检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Dubey, Shiv Ram Singh, Satish Kumar Chu, Wei-Ta Indian Institute of Information Technology Computer Vision and Biometrics Lab Allahabad India National Cheng Kung University Dept. of Computer Science and Information Engineering Taiwan

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Recently, Transformer has emerged as a new architecture in deep learning by utilizing self-attention without convolution. Transformer is also extended to vision Transformer (ViT) for the visual recognition with a promising performance on ImageNet. In this paper, we propose a vision Transformer Hashing (VTS) for image retrieval. We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head. The proposed VTS model is fine tuned for hashing under six different image retrieval frameworks with their objective functions. We perform the extensive experiments on CIFAR10, ImageNet, NUS-Wide, and COCO datasets. The proposed VTS based image retrieval outperforms the recent state-of-the-art hashing techniques with a significant margin. We also find the proposed VTS model as the backbone network is better than the existing networks, such as AlexNet and ResNet. The code is released at https://***/shivram1987/visionTransformerHashing. © 2022 IEEE.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Fire and Smoke Detection using an Enhanced YOLOv8 Model

Fire and Smoke Detection using an Enhanced YOLOv8 Model

引用

2024 IEEE International Conference on computer vision and Machine Intelligence, CVMI 2024

作者： Bohra, Bhavesh Kumar Rajesh, Bulla Javed, Mohammed Doermann, David Iiit Computer Vision and Biometrics Lab Department of It Allahabad India Iiit Sricity Department of Computer Science and Engineering India University at Buffalo Department of Computer Science and Engineering BuffaloNY United States

ISBN: (纸本)9798350376876

Due in part to global warming, the frequency of wildfires has increased in recent years, significantly impacting humans, wildlife, and forest ecosystems. To address this challenge, using technology for early fire detection through smoke can help firefighters and other stakeholders limit their spread and reduce the impact. In this research, we adopt the latest object detection model - YOLOv8 and use a fine-tuned version for detecting smoke and fire using the latest datasets. YOLOv8 backbone begins with two convolutional (Conv) layers, followed by a series of alternating Conv layers and C2F modules, and ends with a Spatial Pyramid Pooling - Fast (SPPF) module. Our improvement involves adding two extra Conv layers at the beginning of the backbone, between the alternating sequence of Conv and C2F layers. As the smoke and fire detection problem involves searching for smaller objects in the image, increasing the feature extraction layers improves the performance of smoke and fire detection. The fine-tuned model is tested with the FASDD v4 dataset, which depicts fire, smoke, non-fire, and non-smoke scenarios. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

YOLOv8 Based Deep Learning Method for Potholes Detection 2

YOLOv8 Based Deep Learning Method for Potholes Detection

引用

2nd IEEE International Conference on computer vision and Machine Intelligence, CVMI 2023

作者： Kumari, Shruti Gautam, Anjali Basak, Suvramalya Saxena, Nidhi Indian Institute of Information Technology Allahabad Computer Vision and Biometrics Lab It Department Prayagraj India Madhav Institute of Technology and Science It Department Gwalior India

ISBN: (纸本)9798350305142

Potholes are a common road hazard that may cause significant damage to vehicles and pose risks to drivers and pedestrians. The detection and classification of potholes in images can aid in effective maintenance and repair of road infrastructure. In this study, the training of YOLOv8, an advanced object detection algorithm, on a pothole image dataset is presented. The pothole image dataset consists of diverse images captured from various road conditions and environments. The dataset is annotated with bounding boxes around the pothole instances to facilitate supervised learning. YOLOv8, known for its accuracy and efficiency, is utilized as the object detection framework due to its real-time object detection ability. To train YOLOv8, a two-step procedure is followed. Firstly, a pre-training phase is conducted on a large-scale COCO dataset. This pre-trained model is fine-tuned on the pothole image dataset. The fine-tuning process adapts the pre-trained model to accurately detect and classify potholes. The performance of the trained YOLOv8 model is evaluated. This proposed approach is able to accurately detect and classify potholes in images. In this work YOLOv8 is used for pothole detection. Different variants of YOLOv8 (YOLOv8x, YOLOv81, YOLOv8m, YOLOv8s, YOLOv8n) are used and then the results on the dataset 'Pothole detection Image Dataset' is analysed. Overall, this study presents a comprehensive framework for training YOLOv8 on a pothole image dataset. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Eye-verifier using ternary template for reliable eye detection in facial color images

Eye-verifier using ternary template for reliable eye detecti...

引用

IEEE International Conference on biometrics: Theory, Applications, and Systems (BTAS)

作者： Nguyen Van Huan Nguyen Thi Hai Binh Hakil Kim Computer Vision Lab. Biometrics Engineering Research Center Incheon Korea Computer Vision Laboratory INHA University Incheon South Korea

This paper introduces an eye-verifier for reliable detection of eyes in facial color images. At first, the eye region candidates are searched by the circular filter to the binary face image. The eye candidates are then fed into an eye-verifier. The eye-verifier uses a ternary template, generated from the eye area consisting of iris, sclera and skin. Then the template matching is made by ternary Hamming distance. Experimental results evaluating the proposed method on our own face database and FERET database show promising performance in terms of detection rate. The proposed algorithm showed a robust performance to the face poses and eye directions.

关键词： Face detection Color Eyes Iris Skin biometrics Humans Mouth Shape Filters

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Inpainting Occluded Face Images

Generative Adversarial Networks for Inpainting Occluded Face...

引用

Conference on Information and Communication Technology (CICT)

作者： Riya Shah Anjali Gautam Satish Kumar Singh Information Technology Computer Vision and Biometrics Lab (CVBL) IIIT Allahabad Uttar Pradesh India

ISBN: (数字)9781665473125

ISBN: (纸本)9781665473132

Convolutional neural network (CNN) recognizers have made substantial progress in face recognition. Existing recognizers have a lot of power over un-occluded faces, but their performance suffers when it comes to recognizing occluded faces directly. As occlusions cause a lack of visual and recognition signals. The face inpainting task is complicated as it requires generating new pixels for the missing regions of the face image. Generative adversarial networks (GAN) are more suitable for this task when we have to reconstruct visually plausible occlusions in face inpainting. The GAN model is able to generate and inpaint the missing regions of the image. In this paper, we have developed a methodology that makes use of GAN and contextual attention to inpaint images. This image inpainting has applications in the area of face recognition, face animation, and generating synthetic data.

关键词： Training Deep learning Representation learning Visualization Face recognition Generative adversarial networks Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

iris recognition in wearable computer

引用

1st International Conference on Biometric Authentication, ICBA 2004

作者： Lee, Jeong Jun Noh, Seungin Park, Kang Ryoung Kim, Jaihie Computer Vision Lab Dept. of Electrical and Electronic Eng. Biometrics Engineering Research Center Yonsei University Seoul Korea Republic of Division of Media Technology Sangmyung University Seoul Korea Republic of

ISBN: (纸本)3540221468

Recently, there has been much progress in wearable computing. Input/output interface and security are important research areas in wearable computing. In this paper, we describe considerations which should be taken into account in designing a wearable interface and iris recognition system. One of the most important issues in designing a wearable iris recognition system is the radial lens distortion. We suggest a radial distortion elimination method which is simple but accurate. Experimental results show that the quality of the image captured by our system is good enough for iris recognition and we can achieve 0.18% of the EER by applying our proposed radial distortion elimination method. © Springer-Verlag Berlin Heidelberg 2004.

关键词： biometrics

来源：评论

学校读者我要写书评

暂无评论

PTSR: Patch Translator for Image Super-Resolution

arXiv

引用

arXiv 2023年

作者： Baghel, Neeraj Dubey, Shiv Ram Singh, Satish Kumar The Computer Vision and Biometrics Lab Department of Information Technology Indian Institute of Information Technology Allahabad Prayagraj India

Image super-resolution generation aims to generate a high-resolution image from its low-resolution image. However, more complex neural networks bring high computational costs and memory storage. It is still an active area for offering the promise of overcoming resolution limitations in many applications. In recent years, transformers have made significant progress in computer vision tasks as their robust self-attention mechanism. However, recent works on the transformer for image super-resolution also contain convolution operations. We propose a patch translator for image super-resolution (PTSR) to address this problem. The proposed PTSR is a transformer-based GAN network with no convolution operation. We introduce a novel patch translator module for regenerating the improved patches utilising multi-head attention, which is further utilised by the generator to generate the 2× and 4× super-resolution images. The experiments are performed using benchmark datasets, including DIV2K, Set5, Set14, and BSD100. The results of the proposed model is improved on an average for 4× super-resolution by 21.66% in PNSR score and 11.59% in SSIM score, as compared to the best competitive models. We also analyse the proposed loss and saliency map to show the effectiveness of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network

arXiv

引用

arXiv 2023年

作者： Baghel, Neeraj Dubey, Shiv Ram Singh, Satish Kumar Computer Vision and Biometrics Lab Department of Information Technology Indian Institute of Information Technology Allahabad211015 India

Image super-resolution aims to synthesize high-resolution image from a low-resolution image. It is an active area to overcome the resolution limitations in several applications like low-resolution object-recognition, medical image enhancement, etc. The generative adversarial network (GAN) based methods have been the state-of-the-art for image super-resolution by utilizing the convolutional neural networks (CNNs) based generator and discriminator networks. However, the CNNs are not able to exploit the global information very effectively in contrast to the transformers, which are the recent breakthrough in deep learning by exploiting the self-attention mechanism. Motivated from the success of transformers in language and vision applications, we propose a SRTransGAN for image super-resolution using transformer based GAN. Specifically, we propose a novel transformer-based encoder-decoder network as a generator to generate 2× images and 4× images. We design the discriminator network using vision transformer which uses the image as sequence of patches and hence useful for binary classification between synthesized and real high-resolution images. The proposed SRTransGAN outperforms the existing methods by 4.38% on an average of PSNR and SSIM scores. We also analyze the saliency map to understand the learning ability of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ETLNet: An Efficient TCN-BiLSTM Network for Road Anomaly Detection Using Smartphone Sensors

arXiv

引用

arXiv 2024年

作者： Ansari, Mohd Faiz Sandilya, Rakshit Javed, Mohammed Doermann, David Computer Vision and Biometrics Lab Department of IT IIIT Allahabad India Computer Science and Engineering University at Buffalo BuffaloNY United States

Road anomalies can be defined as irregularities on the road surface or in the surface itself. Some may be intentional (such as speed-bumps), accidental (such as materials falling off a truck), or the result of roads’ excessive use or low or no maintenance, such as potholes. Despite their varying origins, these irregularities often harm vehicles substantially. Speed bumps are intentionally placed for safety but are dangerous due to their non-standard shape, size, and lack of proper markings. Potholes are unintentional and can also cause severe damage. To address the detection of these anomalies, we need an automated road monitoring system. Today, various systems exist that use visual information to track these anomalies. Still, due to poor lighting conditions and improper or missing markings, they may go undetected and have severe consequences for public transport, automated vehicles, etc. In this paper, the Enhanced Temporal-BiLSTM Network (ETLNet) is introduced as a novel approach that integrates two Temporal Convolutional Network (TCN) layers with a Bidirectional Long Short-Term Memory (BiLSTM) layer. This combination is tailored to detect anomalies effectively irrespective of lighting conditions, as it depends not on visuals but smartphone inertial sensor data. Our methodology employs accelerometer and gyroscope sensors, typically in smartphones, to gather data on road conditions. Empirical evaluations demonstrate that the ETLNet model maintains an F1-score for detecting speed bumps of 99.3%. The ETLNet model’s robustness and efficiency significantly advance automated road surface monitoring technologies. © 2024, CC BY.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep Learning Models to Detect Breast Cancer from Histopathology Images

Analysis of Deep Learning Models to Detect Breast Cancer fro...

引用

IEEE Region 10 International Conference TENCON

作者： Anjali Gautam Satish Kumar Singh Department of Information Technology Computer Vision and Biometrics Lab (CVBL) Indian Institute of Information Technology Allahabad Prayagraj INDIA

Breast cancer is a disease where breast cells grow out of control and leads to cancer. Various methodologies have been developed to identify breast cancer. In this paper, we have developed an approach to classify breast cancer from histopathology images. The approach makes use of deep learning based architectures by setting same parameters for all while training and testing on them. Thereafter, all the architectures are compared to see which one is most suited for the classification of breast cancer. Previous works on AlexNet, VGG, ResNet have already been published, and here we have tried to see the performance of those models which have less number of trainable parameters, namely DenseNet121, DenseNet169, DenseNet201, EfficientNetB0, EfficientNetB5, EfficientNetV2B0 and EfficientNetV2S. Here, all the experiments are conducted on BreakHis histopathology dataset by utilizing all the images of resolutions 40X, 100X, 200X and 400X of benign and malignant cancer.

关键词：

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：