DeepSR: A deep learning tool for image super resolution

Temiz, Hakan

doi:10.1016/j.softx.2022.101261

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same seed value was used in all studies to ensure reproducibility. Developments and all experiments were performed with the DeepSR [34] framework, which provides an integrated environment for all processes of the SR task-design, training, test, visualization, etc. The Tensorflow was chosen as the backend.…”

Section: Common Training Detailsmentioning

confidence: 99%

Enhancing the Resolution of Historical Ottoman Texts Using Deep Learning-Based Super-Resolution Techniques

Temiz¹

2023

View full text Add to dashboard Cite

The Ottoman Empire's extensive archives hold valuable insights into centuries of history, necessitating the preservation and transfer of this rich heritage to future generations. To facilitate access and analysis, numerous digitization efforts have been undertaken to transform these valuable resources into digital formats. The quality of digitized documents directly impacts the success of tasks such as text search, analysis, and character recognition. This study aims to enhance the resolution and overall image quality of Ottoman archive text images using four deep learning-based super-resolution (SR) algorithms: VDSR, SRCNN, DECUSR, and RED-Net. The performance of these algorithms was assessed using SSIM, PSNR, SCC, and VIF image quality measures (IQMs) and evaluated in terms of human visual system perception. All SR algorithms achieved promising IQM scores and a significant improvement in image quality. Experimental results demonstrate the potential of deep learning-based SR techniques in enhancing the resolution of historical Ottoman text images, paving the way for more accurate character recognition, text processing, and analysis of archival documents.

show abstract

Section: Common Training Detailsmentioning

confidence: 99%