To help colourblind people see colours, Surat tech student develops technique
Padmawar's research focuses on improving the visual experience for individuals with Colour Vision Deficiency (CVD), popularly known as colour blindness, a condition that affects around eight per cent of the global male population and 0.4 per cent of women and girls.
People with CVD often find it difficult to distinguish between certain colour combinations, especially red and green, or blue and yellow, which can make it challenging to interpret traffic lights, educational charts, websites and more.
Padmawar, a student of Computer Science, developed an algorithm which can help people to see a wider range of colours. 'This can be used on the screens of gadgets. In the future, such techniques can be used in smart eyeglasses, allowing people to enjoy seeing different colours. I thought about helping people in the medical field. I chose the topic as it came under our subject project. I worked for five to six hours a day for five months on this topic,' she told The Indian Express.
According to Padmawar, 'By applying recolouration techniques, we aim to separate red and green hues effectively, enhancing distinguishing while maintaining visual naturalness. The ability to perceive colours arises from the complex interaction of light with the human visual system, particularly the retina cone cells. Any disruption in this process can lead to colour vision deficiencies that impact a person's daily activities and overall quality of life.'
The paper — titled 'Colourblind-Friendly Image Recolouring Using Generative Adversarial Networks' — was prepared under the guidance of associate professor Dr Chandra Prakash.
Sources said that out of 440 submissions from across the country to the OPJU International Technology Conference, her paper was chosen among the top 35 before it went on to receive the Best Paper Award.
The paper notes how colour blindness often goes unnoticed for years because people with the condition may adapt to their environment without realising that they perceive colours differently. This is especially true for mild to moderate forms of CVD, where individuals may only have trouble distinguishing specific colours, such as red and green or blue and yellow.
Human colour vision relies on three types of cone cells in the retina L-cones (sensitive to long wavelengths, associated with red), M-cones (sensitive to medium wavelengths, linked to green), and S-cones (sensitive to medium wavelengths, related to blue).
Dr Chandra Prakash said, 'In dichromatism, the absence of one type of cone limits colour perception…. Protanopia results from the absence of L-cones, while deuteranopia arises from the absence of M-cones. This leads to a significant overlap in perceived red and green hues, which diminishes contrast. For individuals with Protanopia or Deuteranopia, the red-green opponent channel is severely impaired.'
'Our study addresses these deficiencies, particularly for Protanopia and Deuteranopia. These conditions affect red-green differentiation, creating challenges in distinguishing colours in natural and artificial scenes,' Dr Prakash said.
Padmawar further said, '… Our methodology consists of three parts: simulating dichromatic vision, recolouring using linear transformation techniques, and generalising recolouration for unseen images using a GAN-based approach. Every phase is intended to address a different facet of improving dichromatic people's visual perception.'
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
New Indian Express
12-07-2025
- New Indian Express
Deal with proven culprits for sudden cardiac deaths in Karnataka's Hassan district than the unproven
Twenty-four 'sudden' deaths over 40 days in May-June this year in Hassan district, suspected to be due to cardiac issues, have sent shock waves across the state. Of these deaths, 14 were aged under-45 while 10 were over that age. Even before the facts behind the deaths were established, a section of experts, politicians and the general public jumped the gun to speculate that the sudden increase in cardiac deaths was due to Covid-19 vaccine-induced clotting, affecting the cardiovascular system. The Karnataka government ordered an investigation into the deaths by the Director, Sri Jayadeva Institute of Cardiovascular Sciences (SJICS), Bengaluru. The probe report, which came out on July 10, concluded that the deaths did not indicate any increase in sudden cardiac deaths in the district. It was almost the same as in the previous months in Hassan district. Analysis of cardiac cases data at SJICS, Bengaluru, and its peripheral centres in Mysuru and Kalaburagi, in the last six months also did not show any increasing trends in cardiac deaths. The report also stated that definitive conclusions about cause of deaths in each case were limited due to lack of autopsy data, clinical data and limited history from family members. However, it did note that the occurrences of sudden deaths in younger adults underscored the growing burden of premature cardiovascular disease. The report called for early cardiovascular screening programs and health education, and establishing mandatory investigation protocols (including post-mortems) for all sudden deaths in apparently healthy young adults. The deaths in Hassan districts have rattled many. But it must be remembered that cardiovascular disease (CVD) has been a major health concern – in fact at epidemic proportions – not only in Karnataka, but across India, from much before the Covid-19 pandemic and the vaccines came on the scene. Moreover, international studies have failed to conclusively prove a link between the Covid-19 vaccines and cardiac-related incidents or deaths.
Time of India
08-07-2025
- Time of India
IEEE I2ITCON 2025 recognizes cutting-edge research with best paper awards
PUNE: The IEEE I2ITCON 2025 conference, technically co-sponsored by the IEEE Pune Section, concluded on a high note on July 5 at The Hope Foundation and Research Centre - International Institute of Information Technology (I²IT), Pune. The prestigious two-day event, held on July 4 and 5, brought together leading researchers, academicians, and industry experts from across the globe to showcase and deliberate on innovations in AI, computing, and emerging technologies, a statement issues hy the organisers said. This year, the conference witnessed an overwhelming response, with over 2,500 paper submissions from researchers worldwide. Out of these, 236 papers were shortlisted and presented across various technical tracks. In a keenly awaited valedictory session, four outstanding papers were conferred with the coveted Best Paper Award, recognizing exemplary contributions in advancing technology and research. You Can Also Check: Pune AQI | Weather in Pune | Bank Holidays in Pune | Public Holidays in Pune In the AI, ML & Deep Learning track, the paper titled 'GovernAI: Policy-Driven Model Governance for Dynamic and Multi-Tenant AI Systems', authored by Sana Zia Hassan, Karan Alang, Nagarjuna Nellutla, Shrinivass Arunachalam Balasubramanian, and Vamshidhar Morusu, was awarded for its pioneering approach to managing AI systems in complex, multi-tenant environments. by Taboola by Taboola Sponsored Links Sponsored Links Promoted Links Promoted Links You May Like An engineer reveals: One simple trick to get internet without a subscription Techno Mag Learn More Undo Another paper from the same track, 'Differentially Private Pipelines: Practical Approaches for Large-Scale Feature Stores', by Pooja Devaraju, Satya Manesh Veerapaneni, Ram Ghadiyaram, Jaya Eripilla, and Sudeep Acharya, was recognized for its innovative techniques ensuring privacy in large-scale AI data pipelines. In the Computing Technologies track, the award-winning paper 'A Framework for Intelligent Cloud Systems: Enabling Secure, Policy-Driven, and Sustainable AI at Scale', authored by Lakshman Kumar Jamili, Sumeer Basha Peta, Ranganath Nagesh Taware, Balaji Krishnan, and Srikanth Perla, impressed the jury with its vision for scalable and secure AI deployments. Another paper titled 'Training AI to Simulate Reality Through Self-Constructed Representations', by Rohan Shahane, Shazia Hassan, Nandita Giri, Sashi Kiran Kaata, and Vijayakumar Krishnapillai, was honored for its innovative approach to bridging the gap between AI learning and real-world simulations. The conference underscored Pune's growing prominence as a hub for technological innovation and research, providing a robust platform for knowledge exchange and collaboration. With its diverse and forward-looking discussions, IEEE I2ITCON 2025 reaffirmed its commitment to shaping the future of technology.
Indian Express
01-07-2025
- Indian Express
To help colourblind people see colours, Surat tech student develops technique
An MTech student of Sardar Vallabhbhai National Institute of Technology (SVNIT), Surat, has won an award for developing an image recolouring technique to help people with colour blindness. Saakshi Padmawar's research paper was selected for the best paper award at the OPJU International Technology Conference, held at O P Jindal University, Chhattisgarh, recently. Padmawar's research focuses on improving the visual experience for individuals with Colour Vision Deficiency (CVD), popularly known as colour blindness, a condition that affects around eight per cent of the global male population and 0.4 per cent of women and girls. People with CVD often find it difficult to distinguish between certain colour combinations, especially red and green, or blue and yellow, which can make it challenging to interpret traffic lights, educational charts, websites and more. Padmawar, a student of Computer Science, developed an algorithm which can help people to see a wider range of colours. 'This can be used on the screens of gadgets. In the future, such techniques can be used in smart eyeglasses, allowing people to enjoy seeing different colours. I thought about helping people in the medical field. I chose the topic as it came under our subject project. I worked for five to six hours a day for five months on this topic,' she told The Indian Express. According to Padmawar, 'By applying recolouration techniques, we aim to separate red and green hues effectively, enhancing distinguishing while maintaining visual naturalness. The ability to perceive colours arises from the complex interaction of light with the human visual system, particularly the retina cone cells. Any disruption in this process can lead to colour vision deficiencies that impact a person's daily activities and overall quality of life.' The paper — titled 'Colourblind-Friendly Image Recolouring Using Generative Adversarial Networks' — was prepared under the guidance of associate professor Dr Chandra Prakash. Sources said that out of 440 submissions from across the country to the OPJU International Technology Conference, her paper was chosen among the top 35 before it went on to receive the Best Paper Award. The paper notes how colour blindness often goes unnoticed for years because people with the condition may adapt to their environment without realising that they perceive colours differently. This is especially true for mild to moderate forms of CVD, where individuals may only have trouble distinguishing specific colours, such as red and green or blue and yellow. Human colour vision relies on three types of cone cells in the retina L-cones (sensitive to long wavelengths, associated with red), M-cones (sensitive to medium wavelengths, linked to green), and S-cones (sensitive to medium wavelengths, related to blue). Dr Chandra Prakash said, 'In dichromatism, the absence of one type of cone limits colour perception…. Protanopia results from the absence of L-cones, while deuteranopia arises from the absence of M-cones. This leads to a significant overlap in perceived red and green hues, which diminishes contrast. For individuals with Protanopia or Deuteranopia, the red-green opponent channel is severely impaired.' 'Our study addresses these deficiencies, particularly for Protanopia and Deuteranopia. These conditions affect red-green differentiation, creating challenges in distinguishing colours in natural and artificial scenes,' Dr Prakash said. Padmawar further said, '… Our methodology consists of three parts: simulating dichromatic vision, recolouring using linear transformation techniques, and generalising recolouration for unseen images using a GAN-based approach. Every phase is intended to address a different facet of improving dichromatic people's visual perception.'
