ENHANCING IMAGES FOR COLOR VISION DEFICIENCY (CVD) USING DEEP LEARNING

Simple item page
creativework.keywordsDeep LearningDeep Learning
dc.contributor.advisorDr. Mohammad Ashrafuzzaman Khan (AZK)
dc.contributor.authorTANEEM AHMED
dc.contributor.authorSIDDHARTHA SANKAR SAHA
dc.contributor.authorMAHBUB MORSHED RIFAT
dc.contributor.id2013102042
dc.contributor.id2011567042
dc.contributor.id2011415042
dc.coverage.departmentElectrical and Computer Engineering
dc.date.accessioned2026-08-12
dc.date.accessioned2026-08-12T11:22:34Z
dc.date.available2026-08-12T11:22:34Z
dc.date.issued2024-04-30
dc.description.abstractIn a stunning world full of colors, color vision deficiency is the most common difficulty every human being faces. This problem still has no treatment. The subject of this research is to expose artificial intelligence methods as profound studies that aim at material, tangible visualization through images of color blindness in humanity, hence becoming a hope that technology will eventually fill the gap in color perception. The two AI models are the basis for creating and utilizing the project. The first model is Daltonization, which simulates the perception of color by different kinds of CVD and hence can create image transformations that specifically cater to one's eye problems. Secondly, A CNN-based Autoencoder model trains on various images taken under normal vision color conditions and color vision deficiency (CVD) conditions. Therefore, the aim is to create an autoencoder that will convert any image into a better-colored one that is clearly visible to individuals suffering from CVDs. The triumph of this task is determined by how well it performs in terms of two criteria. Quantitative measurements allow for an analysis of the degree to which the latest picture reproduces original images through methods like SSIM (Structural similarity index). User testing and feedback obtained by people suffering from CVD constitute quality appraisals for verifying the acceptability of changes made to their visual perception. We ensure that data collection and utilization are done per strict ethical principles to avoid violating privacy rights or obtaining participants' permission. The primary objective of using converted images is to adhere to and also maintain established accessibility standards for people with Color Vision Deficiency (CVD), therefore rendering them more manageable. The project focuses on user feedback and iterative design methods aimed at guaranteeing that the produced tools are intuitive and user-friendly for persons with low vision (CVD). These AI models work well on web browsers, mobile devices, or picture-editing tools. This project looks not only at improving the accessibility of images but also examines possible uses for the models in this field within augmented reality and virtual reality, amongst other emerging technologies. By improving how they see things while learning or working with it every day during their hours of relaxation at home, we hope that through our efforts, those suffering from CVD would experience an enhanced quality of life. "The exploration of AI will demonstrate how deep learning could come in handy in solving accessibility issues, hence pushing the field further. A user-friendly tool will be developed through this project, which should integrate its software or applications with existing platforms and workflow easily. The project asserts higher levels of inclusivity in visual design by increasing awareness and promotion. This project combines leading-edge AI tech and user-centered design principles, potentially changing how people with color vision deficiencies see objects.
dc.description.degreeUndergraduate
dc.identifier.cd600000603
dc.identifier.urihttps://repository.northsouth.edu/handle/123456789/1729
dc.language.isoen_US
dc.publisherNorth South University
dc.rights@ NSU Library
dc.titleENHANCING IMAGES FOR COLOR VISION DEFICIENCY (CVD) USING DEEP LEARNING
dc.typeProject
oaire.citation.endPage53
oaire.citation.startPage1
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
600000603 -abstract.pdf
Size:
418.1 KB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
600000603.pdf
Size:
2.63 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.93 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Theses - Undergraduate