion method for multi-modality medical images. The complementary information of multi-modality images is extracted using an improved novel sum-modified Laplacian (INSML) feature, which is used in the fusion rules for the low-frequency NSCT coefficients. Moreover, the high-frequency NSCT coefficients are extracted using the WLE-INSML features, which are used to construct the fusion rules for these coefficients. The proposed fusion method is evaluated on an open dataset consisting of twelve pairs of multi-modality medical images. In addition, it is compared with nine previously reported fusion methods and four deep learning based fusion methods. The qualitative and quantitative experimental results demonstrate the advantage of the proposed fusion method in terms of the visual quality and fusion performance. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Dynamic threshold neural P systems Nonsubsampled contourlet transform image fusion Multi-modality medical images

来源：评论

学校读者我要写书评

暂无评论

Detection of Nuclear Cataract in Retinal Fundus image using RadialBasis FunctionbasedSVM

Detection of Nuclear Cataract in Retinal Fundus Image using ...

引用

International conference on parallel distributed and Grid Computing (PDGC)

作者： Manoj Kumar Behera S. Chakravarty Apurwa Gourav Satyabrata Dash Centurion University of Technology & Management Odisha India Gandhi Engineering College Bhubaneswar Orissa India

The following topics are dealt with: learning (artificial intelligence); feature extraction; pattern classification; diseases; support vector machines; Internet of Things; cloud computing; image classification; health... 详细信息

ISBN: (数字)9781728171326

ISBN: (纸本)9781728171333

关键词： Cataracts Support vector machines Kernel Retina Feature extraction Biomedical imaging Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Multidimensional Scaling Analysis for Target Localization From Bistatic Range Measurements in distributed MIMO Radars 4

Multidimensional Scaling Analysis for Target Localization Fr...

引用

4th IEEE International conference on Signal and image processing (ICSIP)

作者： Ma, Fuhe Guo, Fucheng Natl Univ Def Technol State Key Lab Complex Electromagnet Environm Effe Changsha 410073 Peoples R China

ISBN: (纸本)9781728136608

The multidimensional scaling (MDS) analysis is exploited in this paper to localize the target using bistatic range (BR) measurements in multiple-input multiple-output (MIMO) radar systems. Two methods are proposed, which are termed distributed MDS and joint MDS methods, respectively. In the proposed methods, the scalar product matrix in classic MDS framework is formulated using BR measurements. By minimizing the cost function composed of multiple scalar product matrices, a closed-form solution for target location is presented. Simulation results demonstrate the effectiveness of the proposed methods.

关键词： target localization multidimensional scaling bistatic range (BR) multiple-input multiple-output (MIMO) radar

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：