Simplified VGG based Super Resolution Restoration for Face Recognition

Wang, Mengmeng; Wang, Suyu; Kong, Peiling

doi:10.1145/3373509.3373569

Cited by 4 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG [23], the full name of visual geometry group, is a series of convolutional neural network models starting with VGG published by the department of science and engineering of Oxford university, which can be applied to face recognition [24,25,26], image classification [27,28] and other aspects. The original purpose of studying the depth of convolution network is to find out how the depth of convolution network affects the accuracy and accuracy of large-scale image classification and recognition.…”

Section: B Vgg Network Overviewmentioning

confidence: 99%

Multi-Scale and Multi-Channel Information Fusion for Exercise Electrocardiogram Feature Extraction and Classification

Wang,

Zhang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Increased physical activity can help reduce the occurrence of cardiovascular disease. However, cardiovascular disease during strenuous exercise also brings certain risks, so a convenient and effective method is needed to accurately identify heart rate. Due to the low amplitude characteristics of ECG signals, automatic classification of the imperceptibility and irregularities of ECG signals remains a great challenge. To address this issue, we propose an automatic heart rate detection method using a two-dimensional convolutional neural network. First, the ECG data is preprocessed to convert the multi-lead single-channel ECG data into dual-channel ECG data. Then, the ECG image is input into the convolutional neural network. To enhance the diagnostic accuracy of an abnormal heart rate diagnosis model, this study integrates a multiscale pyramid module into the network to fully extract image contextual information. Experimental analysis utilizes MIT-BIH and sudden cardiac death holter public datasets for training and testing. The results show that the final classification accuracy reaches 99.12% and 98.40%, respectively. The method requires no manual pre-processing of converted ECG images, has high accuracy, can effectively monitor abnormal heart rate, and minimize sudden death caused by abnormal heart rate.

show abstract

Section: B Vgg Network Overviewmentioning

confidence: 99%

Multi-Scale and Multi-Channel Information Fusion for Exercise Electrocardiogram Feature Extraction and Classification

Wang,

Zhang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, significant progress has been made in FSR, thanks to the powerful feature extraction capabilities of deep convolutional neural networks (CNN) in the field of image processing [14, 15]. One notable contribution is the ultra‐resolution discriminative generative network proposed by Yu et al.…”

Section: Related Workmentioning

confidence: 99%

A Decoder Structure Guided CNN‐Transformer Network for face super‐resolution

Dou,

Li,

Wan

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Recent advances in deep convolutional neural networks have shown improved performance in face super‐resolution through joint training with other tasks such as face analysis and landmark prediction. However, these methods have certain limitations. One major limitation is the requirement for manual marking information on the dataset for multi‐task joint learning. This additional marking process increases the computational cost of the network model. Additionally, since prior information is often estimated from low‐quality faces, the obtained guidance information tends to be inaccurate. To address these challenges, a novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding. Specifically, the proposed GLFEU is composed of an attention branch and a Transformer branch, to simultaneously restore global facial structure and local texture details. Additionally, a Multi‐Stage Feature Fusion Module is incorporated to fuse features from different network stages, further improving the quality of the restored face images. Compared with previous methods, DCTNet improves Peak Signal‐to‐Noise Ratio by 0.23 and 0.19 dB on the CelebA and Helen datasets, respectively. Experimental results demonstrate that the designed DCTNet offers a simple yet powerful solution to recover detailed facial structures from low‐quality images.

show abstract

“…In particular, we denote the extracted feature of 𝑃 and 𝑄 at the 𝑖 − 𝑡ℎ stage as P𝑖 and Q𝑖 , 𝑖 ∈ {1, 5}. Herein, the VGG16 network was originally used to deal with the image classification task and has been widely used in different CV tasks including super-resolution [41] and denoising [36]. In LPIPS [50] and DISTS [9], features of the VGG16 network were also proved to be useful for quality assessment.…”

Section: The Proposed Deepwsdmentioning

confidence: 99%

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Liao,

Chen,

Zhu

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1D Wasserstein distance at each stage of the pre-trained VGG network is measured, based on which the final quality score is performed. The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys better interpretability of the quality contamination caused by various types of distortions and presents an advanced quality prediction capability. Extensive experiments and theoretical analysis show the superiority of the proposed DeepWSD in terms of both quality prediction and optimization. The implementation of our method is publicly available at https://github.com/Buka-Xing/DeepWSD.

show abstract

Simplified VGG based Super Resolution Restoration for Face Recognition

Cited by 4 publications

References 6 publications

Multi-Scale and Multi-Channel Information Fusion for Exercise Electrocardiogram Feature Extraction and Classification

Multi-Scale and Multi-Channel Information Fusion for Exercise Electrocardiogram Feature Extraction and Classification

A Decoder Structure Guided CNN‐Transformer Network for face super‐resolution

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Contact Info

Product

Resources

About