Image Processing

The "MANUU: Handwritten Urdu OCR Dataset" is an extensive and meticulously curated collection to advance OCR (Optical Character Recognition) for handwritten Urdu letters, digits, and words. The compilation of the dataset has been conducted methodically, ensuring that it encompasses a wide variety of handwritten instances. This comprehensive collection enables the construction and assessment of strong models for Optical Character Recognition (OCR) systems specifically designed for the complexities of the Urdu script.

Categories:
128 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
39 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
17 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
21 Views

To test the feasibility of the idea: Using the processed data of sentinel-2 and GlobeLand30 as the input image and ground truth of subspace clustering for land cover classification, a dataset named 'MSI_Gwadar' is created.

'MSI_Gwadar' is a multi-spectral remote sensing image of Gwadar (town and seaport, southwestern Pakistan) and its four regions of interest, which includes MATLAB data files and ground truth files of the study area and its four regions of interest.

 

Categories:
176 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
20 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
22 Views

VSR-QAD-3Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
32 Views

The dataset is a validation dataset for low-light image enhancement and noise reduction tasks. The dataset contains triples of images: low-light images, target images and low-light enhanced images. We used this dataset to generate results for the manuscript "Adaptive Guided Upsampling for Low-light Image Enhancement" submitted to IEEE ACCESS for review. The dataset allows other researchers to work our material. 

Categories:
22 Views

Video super-resolution (SR) has important real world applications such as enhancing viewing experiences of legacy low-resolution videos on high resolution display devices. However, there are no visual quality assessment (VQA) models specifically designed for evaluating SR videos while such models are crucially important both for advancing video SR algorithms and for viewing quality assurance. Therefore, we establish a super-resolution video quality assessment database (VSR-QAD) for implementing super-resolution video quality assessment.

Categories:
21 Views

Pages