Search Results for author:
Found 5 papers, 4 papers with code
Semantic Segmentation Using Super Resolution Technique as Pre-Processing
Combining high-level and low-level visual tasks is a common technique in the field of computer vision.
CCDWT-GAN: Generative Adversarial Networks Based on Color Channel Using Discrete Wavelet Transform for Document Image Binarization
This work compares the performance of the proposed method with other state-of-the-art (SOTA) methods on DIBCO and H-DIBCO ((Handwritten) Document Image Binarization Competition) datasets.
Ranked #4 on
Binarization
on DIBCO 2013
Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy
We apply this strategy to SwinIR and present a new model, which named SwinOIR (Object Image Restoration Using Swin Transformer).
Ranked #9 on
Image Super-Resolution
on BSD100 - 3x upscaling
Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks
The efficient segmentation of foreground text information from the background in degraded color document images is a critical challenge in the preservation of ancient manuscripts.
Ranked #2 on
Binarization
on H-DIBCO 2018
Connection Reduction of DenseNet for Image Recognition
Baseline is a densely connected network, and the networks connected by the two new algorithms are named ShortNet1 and ShortNet2 respectively.
Ranked #3 on
Image Classification
on SVHN
(Percentage correct metric)
