Skip to search formSkip to main contentSkip to account menu
Unsupervised feature learning framework for no-reference image quality assessment
TLDR
This paper uses raw image patches extracted from a set of unlabeled images to learn a dictionary in an unsupervised manner and uses soft-assignment coding with max pooling to obtain effective image representations for quality estimation.
View on IEEE
Convolutional Neural Networks for No-Reference Image Quality Assessment
TLDR
A Convolutional Neural Network is described to accurately predict image quality without a reference image to achieve state of the art performance on the LIVE dataset and shows excellent generalization ability in cross dataset experiments.
View on IEEE
Text Detection and Recognition in Imagery: A Survey
TLDR
This review provides a fundamental comparison and analysis of the remaining problems in the field and summarizes the fundamental problems and enumerates factors that should be considered when addressing these problems.
View on IEEE
Blind Image Quality Assessment Based on High Order Statistics Aggregation
TLDR
A novel general purpose BIQA method based on high order statistics aggregation (HOSA), requiring only a small codebook, which has been extensively evaluated on ten image databases with both simulated and realistic image distortions, and shows highly competitive performance to the state-of-the-art BIZA methods.
View on IEEE
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
TLDR
This paper proposes an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner and effectively solves the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end to end manner.
View on IEEE
Automatic text detection and tracking in digital video
TLDR
This work presents algorithms for detecting and tracking text in digital video that implements a scale-space feature extractor that feeds an artificial neural processor to detect text blocks.
View on PubMed
Simultaneous estimation of image quality and distortion via multi-task convolutional neural networks
TLDR
This work designs a compact multi-task Convolutional Neural Network for simultaneously estimating image quality and identifying distortions, and demonstrates its learning power.
View on IEEE
No-Reference Image Quality Assessment Using Visual Codebooks
TLDR
The proposed method is comparable to state-of-the-art general-purpose NR-IQA methods and outperforms the full-reference image quality metrics, peak signal-to-noise ratio and structural similarity index on the Laboratory for Image and Video Engineering IQA database.
View on IEEE
Robust point matching for nonrigid shapes by preserving local neighborhood structures
TLDR
This paper introduces the notion of a neighborhood structure for the general point matching problem, and forms point matching as an optimization problem to preserve local neighborhood structures during matching.
View on IEEE
Script-Independent Text Line Segmentation in Freestyle Handwritten Documents
TLDR
A novel approach based on density estimation and a state-of-the-art image segmentation technique, the level set method, which consistently outperforms previous methods on text line segmentation in freestyle handwritten documents.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License