Empowering Face Recognition Methods using a GAN-based Single Image Super-Resolution Network

Shahbakhsh, M. B.; Hassanpour, H.

doi:10.5829/ije.2022.35.10a.05

Cited by 10 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, to solve the problem of low-resolution faces, Nam et al [ 36 ] introduced PSI-CNN, which uses a generic CNN architecture based on scale-invariant pyramids that can learn information at a different level in low-resolution images. Shahbakhsh and Hassanpou [ 37 ] presented a GAN to consider the image edges, which reconstructs the details to preserve the facial structure. Some works solve both the aforementioned problems of facial recognition in video-surveillance camera applications.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

et al. 2023

View full text Add to dashboard Cite

In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.

show abstract

Section: Related Workmentioning

confidence: 99%

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The facial expression has numerous applications in several fields including healthcare, augmented reality (AR), virtual reality (VR), entertainment, and driver assistant systems [1]. The performance of existence methods depends on the quality and quantity of training information [2].…”

Section: Introductionmentioning

confidence: 99%

Generative adversarial networks with attentional multimodal for human face synthesis

BJ,

Meeradevi,

Shedole

2024

IJEECS

View full text Add to dashboard Cite

<p><span>Face synthesis and editing has increased cumulative consideration by the improvement of generative adversarial networks (GANs). The proposed attentional GAN-deep attentional multimodal similarity modal (AttnGAN-DAMSM) model focus on generating high-resolution images by removing discriminator components and generating realistic images from textual description. The attention model creates the attention map on the image and automatically retrieves the features to produce various sub-areas of the image. The DAMSM delivers fine-grained image-text identical loss to generative networks. This study, first describe text phrases and the model will generate a photorealistic high-resolution image composed of features with high accuracy. Next, model will fine-tune the selected features of face images and it will be left to the control of the user. The result shows that the proposed AttnGAN-DAMSM model delivers the performance metrics like structural similarity index measure (SSIM), feature similarity index measure (FSIM) and frechet inception distance (FID) using CelebA and CUHK face sketch (CUFS) dataset. For CelebFaces attribute (CelebA) dataset, the SSIM achieves 78.82% and for CUFS dataset, the SSIM achieves 81.45% which ensures accurate face synthesis and editing compared with existing methods such as GAN, SuperstarGAN and identity-sensitive GAN (IsGAN) models.</span></p>

show abstract

“…Digitized documents can be used for various applications of information extraction and retrieval (4)(5)(6)(7)(8). Information extraction is the process of automatically extracting structured information from unstructured documents (8).…”

Section: Introductionmentioning

confidence: 99%

Enhancing Book and Document Digitization from Videos: A Feature Fusion-Based Approach

Buddhawar,

Jariwala,

Chattopadhyay

2024

IJE

View full text Add to dashboard Cite

In an age where preserving knowledge and information from books and documents is crucial, traditional manual scanning methods are tedious and error-prone. It involves a lot of human intervention and, as a result, sometimes results in erroneous digitization, which makes the downstream tasks, such as optical character recognition, difficult. Therefore, innovative techniques are required to be proposed that not only reduce human effort in terms of digitization but also give highly accurate results over the recently proposed state-of-the-art techniques. We proposed a novel computer vision-based algorithm that combines Gray-Level Co-occurrence Matrix (GLCM) features with Thepade's 10-ary texture features (TSBTC) for video frame classification. This hybrid approach significantly enhances frame selection accuracy, ensures high-quality digitization, and accommodates multiple languages and document types. We also proposed a dataset of 54,000 diverse images to demonstrate our algorithm's effectiveness in realworld scenarios and compare it to existing methods, making a valuable contribution to document digitization. The proposed dataset can be utilized for several document image analysis tasks.

show abstract

Empowering Face Recognition Methods using a GAN-based Single Image Super-Resolution Network

Cited by 10 publications

References 51 publications

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

Generative adversarial networks with attentional multimodal for human face synthesis

Enhancing Book and Document Digitization from Videos: A Feature Fusion-Based Approach

Contact Info

Product

Resources

About