检索结果-内蒙古大学图书馆

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Bönhof, Berenice N. Hanne, Thomas Dornberger, Rolf Gachnang, Phillip Bönhof, Gidon J. School of Business University of Applied Sciences and Arts Northwestern Switzerland Basel Switzerland Vetsuisse-Faculty Institute of Veterinary Pharmacology and Toxicology University of Zurich Zurich Switzerland Institute for Information Systems University of Applied Sciences and Arts Northwestern Switzerland Olten Switzerland Institute for Clinical Diabetology German Diabetes Center Leibniz Center for Diabetes Research at Heinrich Heine University Düsseldorf Düsseldorf Germany Department of Endocrinology and Diabetology Medical Faculty University Hospital Düsseldorf Heinrich Heine University Düsseldorf Düsseldorf Germany German Center for Diabetes Research Partner Düsseldorf München-Neuherberg Germany

ISBN: (纸本)9783031810824

The use of artificial Intelligence (AI) in the medical field has grown significantly in recent years, also with computer vision techniques, such as Convolutional neural networks (CNNs), gaining prominence in medical image processing applications. While CNNs have proven helpful in various medical tasks, there is a research gap in the automatic selection of Corneal Confocal Microscopy (CCM) images for diagnostic purposes. CCM could be used to screen for early stages of Diabetic Peripheral Neuropathy (DPN), the most common complication of diabetes. However, manually selecting CCM images for diagnosis is time-consuming and requires expertise. This paper aims to evaluate the effectiveness of a Genetic Algorithm (GA) in finding an optimized CNN architecture for accurate quality control of CCM images. The GA-based approach is compared to the widely used VGG16 architecture. The results demonstrate that the GA-evolved CNN architecture achieved a validation accuracy of 67.57 to 72.97%, outperforming VGG16. This research highlights the potential of GAs in optimizing CNN architectures for medical image classification tasks and indicates a first step towards automatically selecting CCM images for analysis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

T-former: An Efficient Transformer for image Inpainting 22

T-former: An Efficient Transformer for Image Inpainting

引用

30th ACM International Conference on Multimedia (MM)

作者： Deng, Ye Hui, Siqi Zhou, Sanping Meng, Deyu Wang, Jinjun Xi An Jiao Tong Univ Xian Shaanxi Peoples R China Shunan Acad Artificial Intelligence Ningbo Peoples R China

ISBN: (纸本)9781450392037

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit the performance in the face of broken images with diverse and complex forms. Recently, a class of attention-based network architectures, called transformer, has shown significant performance on natural language processing fields and high-level vision tasks. Compared with CNNs, attention operators are better at long-range modeling and have dynamic weights, but their computational complexity is quadratic in spatial resolution, and thus less suitable for applications involving higher resolution images, such as image inpainting. In this paper, we design a novel attention linearly related to the resolution according to Taylor expansion. And based on this attention, a network called T-former is designed for image inpainting. Experiments on several benchmark datasets demonstrate that our proposed method achieves state-of-the-art accuracy while maintaining a relatively low number of parameters and computational complexity.

关键词： image inpainting attention neural networks transformer

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of artificial Intelligence (AI) Powered Brain Stroke Detection Methodology by Using Learning Based image processing Techniques

Empirical Evaluation of Artificial Intelligence (AI) Powered...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Shifani, S. Agnes Suresh, M. Deepa Franklin ThamilSelvi, M.S. Paramaiyappan, M. Korde, Vivek Attar, H. Saveetha University Department of Ece Chennai India School of Sciences Srm Institute of Science and Technology Division of Mathematics Trichy India Sathyabama Institute of Science and Technology Department of Mathematics Chennai India J.P. College of Engineering Department of Ece Tenkasi India Yeshwantrao Chavan College of Engineering Division of Mechanical Engineering Nagpur India Zarqa University Department of Energy Engineer zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Stroke is a leading cause of death and disability worldwide, making early detection and accurate diagnosis critical for patient outcomes. This study presents a Hybrid Learning Assisted Tumor Detection Scheme (HLTDS) for stroke detection from brain CT images. The proposed model integrates Convolutional neural networks (CNNs) with advanced feature extraction techniques, including AutoEncoders and edge detection, to enhance accuracy and computational efficiency. HLTDS was evaluated against nine existing models: CNN, ResNet50, VGG16, MobileNet, DenseNet, Inception, Xception, and EfficientNet, based on key performance metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that HLTDS outperforms all compared models with an accuracy of 96.45%, achieving the highest precision (95.82%) and recall (94.67%), making it the most reliable model for identifying stroke-related anomalies. The model's efficiency in terms of training time (58 minutes) and inference time (145 milliseconds) positions it as an optimal choice for real-time clinical applications. Furthermore, HLTDS achieves a balance between model size and memory usage, making it suitable for deployment in resource-constrained environments. These results highlight the importance of hybrid learning approaches in improving stroke detection while ensuring scalability. Future work will focus on expanding the model's capability to handle multiclass classification and further reducing computational costs. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bridging the Machine-Human Gap in Blurred-image Classification via Entropy Maximisation

Bridging the Machine-Human Gap in Blurred-Image Classificati...

引用

International image processing, applications and Systems Conference (IPAS)

作者： Emilio Sansano-Sansano Marina Martínez-García Javier Portilla INIT Universitat Jaume I Castellón de la Plana Spain IMAC Universitat Jaume I Castellón de la Plana Spain Instituto de Óptica CSIC Madrid Spain

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

Recent studies point to an accuracy gap between humans and artificial neural Network (ANN) models when classifying blurred images, with humans outperforming ANNs. To bridge this gap, we introduce a spectral channel-based range-constrained entropy merit function, from which we devise a zero-phase, circular symmetric blind deblurring method. We apply it as a pre-processing step for image classification and test it using pre-trained classification models and images blurred by Gaussian kernels. We compare our method to state-of-the-art restoration methods, showing its superiority, effectively bridging the machine-human gap for most models and blur levels. Our results also rank higher than the competitors in no-reference and full-reference image quality metrics. Notwithstanding the limitation to zero-phase blur, this work shows that, for image pre-processing aimed at visual tasks, it may be advantageous to use merit functions based on vision science and information theory, rather than on the expected error to the latent image.

关键词： Measurement image quality Visualization Computer vision artificial neural networks Entropy Kernel Optimization Information theory image classification

来源：评论

学校读者我要写书评

暂无评论

Enhanced image Segmentation by a Novel Test Time Augmentation and Super-Resolution 9th

Enhanced Image Segmentation by a Novel Test Time Augmentatio...

引用

9th International Work-Conference on the Interplay Between Natural and artificial Computation (IWINAC)

作者： Garcia-Aguilar, Ivan Garcia-Gonzalez, Jorge Marcos Luque-Baena, Rafael Lopez-Rubio, Ezequiel Dominguez-Merino, Enrique Univ Malaga Dept Comp Languages & Comp Sci Bulevar Louis Pasteur 35 Malaga 29071 Spain Biomed Res Inst Malaga IBIMA C Doctor Miguel Diaz Recio 28 Malaga 29010 Spain

ISBN: (纸本)9783031065279;9783031065262

image segmentation in computer vision applications plays a critical role in the video processing workflow. In real applications, where interesting elements are moving in the presence of moving objects in the background, complex models are required in the segmentation process to obtain better results. In this paper, a methodology based on super-resolution and test time augmentation is proposed to improve the precision and effectiveness of the segmentation process. Our proposal avoids both modification and retraining of the model. Experiments show that our approach can increase the mean average precision of images segmentation in sequences from well-known benchmark datasets with a significant improvement.

关键词： image segmentation Convolutional neural networks (CNN) Test Time Augmentation (TTA) Super-resolution (SR)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Identification of Birds in Agricultural Fields

Deep Learning-Based Identification of Birds in Agricultural ...

引用

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Chaturvedi, Keya Nithin Skantha, M. Navanithi, V.K. Pranesh, R. Harissh, G. Tangavel, Senthil Kumar Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore641112 India Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore641042 India

ISBN: (纸本)9798331510299

Studies on bird species provide important informa- tion about the biological systems that support the transportation of all life on Earth, including humans. Understanding bird species, their characteristics, migration patterns, and life cycles is important for maintaining ecological balance and a healthy planet. Recent advances in artificial intelligence (AI) and imaging tools have greatly improved the identification of bird species, helping in ecological research and agricultural management. However, identifying bird species in the field by photographing them remains a difficult and time-consuming task due to the similarity of class and quality attributes. Our research aims to address this challenge using deep learning, a machine learning technique that uses deep neural networks to identify birds accurately. We strive to develop and evaluate various CNN models such as VGG- 19, Inception V3, DenseNet-201, EfficientNet-V2, and MobileNet-V3 to analyze the majority using advanced com- puter vision tools such as transfer learning and deep quantum learning. The model is effective. The model will form the basis for the construction of the most advanced (SOTA) classification of birds, achieving 88 percent accuracy with the DenseNet-201 model. In addition, innovations such as Bird@Edge, an instant bird identification and AI-based deterrent system designed to protect plants from harmful birds, demonstrate our mastery of applications in eight of our work in biodiversity monitoring and plant protection. Future developments will focus on improving the accuracy and functionality of the model, making it more useful for ecological protection and permaculture promotion, plant protection, biodiversity management. © 2024 IEEE.

关键词： biodiversity management Bird species convolutional neural networks crop protection deep learning deep quantum learning image processing

来源：评论

学校读者我要写书评

暂无评论

Wide-Angle image Rectification: A Survey

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2022年第3期130卷 747-776页

作者： Fan, Jinlong Zhang, Jing Maybank, Stephen J. Tao, Dacheng Univ Sydney Fac Engn Sch Comp Sci Darlington NSW 2008 Australia Univ London Dept Comp Sci & Informat Syst Birkbeck Coll London England

Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain distortions that violate the assumptions underlying pinhole camera models, resulting in object distortion, difficulties in estimating scene distance, area, and direction, and preventing the use of off-the-shelf deep models trained on undistorted images for downstream computer vision tasks. image rectification, which aims to correct these distortions, can solve these problems. In this paper, we comprehensively survey progress in wide-angle image rectification from transformation models to rectification methods. Specifically, we first present a detailed description and discussion of the camera models used in different approaches. Then, we summarize several distortion models including radial distortion and projection distortion. Next, we review both traditional geometry-based image rectification methods and deep learning-based methods, where the former formulates distortion parameter estimation as an optimization problem and the latter treats it as a regression problem by leveraging the power of deep neural networks. We evaluate the performance of state-of-the-art methods on public datasets and show that although both kinds of methods can achieve good results, these methods only work well for specific camera models and distortion types. We also provide a strong baseline model and carry out an empirical study of different distortion models on synthetic datasets and real-world wide-angle images. Finally, we discuss several potential research directions that are expected to further advance this area in the future.

关键词： Computer Imaging Vision Pattern Recognition and Graphics artificial Intelligence image processing and Computer Vision Pattern Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Dense Space Attention Network for Super-Resolution Construction From Single Input image

引用

IEEE ACCESS 2021年 9卷 126837-126855页

作者： Ooi, Yoong Khang Ibrahim, Haidi Mahyuddin, Muhammad Nasiruddin Univ Sains Malaysia Sch Elect & Elect Engn Engn Campus Nibong Tebal 14300 Pulau Pinang Malaysia

In some applications, such as surveillance and biometrics, image enlargement is required to inspect small details on the image. One of the image enlargement approaches is by using convolutional neural network (CNN)-based super-resolution construction from a single image. The first CNN-based image super-resolution algorithm is the super-resolution CNN (SRCNN) developed in 2014. Since then, many researchers have proposed several versions of CNN-based algorithms for image super-resolution to improve the accuracy or reduce the model's running time. Currently, some algorithms still suffered from the vanishing-gradient problem and relied on a large number of layers. Thus, the motivation of this work is to reduce the vanishing-gradient problem that can improve the accuracy, and at the same time, reduce the running time of the model. In this paper, an enhanced dense space attention network (EDSAN) model is proposed to overcome the problems. The EDSAN model adopted a dense connection and residual network to utilize all the features to correlate the low-level feature and high-level feature as much as possible. Besides, implementing the convolution block attention module (CBAM) layer and multiscale block (MSB) helped reduce the number of layers required to achieve comparable results. The model is evaluated through peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) metrics. EDSAN achieved the most significant improvement, about 1.42% when compared to the CRN model using the Set5 dataset at a scale factor of 3. Compared to the ERN model, EDSAN performed the best, with a 1.22% improvement made when using the Set5 dataset at a scale factor of 4. In terms of overall performance, EDSAN performed very well in all datasets at a scale factor of 2 and 3. In conclusion, EDSAN successfully solves the problems above, and it can be used in different applications such as biometric identification applications and real-time video applications.

关键词： Superresolution Convolutional neural networks Residual neural networks Interpolation Licenses image reconstruction Feature extraction Computational and artificial intelligence image processing image resolution image quality machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Facial Expression Recognition through Effective Preprocessing Techniques

引用

Journal of Computer and Communications 2023年第12期11卷 86-101页

作者： Lakshminarayanan Meena Thambusamy Velmurugan PG Department of Computer Applications Dwaraka Doss Goverdhan Doss Vaishnav College Chennai India PG and Research Department of Computer Science Dwaraka Doss Goverdhan Doss Vaishnav College Chennai India

Analyzing human facial expressions using machine vision systems is indeed a challenging yet fascinating problem in the field of computer vision and artificial intelligence. Facial expressions are a primary means through which humans convey emotions, making their automated recognition valuable for various applications including man-computer interaction, affective computing, and psychological research. Pre-processing techniques are applied to every image with the aim of standardizing the images. Frequently used techniques include scaling, blurring, rotating, altering the contour of the image, changing the color to grayscale and normalization. Followed by feature extraction and then the traditional classifiers are applied to infer facial expressions. Increasing the performance of the system is difficult in the typical machine learning approach because feature extraction and classification phases are separate. But in Deep neural networks (DNN), the two phases are combined into a single phase. Therefore, the Convolutional neural Network (CNN) models give better accuracy in Facial Expression Recognition than the traditional classifiers. But still the performance of CNN is hampered by noisy and deviated images in the dataset. This work utilized the preprocessing methods such as resizing, gray-scale conversion and normalization. Also, this research work is motivated by these drawbacks to study the use of image pre-processing techniques to enhance the performance of deep learning methods to implement facial expression recognition. Also, this research aims to recognize emotions using deep learning and show the influences of data pre-processing for further processing of images. The accuracy of each pre-processing methods is compared, then combination between them is analysed and the appropriate preprocessing techniques are identified and implemented to see the variability of accuracies in predicting facial expressions. .

关键词： Facial Expression Recognition Preprocessing Techniques Normalization Convolutional neural Network (CNN) Deep neural networks (DNN)

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Spiking Recurrent neural Network on Hardware for Efficient Emotion Recognition 4

A Hybrid Spiking Recurrent Neural Network on Hardware for Ef...

引用

IEEE International Conference on artificial Intelligence Circuits and Systems (AICAS) - Intelligent Technology in the Post-Pandemic Era

作者： Zou, Chenglong Cui, Xiaoxin Kuang, Yisong Wang, Yuan Wang, Xinan Peking Univ Sch Integrated Circuits Key Lab Microelect Devices & Circuits Beijing 100871 Peoples R China Peking Univ Sch ECE Key Lab Integrated Microsyst Shenzhen Grad Sch Shenzhen 518055 Peoples R China

ISBN: (数字)9781665409964

ISBN: (纸本)9781665409964

In recent years, neuromorphic engineering based on spiking neural networks (SNNs) for real-time and low-power artificial intelligence (AI) tasks has attracted a lot of interest. However, most of the previous implementations on hardware of these algorithms concentrate on traditional feedforward fully-connected/convolutional neural network (CNNs) architectures which are used for vision image processing. Their applications in temporal text tasks using recurrent neural networks (RNNs) is less discussed. In this paper, we point out main difficulties of RNNs implementation on conventional neuromorphic systems and propose a hardware-oriented spiking RNN architecture for emotion recognition, which absorbs the external dynamics of traditional RNN and internal dynamics of SNN. Experimental results on two emotion recognition datasets show our spiking RNNs achieve comparable accuracies with other deep learning models and efficient run-time performance.

关键词： AI RNN SNN emotion recognition

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：