Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework
With the recent rise in the development of deep learning techniques, image inpainting—the process of restoring missing or corrupted regions in images—has witnessed significant advancements. Although state-of-the-art models are effective, they often fail to inpaint complex missing areas, especially w...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/1/176 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549173258715136 |
|---|---|
| author | Somanka Maiti Shabari Nath Panuganti Gaurav Bhatnagar Jonathan Wu |
| author_facet | Somanka Maiti Shabari Nath Panuganti Gaurav Bhatnagar Jonathan Wu |
| author_sort | Somanka Maiti |
| collection | DOAJ |
| description | With the recent rise in the development of deep learning techniques, image inpainting—the process of restoring missing or corrupted regions in images—has witnessed significant advancements. Although state-of-the-art models are effective, they often fail to inpaint complex missing areas, especially when handwritten occlusions are present in the image. To address this issue, an image inpainting model based on a residual CycleGAN is proposed. The generator takes as input the image occluded by handwritten missing patches and generates a restored image, which the discriminator then compares with the original ground truth image to determine whether it is real or fake. An adversarial trade-off between the generator and discriminator motivates the model to improve its training and produce a superior reconstructed image. Extensive experiments and analyses confirm that the proposed method generates inpainted images with superior visual quality and outperforms state-of-the-art deep learning approaches. |
| format | Article |
| id | doaj-art-ba5db8362f1e4b7c82dd39e1a2207013 |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-ba5db8362f1e4b7c82dd39e1a22070132025-01-10T13:18:31ZengMDPI AGMathematics2227-73902025-01-0113117610.3390/math13010176Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN FrameworkSomanka Maiti0Shabari Nath Panuganti1Gaurav Bhatnagar2Jonathan Wu3Department of Mathematics, Indian Institute of Technology Jodhpur, Karwar, Jodhpur 342030, Rajasthan, IndiaDepartment of Electrical Engineering, Indian Institute of Technology Jodhpur, Karwar, Jodhpur 342030, Rajasthan, IndiaDepartment of Mathematics, Indian Institute of Technology Jodhpur, Karwar, Jodhpur 342030, Rajasthan, IndiaDepartment of Electrical and Computer Engineering, University of Windsor, 401 Sunset Ave, Windsor, ON N9B 3P4, CanadaWith the recent rise in the development of deep learning techniques, image inpainting—the process of restoring missing or corrupted regions in images—has witnessed significant advancements. Although state-of-the-art models are effective, they often fail to inpaint complex missing areas, especially when handwritten occlusions are present in the image. To address this issue, an image inpainting model based on a residual CycleGAN is proposed. The generator takes as input the image occluded by handwritten missing patches and generates a restored image, which the discriminator then compares with the original ground truth image to determine whether it is real or fake. An adversarial trade-off between the generator and discriminator motivates the model to improve its training and produce a superior reconstructed image. Extensive experiments and analyses confirm that the proposed method generates inpainted images with superior visual quality and outperforms state-of-the-art deep learning approaches.https://www.mdpi.com/2227-7390/13/1/176image inpaintinghandwritten textdeep learningCycleGAN |
| spellingShingle | Somanka Maiti Shabari Nath Panuganti Gaurav Bhatnagar Jonathan Wu Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework Mathematics image inpainting handwritten text deep learning CycleGAN |
| title | Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework |
| title_full | Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework |
| title_fullStr | Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework |
| title_full_unstemmed | Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework |
| title_short | Efficient Image Inpainting for Handwritten Text Removal Using CycleGAN Framework |
| title_sort | efficient image inpainting for handwritten text removal using cyclegan framework |
| topic | image inpainting handwritten text deep learning CycleGAN |
| url | https://www.mdpi.com/2227-7390/13/1/176 |
| work_keys_str_mv | AT somankamaiti efficientimageinpaintingforhandwrittentextremovalusingcycleganframework AT shabarinathpanuganti efficientimageinpaintingforhandwrittentextremovalusingcycleganframework AT gauravbhatnagar efficientimageinpaintingforhandwrittentextremovalusingcycleganframework AT jonathanwu efficientimageinpaintingforhandwrittentextremovalusingcycleganframework |