检索结果-内蒙古大学图书馆

Lightweight Plant Disease Classification Combining grabcut algorithm, New Coordinate Attention, and Channel Pruning

NEURAL PROCESSING LETTERS 2022年第6期54卷 5317-5331页

作者： Qi, Fang Wang, Yongle Tang, Zhe Cent South Univ Sch Comp Sci Changsha 410083 Hunan Peoples R China

In this paper, a lightweight convolutional neural network is proposed for the classification of plant diseases, containing 63 classes of states for 11 plant species. The different context of experimental data and data in the real environment, insufficient accuracy of the model classification, and oversized model are three main problems of deep learning techniques applied to agricultural production. In this paper, we mainly focus on these three problems. First, the grabcut algorithm is adopted to unify the background of the experimental data and the real data to black, allowing the trained model to have the same good effect when applied in practice. Then, we propose a new coordinate attention block to improve the classification accuracy of convolutional neural networks and empirically demonstrate the effectiveness of our approach with several state-of-the-art CNN models. Finally, channel pruning is applied to the trained model, which reduces the model size and computational effort by 85.19% and 92.15% respectively with little change in the model accuracy, making it better suited for agricultural platforms with lower memory and computational capacity.

关键词： Convolutional neural networks Plant diseases grabcut algorithm New coordinate attention block Channel pruning

来源：评论

学校读者我要写书评

暂无评论

grabcut algorithm for dental X-ray images based on full threshold segmentation

引用

IET IMAGE PROCESSING 2018年第12期12卷 2330-2335页

作者： Mao, Jiafa Wang, Kaihui Hu, Yahong Sheng, Weiguo Feng, Qixin Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Zhejiang Peoples R China Hangzhou Normal Univ Dept Comp Sci Hangzhou 311121 Zhejiang Peoples R China Chinese Acad Sci Xinjiang Inst Ecol & Geog Urumqi 830011 Xinjiang Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Teeth are difficult to be destroyed due to their corrosion resistance, high melting point and hardness. Dental biometrics can therefore provide assistance in human forensic identification, especially to the unknown corpses. One of the key issue in dental based human identification is the segmentation of Dental X-ray images. In this paper, a novel segmentation algorithm has been proposed for this purpose. The proposed algorithm is based on full threshold segmentation. We first obtain the outline image set Iwhole(n) and crown image set Icrown(m) of the complete target tooth. Morphological open operation is then applied to the difference images of Iwhole(n) and Icrown(m). Subsequently, the most complete target tooth image and its corresponding crown image are selected. Getting independent target tooth image I-contour and its crown image I-crown from these two images. Median filtering is applied to the synthetic image of I-contour and I-crown, and the resulted image will be used as the Mask for grabcut to obtain the target tooth image. Experimental results show our proposed algorithm can effectively overcome the problems of uneven grayscale distribution and adhesion of adjacent crowns in dental X-ray images. It can also achieve a high segmentation accuracy and outperform related methods to be compared.

关键词： feature extraction biometrics (access control) dentistry medical image processing image segmentation grabcut algorithm dental X-ray images threshold segmentation high melting point hardness dental biometrics human forensic identification dental-based human identification novel segmentation algorithm difference images complete target tooth image corresponding crown image independent target tooth shape image synthetic image resulted image adjacent dental crowns high segmentation accuracy outline image set median filtering morphological open operation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Skin Cancer Diagnosis: A Modified Ensemble Convolutional Neural Network for Classification

引用

MICROSCOPY RESEARCH AND TECHNIQUE 2025年第6期88卷 1681-1700页

作者： Vidhyalakshmi, A. M. Kanchana, M. SRM Inst Sci & Technol Dept Comp Technol Kattankulathur Tamilnadu India

Skin cancer is recognized as one of the most harmful cancers worldwide. Early detection of this cancer is an effective measure for treating the disease efficiently. Traditional skin cancer detection methods face scalability challenges and overfitting issues. To address these complexities, this study proposes a random cat swarm optimization (CSO)with an ensemble convolutional neural network (RCS-ECNN) method to categorize the different stages of skin cancer. In this study, two deep learning classifiers, deep neural network (DNN) and Keras DNN (KDNN), are utilized to identify the stages of skin cancer. In this method, an effective preprocessing phase is presented to simplify the classification process. The optimal features are selected using the feature extraction phase. Then, the grabcut algorithm is employed to carry out the segmentation process. Also, the CSO is employed to enhance the effectiveness of the method. The HAM10000 and ISIC datasets are utilized to evaluate the RCS-ECNN method. The RCS-ECNN method achieved an accuracy of 99.56%, a recall of 99.66%, a specificity value of 99.254%, a precision value of 99.18%, and an F1-score value of 98.545%, respectively. The experimental results demonstrated that the RCS-ECNN method outperforms the existing techniques.

关键词： cat swarm optimization deep neural network grabcut algorithm Keras deep neural network skin cancer

来源：评论

学校读者我要写书评

暂无评论

A training-free machine learning approach for 3D powder bed reconstruction and defect detection in PBF-LB/M

引用

PROGRESS IN ADDITIVE MANUFACTURING 2025年 1-25页

作者： Tosoratti, Enrico Potthoff, Ugne Bennewitz, Christopher Bambach, Markus Inspire AG Innovat Ctr Addit Mfg Switzerland CH-9014 St Gallen Switzerland Swiss Fed Inst Technol Adv Mfg Lab D MAVT Technoparkstr 1 CH-8005 Zurich Switzerland

We introduce a novel in situ quality monitoring approach for the Laser Powder Bed Fusion (PBF-LB/M) process that operates independently of prior experimental data and can be integrated into existing systems. We employ a cost-effective, high-resolution CMOS camera coupled with a bright and darkfield lighting arrangement to acquire data layer-by-layer. Using computer vision techniques, specifically the grabcut algorithm, we automate the inspection and the virtual reconstruction of fused part geometries. Our results, compared with nominal slice data and computed tomography scan data, indicate a robust accuracy in quantifying geometric deviations (mean deviation of 15.60 mu\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\upmu$$\end{document}m and 15.20 mu\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\upmu$$\end{document}m respectively, Jaccard scores of 0.99). The proposed training-free framework, unlike traditional machine learning methods, requires no labeled datasets or prior training, offering a cost-effective and adaptable solution. This eliminates the dependency on material, scan strategy, or part geometry, which typically hinders the scalability of conventional approaches. Additionally, our method facilitates automatic defect detection such as recoater strikes, recoater hopping, and powder shortages, with balanced accuracy scores of up to 0.87. These advantages highlight the framework's potential as a practical tool for in situ process monitoring and quality assurance in PBF-LB/M systems.

关键词： PBF-LB/M Powder bed quality inspection Fused part geometry inspection Image segmentation Computer vision grabcut algorithm

来源：评论

学校读者我要写书评

暂无评论

An efficient hybrid bert model for brain tumor classification

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2024年第3期46卷 7241-7258页

作者： Kumar, S. Selvin Prem Kumar, C. Agees Venugopal, Anita Sharma, Aditi CSI Inst Technol Dept Comp Sci & Engn Thovalai India Arunachala Coll Engn Women Dept Elect & Elect Engn Vellichanthai India Dhofar Univ IT Unit Salalah Oman Symbiosis Int Symbiosis Inst Technol Dept Comp Sci & Engn Pune Maharashtra India

The central nervous system can develop complex and deadly neoplastic growths called brain tumors. Despite being relatively uncommon in comparison to other cancers, brain tumors pose particular challenges because of their delicate anatomical placement and interactions with critical brain regions. The data are taken from TCIA (The Cancer Image Archive) and Kaggle Datasets. Images are first pre-processed using amplified median filter techniques. The pre-processed images are then segmented using the grabcut method. Feature extraction is extracted using the Shape, ABCD rule, and GLCM are the features were retrieved. The MRI images are then classified into several classes using the Bi-directional Encoder Representations from Transformers-Bidirectional Long Short Term Memory (BERT-Bi-LSTM) model. Kaggle and TICA datasets are used to simulate the proposed approach, and the results are evaluated in terms of F1-score, recall, precision and accuracy. The proposed model shows improved brain tumour identification and classification. To evaluate the expected technique's efficacy, a thorough comparison of the current techniques with preceding methods is made. The trial results showed that an efficient hybrid bert model for brain tumor classification suggested strategy provided precision of 98.65%, F1-score of 98.25%, recall of 99.25%, and accuracy of 99.75%.

关键词： Brain tumor BERT Bi-LSTM grabcut algorithm classification feature extraction

来源：评论

学校读者我要写书评

暂无评论

Optimization integrated generative adversarial network for occluded text recognition with language modeling

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2023年第8期35卷

作者： Selvaraj, Selvin Ebenezer Tripuraribhatla, Raghuveera Anna Univ Coll Engn Dept Comp Sci & Engn Guindy Campus Chennai India

Text recognition has attracted increased attention recently as a result of the complexity of natural settings and the variety of text instances. Various text or character recognition methods are introduced to distinguish the text from the natural scene, but existing methods struggle with the distorted and highly curved text instances. Consequently, an effective method for occluded text or character detection from object-background images is developed using the suggested elephant herding exponential sailfish optimizer-based generative adversarial network (EHESFO-based GAN). In order to build the proposed EHESFO, elephant herding optimization and Exponential SailFish Optimizer (ESFO) are merged. ESFO was created by fusing exponentially weighted moving average and SailFish Optimizer. With GAN, features extracted from the background and foreground of an image are efficiently used for image annotation and text recognition. The best features from the background and foreground images are extracted to create the optimal solution, which increases the efficacy and efficiency of text recognition. While taking the occlusion as 0.4, the proposed EHESFO-based GAN achieved higher accuracy of 98.1090% and lower error of 1.4%.

关键词： generative adversarial network (GAN) grabcut algorithm image annotation language modeling text recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic Segmentation algorithm of Ultrasound Heart Image Based on Convolutional Neural Network and Image Saliency

引用

IEEE ACCESS 2020年 8卷 104445-104457页

作者： Liu, Hui Chu, Wen Wang, Hua Zhengzhou Univ Luoyang Cent Hosp Luoyang 471000 Peoples R China

The emergence of 4D heart images makes the data volume of the images multiply. It is more urgent to require an effective and fast segmentation algorithm. Therefore, a heart image can be accurately segmented from a large amount of image data and an area of interest can be extracted The segmentation algorithm is very necessary. Based on the segmentation and recognition of medical images, this paper proposes a neural network and image saliency based on the obvious difference between the heart image and other tissues in the slice, and the high similarity between adjacent slices in the CT image sequence. Fully automatic segmentation algorithm and 3D visual reconstruction is the segmented heart image. Convolutional neural network is a special deep neural network model of artificial intelligence. Its connections between neurons are not fully connected. The weights of connections between certain neurons in the same layer are shared, and the network model is reduced. The complexity reduces the number of weights. The use of visual saliency techniques to achieve cardiac segmentation based on CT images. An image saliency detection algorithm is adopted to introduce the image segmentation algorithm based on the saliency technique. In this paper, considering the PET image as grayscale image with low resolution, an improved Itti model and an improved grabcut image segmentation algorithm are proposed to solve the problem of the original algorithm in grayscale image. At the same time, the operation steps of the user division area are cancelled, and the automatic processing is realized, and the running time of the algorithm is improved while optimizing the image segmentation effect. The convolutional neural network is constructed to realize the positioning function of the heart in the image. The original cardiac CT image is cropped by the positioning result, and some non-target areas are removed. A stacking noise reduction self-coding network is constructed, and the network is manuall

关键词： Convolutional neural network Itti model grabcut algorithm heart segmentation image saliency stacking noise reduction self-coding network

来源：评论

学校读者我要写书评

暂无评论

Fiber Distribution Identification of Blended Yarns Based on Image Processing

Fiber Distribution Identification of Blended Yarns Based on ...

引用

作者： Xiu-Wen Yuan Qiong-Xin Huang Xin-Ping Lu Bin-Jie Xin Ying-Qi Xu Fashion School Shanghai University of Engineering Science

To study the distributions of four kinds of fibers meta-aramid,poly(phenylene-1,3,4-oxadiazole)(POD),flameretardant viscose,and flame-retardant vinylon in the flame-retardant yarn,this paper discussed the preparation method of the cross-section of flame-retardant multi-fiber blended *** to the characteristics of each component of flame-retardant blended yarn,the blended yarn was dyed via a two-bath two-step method with Argazol Red NF-3B and Cationic Blue *** the surface of the fiber was modified by the STR/I Plasma treatment *** embedding with resin,and sectioning with KD-202 Hand-operated Slicer,the crosssection image of the blended yarn was obtained by CX41RF Microscope(×400).By using the BP neural network model and the grabcut algorithm,the fibers were separated from the background,and the distribution of the fibers for each component of the flame-retardant blended yarn is *** results show that the crosssection image of flame-retardant blended yarn can be obtained quickly and easily using this method,and the distribution of each component fiber can be identified with the computer system.

关键词： Blend Yarn Fiber Identification BP Neural Network Image Processing grabcut algorithm

来源：评论

学校读者我要写书评

暂无评论

A method for measuring the width of welding seam based on machine vision

A method for measuring the width of welding seam based on ma...

引用

Applied Optics and Photonics China (AOPC) Conference - Optics Ultra Precision Manufacturing and Testing

作者： Jin Wei Sun Hai-bin Adv Laser Technol Lab Anhui Prov Hefei 230037 Peoples R China Natl Univ Def Technol State Key Lab Pulsed Power Laser Technol Hefei 230037 Peoples R China Key Lab Infrared & Low Temp Plasma Anhui Prov Hefei 230037 Peoples R China Chinese Peoples Liberat Army Unit 96871 Baoji 721012 Peoples R China

ISBN: (纸本)9781510639584

Aiming at the problems of low measurement efficiency and large measurement error when manually measuring the width of the welding seam using the welding seam ruler, a method for measuring the width of the weld seam based on machine vision was proposed in this paper. Firstly, the hardware of the measuring device was designed. The hardware included a measurement platform, an image acquisition and control module, a computer. One motor guide, one stepper motor, an industrial camera and a lighting source were installed on the measurement platform. Secondly, based on Matlab + OpenCV, the measurement software was developed. The software included five functions: controlling the stepper motor and the lighting source, receiving weld seam images, preprocessing the images, segmenting images, correcting images and calculating the width of the weld seam. The image segmentation was implemented by grabcut algorithm, which could extract the weld area very well. The calculation of the weld width was based on the imaging size and resolution of the industrial camera and the pixels positions on the upper and lower edges of the weld area. Finally, a measurement experiment was carried out on the width of the weld. According to the measurement results, the measurement accuracy of the width of the welding seam reached to 0.1 mm and the measurement speed reached to 30.7 mm / s. The results showed that measuring the width of the welding seam based on machine vision could replace manual measurement and be applied to industrial automation.

关键词： machine vision the width of welding seam measurement grabcut algorithm

来源：评论

学校读者我要写书评

暂无评论

Effective segmentations in white blood cell images using ε-SVR-based detection method

引用

NEURAL COMPUTING & APPLICATIONS 2019年第10期31卷 6767-6780页

作者： Cao, Feilong Liu, Yuehua Huang, Zhen Chu, Jianjun Zhao, Jianwei China Jiliang Univ Dept Appl Math Coll Sci Hangzhou 310018 Zhejiang Peoples R China Jiashan Jasdaq Med Device Co Ltd Jiashan 314100 Zhejiang Peoples R China

White blood cell (WBC) image detection plays an important role in automatic morphological systems since it can simplify and facilitate WBC segmentation and classification procedures. However, existing WBC detection methods mainly rely on the location of the nucleus, which is found difficult to achieve accurate detection results. This paper proposes a novel WBC detection algorithm through sliding windows with varying sizes to traverse the image for candidates. Three cues are explored to measure the candidates, and a combined cue is used as a single output to distinguish positives from negatives. The epsilon-support vector regression is employed to determine the detection window from the candidates. In this paper, two applications of the proposed WBC detection approach are carried out, including an adaptive thresholding algorithm based on WBC detection for nucleus segmentation from images and target detection to lessen the users' interaction for automatic cytoplasm segmentation.

关键词： White blood cell (WBC) image Detection Segmentation Support vector regression grabcut algorithm

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：