4.6 Article

Number plate recognition from enhanced super-resolution using generative adversarial network

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Gene selection for microarray data classification via multi-objective graph theoretic-based method

Mehrdad Rostami et al.

Summary: The proposed social network analysis-based gene selection approach aims to maximize relevance and minimize redundancy of selected genes by repetitively selecting maximum communities and using node centrality-based criteria. This method improves classification accuracy of microarray data while reducing time complexity.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Co-clinical FDG-PET radiomic signature in predicting response to neoadjuvant chemotherapy in triple-negative breast cancer

Sudipta Roy et al.

Summary: The study aimed to optimize radiomic features using patient-derived tumor xenografts (PDX) in predicting therapy response in TNBC, and to implement these features in a co-clinical study using machine learning algorithms to predict therapy response.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2022)

Review Computer Science, Artificial Intelligence

Real-world single image super-resolution: A brief review

Honggang Chen et al.

Summary: This article provides a comprehensive review of real-world single image super-resolution (RSISR), covering critical datasets, assessment metrics, and four major categories of RSISR methods. It compares representative RSISR methods on benchmark datasets in terms of reconstruction quality and computational efficiency, while also discussing challenges and promising research topics in RSISR.

INFORMATION FUSION (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Post-OCR Paragraph Recognition by Graph Convolutional Networks

Renshen Wang et al.

Summary: This article proposes a new approach to paragraph recognition in document images using spatial graph convolutional networks (GCN) applied on OCR text boxes. The approach involves line splitting and line clustering steps to extract paragraphs from OCR results, utilizing a beta-skeleton graph constructed from bounding boxes for efficient graph convolution operations. The GCN model, with pure layout input features, is significantly smaller in size (3 to 4 orders of magnitude) compared to R-CNN based models, while achieving comparable or better accuracies on PubLayNet and other datasets. Moreover, the GCN models demonstrate good generalization from synthetic training data to real-world images, and adapt well to variable document styles.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Brazilian Mercosur License Plate Detection and Recognition Using Haar Cascade and Tesseract OCR on Synthetic Imagery

Cyro M. G. Saboia et al.

Summary: This article proposes a method for Brazilian Mercosur license plate detection and character recognition on synthetic imagery. The experiments were conducted using Cascade Classifiers and Tesseract OCR, and a multi-stage classifier was trained with Haar-type features. The proposed method achieved high detection success rate and digit classification accuracy on the Mercosur license plate dataset.

INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, ISDA 2021 (2022)

Article Computer Science, Information Systems

License Plate Image Analysis Empowered by Generative Adversarial Neural Networks (GANs)

Ibrahim H. El-Shal et al.

Summary: This study proposes a deep learning framework based on generative adversarial networks for detecting license plates in digital images in a natural environment. By processing low-resolution images into high-resolution images, the quality of the license plate is improved. Experimental results show that the proposed method significantly improves the accuracy of license plate recognition compared to other systems.

IEEE ACCESS (2022)

Proceedings Paper Computer Science, Artificial Intelligence

On the Cross-dataset Generalization in License Plate Recognition

Rayson Laroca et al.

Summary: This paper empirically assesses the cross-dataset generalization of 12 OCR models in license plate recognition on 9 publicly available datasets. The experimental results reveal the limitations of the traditional-split protocol for evaluating approaches in the ALPR context.

PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5 (2022)

Article Mathematics, Interdisciplinary Applications

Development of ANPR Framework for Pakistani Vehicle Number Plates Using Object Detection and OCR

Salma et al.

Summary: The study collected a Pakistani vehicle dataset with various plate configurations to develop an ANPR framework using YOLO object detection and OCR Tesseract, achieving an accuracy of 73% and showing good potential for countries with similar vehicle number plate challenges.

COMPLEXITY (2021)

Article Biochemical Research Methods

Evaluation and development of deep neural networks for image super-resolution in optical microscopy

Chang Qiao et al.

Summary: This study investigates the performance of deep-learning models for super-resolution imaging, introducing models that utilize frequency content information in the Fourier domain to improve imaging under low-SNR conditions. The research shows that deep-learning models can robustly reconstruct SIM images under low signal-to-noise ratio conditions, achieving comparable image quality to SIM in multicolor live-cell imaging experiments.

NATURE METHODS (2021)

Review Automation & Control Systems

Review of swarm intelligence-based feature selection methods

Mehrdad Rostami et al.

Summary: Research has shown that feature selection methods can improve the accuracy of data mining tasks and reduce computational complexity by reducing irrelevant, redundant, or noisy data to lower data dimensionality. The aim of feature selection is to select a subset of features with the lowest inner similarity and highest relevancy to the target class.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2021)

Article Environmental Sciences

License Plate Image Reconstruction Based on Generative Adversarial Networks

Mianfen Lin et al.

Summary: The paper introduces a super-resolution image reconstruction method based on Generative Adversarial Networks (GAN), which outperforms the current better algorithm in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) on the Chinese City Parking Dataset (CCPD), while also requiring less reconstruction time.

REMOTE SENSING (2021)

Proceedings Paper Computer Science, Information Systems

MC-OCR Challenge: Mobile-Captured Image Document Recognition for Vietnamese Receipts

Xuan-Son Vu et al.

Summary: The Mobile Captured Receipt Recognition Challenge (MC-OCR) task was organized at the RIVF 2021 conference to recognize fine-grained information in Vietnamese receipts captured using mobile devices. Participants were challenged to build a multi-tasking model capable of predicting receipt quality and recognizing four required information in the receipts. This challenge attracted 105 participants and received about 1,285 submission entries within one month.

2021 RIVF INTERNATIONAL CONFERENCE ON COMPUTING AND COMMUNICATION TECHNOLOGIES (RIVF 2021) (2021)

Article Computer Science, Information Systems

Real-time license plate detection and recognition using deep convolutional neural networks

Sergio Montazzolli Silva et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2020)

Article Biotechnology & Applied Microbiology

Integration of multi-objective PSO based feature selection and node centrality for medical datasets

Mehrdad Rostami et al.

GENOMICS (2020)

Article Computer Science, Information Systems

Saliency-based framework for facial expression recognition

Rizwan Ahmed Khan et al.

FRONTIERS OF COMPUTER SCIENCE (2019)

Article Computer Science, Artificial Intelligence

Improved Recognition Results of Medieval Handwritten Gurmukhi Manuscripts Using Boosting and Bagging Methodologies

Munish Kumar et al.

NEURAL PROCESSING LETTERS (2019)

Article Computer Science, Artificial Intelligence

Neural Networks Pipeline for Offline Machine Printed Arabic OCR

Mohamed A. Radwan et al.

NEURAL PROCESSING LETTERS (2018)

Article Engineering, Electrical & Electronic

Residual Networks of Residual Networks: Multilevel Residual Networks

Ke Zhang et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2018)

Article Computer Science, Information Systems

An improved brain MR image binarization method as a preprocessing for abnormality detection and features extraction

Sudipta Roy et al.

FRONTIERS OF COMPUTER SCIENCE (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Wei-Sheng Lai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Simultaneous Orthogonal Basis Clustering Feature Selection

Dongyoon Han et al.

2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2015)

Proceedings Paper Computer Science, Artificial Intelligence

Learning a Deep Convolutional Network for Image Super-Resolution

Chao Dong et al.

COMPUTER VISION - ECCV 2014, PT IV (2014)

Article Computer Science, Artificial Intelligence

A coarse-to-fine strategy for multiclass shape detection

Y Amit et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2004)