Show simple item record

dc.contributor.authorSingh, Ankit
dc.contributor.authorChauhan, Vaishnavi
dc.contributor.authorRani, Sonia
dc.contributor.authorSingh, Brijesh
dc.date.accessioned2023-12-07T09:41:05Z
dc.date.available2023-12-07T09:41:05Z
dc.date.issued2023-06-06
dc.identifier.urihttp://10.10.11.6/handle/1/12287
dc.description.abstractComputer vision faces challenges when reconstructing images. in the proposed idea, we tried an attempt to enhance image quality by providing guidance to a deep residual convolutional neural network using pre-existing datasets. Our method leverages an efficient sub-pixel convolutional neural network (ESPCNN) [1] algorithm to turn the low-resolution (LR) images into high-resolution (HR) or super-resolution (SR) images. The ESPCNN algorithm is designed to enhance and enlarge images, resulting in high-resolution images that retain the original data. We employ a convolutional recurrent neural network (CRNN) [2]approach to reconstruct high-resolution images from under-sampled data, which can be useful in applications such as medical imaging, satellite imagery, and surveillance systems. The method we proposed addresses some of the limitations of techniques that use convolutional neural networks, such as FSRCNN[3] and SRCNN[4]. Through research, we determine the validity of our proposed model.en_US
dc.language.isoenen_US
dc.publisherGalgotias Universityen_US
dc.subjectESPCNN, image resolution, convolution neural network, pixelization.en_US
dc.titleInnovative Image Depixelizer using an Efficient Sub Pixel CNNen_US
dc.typeArticleen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record