检索结果-内蒙古大学图书馆

Research on image text recognition based on canny edge detection algorithm and k-means algorithm

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2022年第SUPPL 1期13卷 72-80页

作者： Wu, Fangsheng Zhu, Changan Xu, Jinxiu Bhatt, Mohammed Wasim Sharma, Ashutosh Anhui Business Vocat Coll Inst Informat Engn Hefei 231131 Anhui Peoples R China Univ Sci & Technol China Hefei 230026 Anhui Peoples R China Cent Univ Punjab Bathinda India Southern Fed Univ Inst Comp Technol & Informat Secur Southern Fed Dist Russia

The latest research in the field of recognition of image characters has led to various developments in the modern technological works for the improvement of recognition rate and precision. This technology is significant in the field of character recognition, business card recognition, document recognition, vehicle license plate recognition etc. for smart city planning, thus its effectiveness should be improved. In order to improve the accuracy of image text recognition effectively, this article uses canny algorithm to process edge detection of text, and k-means algorithm for cluster pixel recognition. This unique combination combined with maximally stable extremal region and optimization of stroke width for image text yields better results in terms of recognition rate, recall, precision, F-score and accuracy. The results show that the correct recognition rate is 88.3% and 72.4% respectively with an accuracy value of 90.5% for the proposed method. This algorithm has high image text recognition rate, can recognize images taken in complex environment, and has good noise removal function. It is significantly an optimal algorithm for image text recognition.

关键词： canny edge detection algorithm k-means algorithm Image text recognition Noise removal

来源：评论

学校读者我要写书评

暂无评论

FPGA implementation of cost-effective robust canny edge detection algorithm

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2019年第4期16卷 957-970页

作者： Sangeetha, D. Deepa, P. Govt Coll Technol Dept Elect & Commun Engn Coimbatore 641013 Tamil Nadu India

Implementation of canny edge detection algorithm significantly outperforms the existing edge detection techniques in many computer vision algorithms. However, canny edge detection algorithm is complex, time-consuming process with high hardware cost. To overcome these issues, a novel canny edge detection algorithm is proposed in block level to detect edges without any loss. It uses sobel operator, approximation methods to compute gradient magnitude and orientation for replacing complex operations with reduced hardware cost, existing non-maximum suppression, block classification for adaptive thresholding and existing hysteresis thresholding. Pipelining is introduced to reduce latency. The proposed algorithm is implemented on Xilinx Virtex-5 FPGA and it provides better performance compared to frame-level canny edge detection algorithm. The synthesized architecture reduces execution time by 6.8% and utilizes less resource to detect edges of 512x512 image compared to existing distributed canny edge detection algorithm.

关键词： Image processing canny edge detection algorithm VLSI architecture FPGA Hardware-cost

来源：评论

学校读者我要写书评

暂无评论

Sub-Pixel edge detection algorithm Based on canny-Zernike Moment Method

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2020年第15期29卷

作者： Huang, Cheng Jin, Wei Xu, Qian Liu, Ziqi Xu, Zhiliang Nanjing Univ Sci & Technol Sch Automat Nanjing 210094 Peoples R China

In order to solve the problems of low efficiency and long running time caused by the traditional Zernike moment method for convolution calculation of the whole image, this paper combines the canny detection algorithm with the Zernike moment method. First, the canny edge detection algorithm, which combined with the Otsu threshold method, is used to extract the pixel edge of the image. Then an improved Hough transform method is used to fit the geometric edge in the image. Based on this, the Zernike moment method is applied to realize sub-pixel positioning of images. The algorithm improves the deficiencies of direct sub-pixel detection, improving accuracy and reducing running time. To verify the effectiveness of the proposed algorithm, the algorithm is applied to the dimension measurement experiment of T-type guide way. The results clearly show that the algorithm is superior to the traditional algorithm in accuracy.

关键词： Zernike moment sub-pixel canny edge detection algorithm Hough transform method

来源：评论

学校读者我要写书评

暂无评论

Detecting the authenticity of two monofloral honeys based on the canny-GoogLeNet deep learning network combined with three-dimensional fluorescence spectroscopy

引用

FOOD CHEMISTRY 2025年 485卷 144509页

作者： Ji, Shengkang Granato, Daniel Wang, Kai Hao, Shengyu Xuan, Hongzhuan Liaocheng Univ Sch Phys Sci & Informat Technol Liaocheng 252059 Peoples R China Univ Limerick Fac Sci & Engn Dept Biol Sci Bioact & Applicat Lab Limerick V94 T9PX Ireland Chinese Acad Agr Sci Inst Apicultural Res Beijing 100093 Peoples R China Liaocheng Univ Coll Agr & Biol Liaocheng 252059 Peoples R China

To determine the authenticity of honey, a deep learning network based on the canny-GoogLeNet architecture combined with three-dimensional (3D) fluorescence spectroscopy was established. The canny edge detection algorithm was used to extract 3D spectral data from two distinct monofloral honeys, rape honey and wolfberry honey, as well as adulterated honey samples with corn syrup or other types of honey. The dataset was divided into training (133 samples), validation (33 samples), and test sets (12 samples). The classical GoogLeNet architecture was enhanced by optimizing the inception module in Block 2, applying L2 regularization to the improved fully-connected layer, and implementing a monitoring training network model to reduce overfitting and enhance model robustness. The final model achieved approximately 100 % accuracy on the training set and 93.7 % accuracy on the validation set. These results indicate that integrating 3D fluorescence spectra with a CNN-based deep learning model has significant potential for authenticating honey.

关键词： Honey Authenticity Fluorescence spectroscopy canny edge detection algorithm Googlenet deep learning network

来源：评论

学校读者我要写书评

暂无评论

Mathematics and Computer Science Volume 2 1

引用

2023年

作者： Sharmistha Ghosh M. Niranjanamurthy Krishanu Deyasi Biswadip Basu Mallik Santanu Das

ISBN: (数字)9781119896715

ISBN: (纸本)9781119896326

MATHEMATICS AND COMPUTER SCIENCE This second volume in a new multi-volume set builds on the basic concepts and fundamentals laid out in the previous volume, presenting the reader with more advanced and cutting-edge topics being developed in this exciting field. This second volume in a new series from Wiley-Scrivener is the first of its kind to present scientific and technological innovations by leading academicians, eminent researchers, and experts around the world in the areas of mathematical sciences and computing. Building on what was presented in volume one, the chapters focus on more advanced topics in computer science, mathematics, and where the two intersect to create value for end users through practical applications. The chapters herein cover scientific advancements across a diversified spectrum that includes differential as well as integral equations with applications, computational fluid dynamics, nanofluids, network theory and optimization, control theory, machine learning and artificial intelligence, big data analytics, Internet of Things, cryptography, fuzzy automata, statistics, and many more. Readers of this book will get access to diverse ideas and innovations in the field of computing together with its growing interactions in various fields of mathematics. Whether for the engineer, scientist, student, academic, or other industry professional, this is a must-have for any library.

关键词： Blockchain Innovation Brain Tumors canny edge detection algorithm Chemical Reaction Computational Fluid Dynamics COVID Cryptography Cryptosystems Data Visualization Database Decryption Directional-gradient of Depth function (D-GoD) Discrete Wavelet Transform

来源：评论

学校读者我要写书评

暂无评论

Mathematics and Computer Science Volume 1 1

引用

2023年

作者： Sharmistha Ghosh M. Niranjanamurthy Krishanu Deyasi Biswadip Basu Mallik Santanu Das

ISBN: (数字)9781119879831

ISBN: (纸本)9781119879671

MATHEMATICS AND COMPUTER SCIENCE This first volume in a new multi-volume set gives readers the basic concepts and applications for diverse ideas and innovations in the field of computing together with its growing interactions with mathematics. This new edited volume from Wiley-Scrivener is the first of its kind to present scientific and technological innovations by leading academicians, eminent researchers, and experts around the world in the areas of mathematical sciences and computing. The chapters focus on recent advances in computer science, and mathematics, and where the two intersect to create value for end users through practical applications of the theory. The chapters herein cover scientific advancements across a diversified spectrum that includes differential as well as integral equations with applications, computational fluid dynamics, nanofluids, network theory and optimization, control theory, machine learning and artificial intelligence, big data analytics, Internet of Things, cryptography, fuzzy automata, statistics, and many more. Readers of this book will get access to diverse ideas and innovations in the field of computing together with its growing interactions in various fields of mathematics. Whether for the engineer, scientist, student, academic, or other industry professional, this is a must-have for any library.

关键词： Blockchain Innovation Brain Tumors canny edge detection algorithm Chemical Reaction Computational Fluid Dynamics COVID Cryptography Cryptosystems Data Visualization Database

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Location algorithm for Rubber tapping robot 41

Design and Implementation of Location Algorithm for Rubber t...

引用

第41届中国控制会议

作者： Mingxiu Lin Bingge Yu Feng Pan Northeastern University College of Information Science and Engineering

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In recent years,new agricultural production methods and rapidly developing new technologies have promoted the development of agricultural equipment,giving birth to intelligent equipment and agricultural *** robots have great advantages in improving rubber *** at the problem of robot-based navigation and positioning and rubber tree incision recognition,a set of SLAM system based on lidar is designed,which is mounted on the robot to realize navigation and positioning,and uses the combination of monocular and binocular cameras to identify the incision and realize the position of the *** the design of system algorithms such as sensor data reading and motion control,the robot navigation adopts the optimized SLAM *** robot's position and direction are determined through the combination of the GPS positioning module and the IMU inertial navigation module,and the rubber tree positioning is realized through the A* *** incision recognition adopts the canny edge detection algorithm,color detection,artificial marking and other methods to realize the local positioning of the rubber tree rubber tapping *** comparative experiments were carried out in this *** to the analysis of the experimental results,it is verified that the system has achieved the expected goals,and has the characteristics of good accuracy and high real-time performance,which provides a reference for the research and application of robots in the field of rubber tapping.

关键词： navigation and positioning monocular camera canny edge detection algorithm color detection

来源：评论

学校读者我要写书评

暂无评论

Salvaging tumor from T1-weighted CE-MR images using automatic segmentation techniques

引用

International Journal of Information Technology (Singapore) 2022年第4期14卷 1869-1874页

作者： Saraswat, Amar Sharma, Neeta Department of CSE/ IT Noida International University Greater Noida India

When there exists a massive growth of abnormal cells inside the human brain, it is called as Brain Tumour. One of the major challenges in Content Based Image Retrieval (CBIR) is the semantic gap, which is extraction of the information between the human evaluator and Magnetic Resonance Imaging (MRI) machines. In the present scenario, the radiologist manually checks for the tumour region segmentation and outlines of that region. This problem can be reduced, if we combine the high-level and low-level feature extraction. In the proposed work, this gap is being bridged out, by using deep learning feature extraction technique over T1-weighted Contrast Enhanced-Magnetic Resonance (CE-MR) images along with canny edge, Gradient Descent Cost Minimization, Loss function evaluation and measurement of similarity through distribution vector and closed form metric learning as an automation segmentation technique to obtain the more precise accuracy. Also, the mean accuracy precision determined by the proposed model is 94.6% for the several query images sets. By this, manual efforts could be minimized in identifying the granular details of the tumours present in the several parts of the brain by employing MR images. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： canny edge detection algorithm Content Based Image Retrieval (CBIR) Contrast Enhanced-Magnetic Resonance (CE-MR) images Magnetic Resonance Imaging (MRI) Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Design of canny edge detection Hardware Accelerator Using xfOpenCV Library 3rd

Design of Canny Edge Detection Hardware Accelerator Using xf...

引用

International Conference on Computational Vision and Bio-Inspired Computing (ICCVBIC)

作者： Vashist, Lokender Kumar, Mukesh Natl Inst Technol Kurukshetra Kurukshetra 136119 Haryana India

ISBN: (纸本)9783030372187;9783030372170

Real time image processing using CPU takes more computational power and thereby processing speed also decreases. FPGA with its parallel processing capability does complex processes with much more speed and less power consumption sharing load of CPU hence it can be used for edge detection in real time where large number of pixels are to be processed. In this paper we developed programmable logic for canny edge detection algorithm intended for Zynq 7000 based Zybo board. xfOpenCV library is used to generate the hardware logic for algorithm after application of a wrapper function so as to make it portable with AXI stream interface of Zynq device. Better edges are detected even for noisy image using xfOpenCV library. Resources utilization of FPGA are very less thus the edge detection done using Zynq 7000 device will be 100x faster and more reliable then CPU's

关键词： xfOpenCV library Vivado HLS canny edge detection algorithm Zybo board

来源：评论

学校读者我要写书评

暂无评论

Research on Improved algorithm of Infrared Image edge detection for Electrical Equipment

Research on Improved Algorithm of Infrared Image Edge Detect...

引用

Chinese Automation Congress (CAC)

作者： Zhao, Lihong Gao, Qiang Yu, Xiao Song, Yu Tianjin Univ Technol Tianjin Key Lab Control Theory & Applicat Complic Tianjin Peoples R China

ISBN: (纸本)9781728176871

In order to diagnose the thermal anomaly of electrical equipment in time, an improved canny edge detection algorithm for infrared image of electrical equipment is proposed to facilitate fault location. To improve the dexterity and adaptive ability of canny edge detection algorithm, wavelet transform and improved homomorphism are used Instead of Gauss filter, the filtering algorithm can denoise the image, reduce the influence of noise and light, keep the edge intensity and details;improve Sobel operator, increase the gradient amplitude in 45 degrees and 135 degrees directions, so as to improve the edge positioning effect;use non maximum suppression to refine the image, and use Otsu algorithm according to the image gray level to adaptively obtain high and low thresholds, and use high and low thresholds Value algorithm detects and connects edges. Through the image verification of electrical equipment, the experimental data shows that the improved algorithm has better detection accuracy and stronger adaptability than canny edge detection algorithm.

关键词： Infrared image of electrical equipment canny edge detection algorithm Improved homomorphic filtering Improved Sobel operator

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

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

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：