1,447 Hits in 1.8 sec

A shallow convolutional neural network for blind image sharpness assessment

Shaode Yu, Shibin Wu, Lei Wang, Fan Jiang, Yaoqin Xie, Leida Li, You Yang
2017 PLoS ONE  
This paper addresses blind image sharpness assessment by using a shallow convolutional neural network (CNN).  ...  Blind image quality assessment can be modeled as feature extraction followed by score prediction.  ...  Acknowledgments The authors would like to thank reviewers for their valuable advices that has helped to improve the paper quality.  ... 
doi:10.1371/journal.pone.0176632 pmid:28459832 pmcid:PMC5436206 fatcat:u5ceycuxhzfohm3uuis3ztmn7e

Deep Activation Pooling for Blind Image Quality Assessment

Zhong Zhang, Hong Wang, Shuang Liu, Tariq Durrani
2018 Applied Sciences  
We first utilize the convolutional maps to select high-contrast patches, and then we utilize these selected patches of pristine images to train a pristine multivariate Gaussian (PMVG) model.  ...  Driven by the rapid development of digital imaging and network technologies, the opinion-unaware blind image quality assessment (BIQA) method has become an important yet very challenging task.  ...  Firstly, we utilize the convolutional maps of a pretrained convolutional neural network (CNN) for high-contrast patch selection.  ... 
doi:10.3390/app8040478 fatcat:yyjf2sgkmnffjoorjy2a6kbwui

Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks [article]

Wei Zhou, Qiuping Jiang, Yuwang Wang, Zhibo Chen, Weiping Li
2020 arXiv   pre-print
In this paper, we propose a no-reference/blind deep neural network-based SR image quality assessor (DeepSRQ).  ...  quality assessment algorithms.  ...  ILNIQE) [44] , convolutional neural networks for no-reference image quality assessment (CNN-IQA) [11] , and the shallow convolutional neural network for SR IQA (CNNSR) [4] .  ... 
arXiv:2004.06163v1 fatcat:yckfryo6lra2pciektyxdf4aiu

Related Work on Image Quality Assessment [article]

Dongxu Wang
2021 arXiv   pre-print
Due to the existence of quality degradations introduced in various stages of visual signal acquisition, compression, transmission and display, image quality assessment (IQA) plays a vital role in image-based  ...  This article will review the state-of-the-art image quality assessment algorithms.  ...  [34] proposed a data-driven blind image quality assessment (BIQA) method based on the quality-aware deep neural network (Q-DNN), in which a supervised learning model is utilized in the Q-DNN.  ... 
arXiv:2111.06291v1 fatcat:a3wrhqws7bg5thadvagtqvwl3q

Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks [article]

Siyuan Liu, Kim-Han Thung, Weili Lin, Pew-Thian Yap, Dinggang Shen
2019 arXiv   pre-print
IQA is first performed slice-wise using a nonlocal residual neural network (NR-Net) and then volume-wise by agglomerating the slice QA results using random forest.  ...  Using a small set of quality-assessed images, we pre-train NR-Net to annotate each image slice with an initial quality rating (i.e., pass, questionable, fail), which we then refine by semi-supervised learning  ...  ACKNOWLEDGEMENT This work was supported in part by NIH grants (MH117943, EB006733, AG041721, 1U01MH110274, NS093842, EB022880, and MH100217) and the efforts of the UNC/UMN Baby Connectome Project Consortium  ... 
arXiv:1904.03639v1 fatcat:sq4pllaogbbwzmy2vtmczabfaa

CNN for License Plate Motion Deblurring [article]

Pavel Svoboda, Michal Hradis, Lukas Marsik, Pavel Zemcik
2016 arXiv   pre-print
In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks in a situation where the blur kernels are partially constrained.  ...  We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality  ...  [4] which relies on convolutional neural networks (CNN) trained on a large set of artificially blurred images to directly deblur images.  ... 
arXiv:1602.07873v1 fatcat:42f24rai2jafvmbc6jdnpmq3am

Deep Optimization model for Screen Content Image Quality Assessment using Neural Networks [article]

Xuhao Jiang, Liquan Shen, Guorui Feng, Liangwei Yu, Ping An
2019 arXiv   pre-print
In this paper, we propose a novel quadratic optimized model based on the deep convolutional neural network (QODCNN) for full-reference and no-reference screen content image (SCI) quality assessment.  ...  Unlike traditional CNN methods taking all image patches as training data and using average quality pooling, our model is optimized to obtain a more effective model including three steps.  ...  These methods utilize image patches as a data augmentation, and design special patch-level neural networks for NI IQA. Kang et al.  ... 
arXiv:1903.00705v1 fatcat:cesomacdi5bsjdm5sykeyhq5hq

Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images [article]

Qunliang Xing, Mai Xu, Tianyi Li, Zhenyu Guan
2020 arXiv   pre-print
Specifically, our approach blindly and progressively enhances the quality of compressed images through a dynamic deep neural network (DNN), in which an early-exit strategy is embedded.  ...  Besides, it is common in practice that compressed images are with unknown quality and it is intractable for existing approaches to select a suitable model for blind quality enhancement.  ...  Then, a novel dynamic deep neural network (DNN) is designed, which progressively enhances the quality of compressed image, assesses the enhanced image quality, and automatically decides whether to terminate  ... 
arXiv:2006.16581v4 fatcat:tuqst7upyrhjzjj2l6gllbnkrq

Deep Learning to Automate Reference-Free Image Quality Assessment of Whole-Heart MR Images

Davide Piccini, Robin Demesmaeker, John Heerfordt, Jérôme Yerly, Lorenzo Di Sopra, Pier Giorgio Masci, Juerg Schwitter, Dimitri Van De Ville, Jonas Richiardi, Tobias Kober, Matthias Stuber
2020 Radiology: Artificial Intelligence  
A deep convolutional neural network for image quality assessment (IQ-DCNN) was designed, trained, optimized, and cross-validated on a clinical database of 324 (training set) scans.  ...  On a separate test set (100 scans), two hypotheses were tested: (a) that the algorithm can assess image quality in concordance with human expert assessment as assessed by human-machine correlation and  ...  -IQ-DCNN = image quality deep convolutional neural network.  ... 
doi:10.1148/ryai.2020190123 pmid:33937825 pmcid:PMC8082371 fatcat:vdfg3cgs3jdcbjru3ak6pfvsoy

Introduction to the Special Section on Deep Learning in Video Enhancement and Evaluation: The New Frontier

Zhenzhong Chen, Huchuan Lu, Junwei Han
2020 IEEE transactions on circuits and systems for video technology (Print)  
., introduces a distortion rectification approach based on residual distortion map estimation using convolutional neural networks and presents a refinement rectification method accordingly.  ...  a bidirectional feature embedding network (B-FEN) to quantitatively measure the quality of a de-rained image.  ...  ., reduces high-quality color image artifacts by developing an implicit dual-domain convolutional network (IDCN) to utilize both pixel-domain features and DCT-domain priors.  ... 
doi:10.1109/tcsvt.2020.3023571 fatcat:csbazoxofbdgho3of2k7n4y4m4

Blind Predicting Similar Quality Map for Image Quality Assessment

Da Pan, Ping Shi, Ming Hou, Zefeng Ying, Sizhe Fu, Yuan Zhang
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we propose a simple and efficient BIQA model based on a novel framework which consists of a fully convolutional neural network (FCNN) and a pooling network to solve this problem.  ...  A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner.  ...  Acknowledgement This work was supported by the National Natural Science Foundation of China under Contract 61472389 and by "Double Tops" construction project.  ... 
doi:10.1109/cvpr.2018.00667 dblp:conf/cvpr/PanSHYFZ18 fatcat:byuyfksxijae7bxcpfzixtdaqe

Blind Predicting Similar Quality Map for Image Quality Assessment [article]

Da Pan, Ping Shi, Ming Hou, Zefeng Ying, Sizhe Fu, Yuan Zhang
2019 arXiv   pre-print
In this paper, we propose a simple and efficient BIQA model based on a novel framework which consists of a fully convolutional neural network (FCNN) and a pooling network to solve this problem.  ...  A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner.  ...  In this paper, we propose a new Deep-IQA model which consists of a fully convolutional neural network (FCNN) and a deep pooling network (DPN).  ... 
arXiv:1805.08493v2 fatcat:ent4yhtwrvecllobn4w22yt6ye

Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks [article]

Sorour Mohajerani, Thomas A. Krammer, Parvaneh Saeedi
2018 arXiv   pre-print
This framework benefits from a Fully Convolutional Neural Network (FCN), which is capable of pixel-level labeling of cloud regions in a Landsat 8 image.  ...  We show that using the hybrid of the two methods (threshold-based and deep-learning) improves the performance of the cloud identification process without the need to manually correct automatically generated  ...  [5] trained a convolutional Neural network (CNN) from multiple small patches.  ... 
arXiv:1810.05782v1 fatcat:7hkce4qfibbxzoakqoiwzh2zyq

Legacy Photo Editing with Learned Noise Prior [article]

Zhao Yuzhi, Po Lai-Man, Wang Xuehui, Liu Kangcheng, Zhang Yujia, Yu Wing-Yin, Xian Pengfei, Xiong Jingjing
2020 arXiv   pre-print
To solve these problems, we propose a noise prior learner NEGAN to simulate the noise distribution of real legacy photos using unpaired images.  ...  We also create a large legacy photo dataset for learning noise prior. Using learned noise prior, we can easily build valid training pairs by degrading clean images.  ...  We utilize a neural network G to simulate the blind noise for clean image x.  ... 
arXiv:2011.11309v2 fatcat:hvmq23f3affdxbohacort7fhgi

Exudate Detection for Diabetic Retinopathy Using Pretrained Convolutional Neural Networks

Muhammad Mateen, Junhao Wen, Nasrullah Nasrullah, Song Sun, Shaukat Hayat
2020 Complexity  
In this paper, pretrained convolutional neural network- (CNN-) based framework has been proposed for the detection of exudate.  ...  In the field of ophthalmology, diabetic retinopathy (DR) is a major cause of blindness. DR is based on retinal lesions including exudate.  ...  In the beginning, the training of the selective convolutional neural network models is performed using sample images taken by the standard publicly available "ImageNet" database; moreover, the idea of  ... 
doi:10.1155/2020/5801870 fatcat:b66vxhh4orfrrju6nybyutfnuu
« Previous Showing results 1 — 15 out of 1,447 results