Higher Studies: IIT Hyderabad Announces 3 New Industry-Oriented BTech Programmes  |  Leadership Instincts: Innovation Hub of IIT Hyderabad and ARAI sign MoU for India Specific AV Tech  |  International Edu News: Nobel Peace Prize Laureates of 20th Century  |  International Edu News: Nobel Peace Prize 2021 for Safeguarding Freedom of Expression  |  Finance: Nobel Prize-Economics: Empirical Modeling and Applications in Textile Industry  |  Science Innovations: Explaining Brown Dwarfs  |  Best Practices: ITIC Incubator at IIT Hyderabad to Promote Six Startups in Autonomous Navigation  |  Teacher Insights: Depressed Adolescents Muted in Reaction to Distressing Images  |  Leadership Instincts: A new Lab for Science in Diplomacy in Geneva  |  Parent Interventions: Parental Genes May Influence Child’s Educational Attainments  |  Education Information: Nobel Stories: a Throwback and Latest Updates   |  Teacher Insights: School Reopening: Online as well as Classroom Learning should go hand-in hand  |  Education Information: UCSF Starts New Organisation to Involve Students in Covid Research  |  International Edu News: Go Green, Go Paperless! Next-Gen Education goes Paperless.  |  National Edu News: Go Green, Go Paperless! Next-Gen Education goes Paperless.  |  
June 18, 2021 Friday 02:13:10 PM IST

Algorithm for Lensless Camera

Researchers at Indian Institute of Technology (IIT), Madras and US-based Rice University have together developed algorithms for lensless and miniature cameras. The deep learning algorithm is capable of producing photo-realistic images fro the blurred lensless capture. Lensless cameras have several applications including Augmented Reality (AR), Virtual Reality (VR), security, smart wearables and robotics where cost, form-factor, and weight become major constraints. Existing algorithms to deblur images based on traditional optimisation schemes yield low-resolution 'noisy images'. Kaushik Mitra, Department of Electrical Engineering, IIT-M and Prof Ashok Veeraraghavan of Rice University who led the team said that they used 'Deep Learning' to develop a reconstruction algorithm called FlatNet. This was tested on various real and challenges scenarios and found to be effective in de-blurring images.