Individuals with color vision deficiency (CVD) often encounter challenges in navigating and interacting with their environment due to limitations in perceiving colors accurately. This deficiency can impede various daily tasks and activities, leading to dependency on others for assistance with color-related tasks and potentially limiting independence and inclusivity. Addressing these challenges, our research focuses on the development of a machine learning-based color transformation system. Leveraging TensorFlow and Keras frameworks, the system employs advanced machine learning techniques to identify and transform colors within images, ultimately enhancing visibility for individuals with CVD. The primary objective is to empower individuals with CVD by providing a real-world tool that improves color visibility in images and enables self-assessment of their condition. This solution aims to enhance navigation, reduce dependency on others for color-related tasks, and foster inclusivity through technological innovation. Additionally, our research emphasizes the accuracy and reliability of the machine learning models through rigorous testing and validation procedures, ensuring effectiveness across various scenarios and image types. An intuitive and user-friendly graphical user interface (GUI) is prioritized to cater to individuals with diverse technical abilities. Beyond its immediate impact, the research seeks to raise awareness and promote understanding of color vision deficiency within the broader community, ultimately contributing to a more equitable and accessible society for all.
Nazneen Pendhari, Danish Shaikh, Nida Shaikh, Abdul Gaffar Nagori
University of Mumbai, India
Color Vision Deficiency (CVD), Machine Learning, Image Processing, Social Impact, Keras
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 0 | 0 | 0 | 12 | 8 | 2 | 0 | 3 | 3 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 14 , Issue: 4 , Pages: 3282 - 3292 )
Date of Publication :
May 2024
Page Views :
212
Full Text Views :
28
|