检索结果-内蒙古大学图书馆

4th IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Wang, Yujie Huang, Langbing Zhang, Yanli Sun, Tang Guangdong Maoming Agriculture & Forestry Technical College Maoming China

ISBN: (纸本)9798350363586

Aiming at the problem that a single feature cannot accurately describe plant leaves, a plant leaf recognition method based on multi-feature fusion is proposed in this paper. In view of the local binary pattern feature extraction method and two improved algorithms, considering implications of multi-neighborhood pixels toward middle pixel, a new mixed weighted neighboring local binary pattern texture descriptor is constructed, and the histogram of oriented gradient feature is fused to gain a more detailed leaf feature description vector. Finally, the experimental results on the open Flavia data set show that the proposed method can obtain good experimental results. © 2024 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Innovative Solutions: LBPH Technology Driving the Future of Intelligent Security Systems 2

Innovative Solutions: LBPH Technology Driving the Future of ...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Rao, Manjula Gururaj Rashmitha, S.K. Sanjana, R.H. Prabhu, Shrigowri Noronha, Shaun Paul, Shaun Karkala India

ISBN: (纸本)9798350383287

In today's organisations, attendance is crucial for confirming a person's dedication, presence, and ability to spot unauthorised access. Historically, roll calls or signatures have been used to manually record attendance. But in the age of digitalization, facial recognition presents a state-of-the-art approach to tracking attendance. This technique analyses a person's facial traits to verify their identity. This model performs image extraction and other crucial tasks by utilising the local binary pattern Histogram (LBPH) approach. Following identification, the system records the date, time, and names of those who have been identified into an Excel file. The unauthorised entry is likewise recognised and mentioned in the proposed approach. This model is remarkably capable of detecting numerous faces at once, which simplifies the attendance process. It's especially helpful in congested circumstances because it can distinguish between duplicate items. Consequently, there is far less reliance on manual attendance systems. The proposed model can identify attendance in a multi-face detection environment with 98% accuracy, granting security access to the premises. © 2024 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Fast and effective pedestrian detection based on low-level visual features combination

引用

JOURNAL OF ELECTRONIC IMAGING 2022年第4期31卷 043004-043004页

作者： Qaid, Tawfik M. A. Loukil, Abdelhamid El Boudadi, Lahouari Kaddour Mohammed, Adam A. Q. Univ Sci & Technol Oran Mohamed Boudiaf Fac Elect Engn Embedded Syst & Microsyst Lab Oran Algeria Univ Sci & Technol Oran Mohamed Boudiaf Fac Elect Engn Intelligent Syst Res Lab Oran Algeria Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China

Automatic pedestrian detection is a crucial task for intelligent vehicles as it helps avoid car-to-pedestrian accidents. Recently, several approaches have been proposed to improve detection accuracy, such as the channel-based family, which is based on the aggregation of channel features (e.g., HOG + LUV) to represent the shape of pedestrians. Previous handcrafted-based detectors significantly improved the detection performance by applying different filters to channel features. However, when there are similar-looking background objects, their detection performance suffers due to the lack of texture features. Another drawback of these approaches lies in their high computational cost, limiting their use for real-world applications, especially for resource constrained systems. To mitigate these drawbacks while maintaining a distinguishable detection accuracy, we propose a method that combines a simple but effective texture descriptor based on local binary patterns with HOG + LUV. The concatenated features are used to train a boosted decision trees classifier. To evaluate our approach, we carried out extensive experiments on four well-known datasets, including INRIA, ETH, KITTI, and Caltech. Experimental results show that the proposed method achieves a competitive performance to the channel-based detectors with significantly lower computational cost;it runs at 91.64 and 6.08 times faster than the closest competitors detectors on the INRIA and Caltech datasets, respectively. Furthermore, it outperforms these methods when evaluating under the corrected annotations of the Caltech dataset.

关键词： pedestrian detection channel features local binary pattern intelligent vehicles

来源：评论

学校读者我要写书评

暂无评论

Iris Recognition using Multi Objective Artificial Bee Colony Optimization Algorithm with Autoencoder Classifier

引用

NEURAL PROCESSING LETTERS 2022年第4期54卷 3489-3505页

作者： Sheela, S., V Radhika, K. R. BMS Coll Engn Dept Informat Sci & Engn Bangalore Karnataka India

In recent decades, iris recognition is a trustworthy and important biometric model for human recognition. Criminal to commercial products, citizen confirmation and border control are few application areas. The research work is a deep learning based integrated model for accurate iris detection and recognition. Initially, eye images are considered from two datasets, the Chinese Academy of Sciences Institute of Automation (CASIA) and the Indian Institute of Technology (IIT) Delhi v1.0. Iris region is accurately segmented using Daugman's algorithm and Circular Hough Transform (CHT). Feature extraction is hybrid that is performed using Dual Tree Complex Wavelet Transform (DTCWT), Gabor filter, local binary pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) from the segmented iris regions. A Multiobjective Artificial Bee Colony (MABC) algorithm is proposed to eliminate noisy and redundant feature vectors by estimating consistent information. In MABC algorithm, two multi-objective functions are formulated as reduction in number of features and classification error rate. The selected active feature vectors are given as input to autoencoder classification for iris recognition. The experimental outcome shows that MABC-autoencoder model obtained 99.67% and 98.73% accuracy on CASIA-Iris, and IIT Delhi v1.0 iris datasets. Performance evaluation is based on accuracy, specificity, Critical Success Index (CSI), sensitivity, Fowlkes Mallows (FM) index, and Mathews Correlation Coefficient (MCC).

关键词： Autoencoder Circular Hough transform Daugman's algorithm Iris recognition local binary pattern Multi objective artificial bee colony

来源：评论

学校读者我要写书评

暂无评论

Inferior alveolar nerve canal segmentation by local features based neural network model

引用

IET IMAGE PROCESSING 2022年第3期16卷 703-716页

作者： Maheswari, P. Uma Banumathi, A. Ulaganathan, G. Yoganandha, R. Thiagarajar Coll Engn Dept ECE Madurai Tamil Nadu India CSI Coll Dent Sci & Res Dept Oral & Maxillofacial Surg Madurai Tamil Nadu India Velammal Med Coll Hosp & Res Inst Dept Craniofacial Surg Dent & Implantol Madurai 15 Tamil Nadu India

The detection of Inferior Alveolar Nerve Canal (IAC) plays major and crucial role in dental surgical procedures to avoid damage to IAC during the course of treatment. Exact visualization and detection of IAC is necessary for precise surgery planning to prevent IAC damage. The proposed method comprises of three stages namely, novel edge enhancement, candidate classification and candidate pixel clustering to detect the IAC. For better visualization of IAC, initially the edges of dental OPG images are enhanced using a novel structural filter. Candidate regions are selected from the enhanced image by the proposed Multi Hidden Layer Extreme Learning Machine Artificial Neural Network (MELMANN) model driven by combined regional features such as Histogram of Gradients (HOG), local binary pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM). Consequently the candidate region pixels are clustered by a Self-Organising Map-based Neural Network (SOM - NNC) along with active contour method to detect the IAC completely. Experimental results show that this method effectively delineated the IAC with the Dice coefficient of 0.854 +/- ***, the proposed method has high potential in clearly visualizing IAC to avoid neurological sensory disorders in oral and maxillofacial surgery and implantology and it provides better prediagnostic approach to the surgeons.

关键词： pattern clustering oral surgery surgery planning LBP GLCM neurophysiology gray level cooccurrence matrix MELMANN model structural filter candidate region pixels orthopantomogram regional features IAC visualization HOG candidate classification dental OPG image enhancement inferior alveolar nerve canal segmentation edge detection oral implantology local features based neural network model dentistry SOM-NNC feature extraction image filtering feedforward neural nets image segmentation candidate pixel clustering neurological sensory disorders image enhancement local binary pattern data visualisation computer vision surgery histogram of gradients diagnostic radiography medical image processing dental surgical procedure edge enhancement object detection self-organising feature maps IAC damage prevention self-organising map-based neural network IAC detection maxillofacial surgery active contour method image classification Dice coefficient multihidden layer extreme learning machine artificial neural network model

来源：评论

学校读者我要写书评

暂无评论

WLBP: Weber local binary pattern for local image description

引用

NEUROCOMPUTING 2013年 120卷 325-335页

作者： Liu, Fan Tang, Zhenmin Tang, Jinhui Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing 210094 Jiangsu Peoples R China

In this paper, we propose a local descriptor, called Weber local binary pattern (WLBP1), which effectively combines the advantages of WLD and LBP. Specifically, WLBP consists of two components: differential excitation and LBP. The differential excitation extracts perception features by Weber's law, while the LBP (local binary pattern) can describe local features splendidly. By computing the two components, we obtain wo images: differential excitation image and LBP image, from which a WLBP histogram is constructed. The differential excitation was extended by bringing in Laplacian of Gaussian (LoG), which makes WLBP robust to noise. By designing a new quantization method, the discriminabilty of WLBP was enhanced. The proposed method is evaluated on the face recognition problem under different challenges. Experimental results show that WLBP performs better than WLD and LBP. Meanwhile, it is robust to time, facial expressions, lightings, pose and noise. We also conduct experiments on Brodatz and KTH-TIPS2-a texture databases, which demonstrate that WLBP is a powerful texture descriptor. (c) 2013 Elsevier B.V. All rights reserved.

关键词： local binary pattern Weber's law Differential excitation Face recognition Texture classification

来源：评论

学校读者我要写书评

暂无评论

An effective edge extraction method using improved local binary pattern for blurry digital radiography images

引用

NDT & E INTERNATIONAL 2013年第1期53卷 26-30页

作者： Bi, Bi Zeng, Li Shen, Kuan Jiang, Haina Chongqing Univ ICT Res Ctr Key Lab Optoelect Technol & Syst Educ Minist China Chongqing 400044 Peoples R China Chongqing Univ Coll Optoelect Engn Chongqing 400044 Peoples R China Chongqing Univ Coll Math & Stat Chongqing 401331 Peoples R China

Aiming at an efficient edge extraction method for blurry digital radiography (DR) image of large size, local binary pattern (LBP) is improved by embedding an H function and a counting scheme, so-called H-LBP. With the aid of similarity distance and the H function, H-LBP can extract surrounding information discriminatively. With the help of counting scheme that records the number of pixels whose values are equal to or greater than that of the centric one, H-LBP can reduce noises and blurring. Experiments on blurry DR images and other images show that, compared with the Canny method, a fusion method called FL-fusion in this paper, and LBP operator, H-LBP extracts edges containing much more details. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Digital radiography Edge extraction local binary pattern H function Counting scheme

来源：评论

学校读者我要写书评

暂无评论

Facial Features based Recognition System using LBPH and AdaBoost 5

Facial Features based Recognition System using LBPH and AdaB...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Srivastava, Mayank Khatiyan, Kalash Dixit, Pratibha Gla University Department of Computer Engineering & Applications UP Mathura India

ISBN: (纸本)9798331504403

Face recognition stands as a pivotal domain within computer vision, boasting myriad applications in security, identification, and biometrics. This research study proposes a face recognition system using image processing techniques with the combination of two algorithms, local binary pattern Histogram (LBPH) and AdaBoost. The LBPH algorithm was used to extract features from the images and create a feature vector for each face. The AdaBoost algorithm was then used to train a classifier on the feature vectors and classify new faces. After testing on the Face Recognition Database, the results reveal that the fusion of LBPH and AdaBoost algorithms achieves an impressive accuracy rate of 96.15% which is better as compared to other similar algorithms. The proposed algorithm is implemented in Python to recognize faces in a dataset of images. © 2024 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Enhancing Contour Features of Tissue Cell Images Based on Fluorescence in Situ Hybridization

An Algorithm for Enhancing Contour Features of Tissue Cell I...

引用

2024 IEEE International Conference on Manipulation, Manufacturing and Measurement on the Nanoscale, 3M-NANO 2024

作者： Song, Dianxin Gong, Ping Zhang, Yue Changchun University of Science and Technology School of Life Science and Technology Changchun China

ISBN: (纸本)9798350362107

With the widespread application of computer technology in medical image processing, preprocessing fluorescence in situ hybridization (FISH) tissue cell images with complex structures to obtain clear contour features is crucial to ensure the effectiveness of artificial intelligence models. Clear image contour features directly affect the performance of artificial intelligence models. Therefore, in-depth research was conducted on how to enhance the contour feature information of complex FISH tissue cell images, and improvements were made based on existing algorithms. An image contour enhancement method combining image illumination and an improved local binary pattern (LBP) algorithm is proposed. This method uses an illumination enhancement algorithm to improve the overall distribution of image brightness, and then uses an improved local binary pattern algorithm to quickly extract the contour features of the image, and weights the extracted features into the illumination-enhanced image to obtain an image with enhanced contour features. Finally, areas with high energy gradients are identified through piecewise linear functions and heat maps, which effectively filter out areas with low energy gradients. The high-frequency signal areas are the outline areas of FISH tissue cell images. Experimental analysis verified the effectiveness of this method in image enhancement. © 2024 IEEE.

关键词： local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Hybrid Restricted Boltzmann Machine- Convolutional Neural Network Model for Image Recognition

引用

IEEE ACCESS 2022年 10卷 24985-24994页

作者： Sobczak, Szymon Kapela, Rafal Poznan Univ Tech Inst Automat Control & Robot PL-60965 Poznan Poland

Convolutional Neural Networks (CNNs) have become a standard approach to many image processing dilemmas. Consequently, most of the proposed CNN architectures tend to increase the model deepness or layer complexity. Thus, they are composed of many parameters and need considerable computing resources and training examples. However, some recent works show that either shallow neural networks or architectures without convolutions can achieve similar results with these models often being used in systems with limited resources. Consideration of these aspects led us to a relatively simple preprocessing layer that increases the accuracy of CNN or may reduce its complexity. The layer is composed of two parts: the first is used to transform RGB data to binary representation, the second is a neural network that transforms the binary data into a multi-channel, real-value matrix and is trained in a fully unsupervised manner. Our proposal also includes a metric that may be used for measuring the similarity of training data, with the latter proving useful when performing transfer learning. Our experiments show that the resulting architecture not only helps to improve accuracy but is also more robust to image noise, including adversarial attacks, when compared to state-of-the-art models.

关键词： Computational modeling Image color analysis Data models Training Computer architecture Task analysis Complexity theory Artificial intelligence binary patterns deep learning local binary pattern image recognition restricted Boltzmann machine

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：