A Photo enhancer with a brain

Roberto Saracco December 7, 2016 Blog 123 Views

I am passionate about photos and I have been using quite a few software for my digital darkroom.  I started by creating a real darkroom over 40 years ago to process film and print photos. At the turn of the century I jumped on digital and never turned back. 
Retouching, enhancing a photo may be quite simple or extremely tricky, it can take me a few seconds to click the "auto" button of a few hours to go deep into the pixels. It requires some "brain" activity first to imagine what you would like to see, then to manipulate pixels till you get what you are expecting often through trials and errors.
You need to get a feeling about the overall picture and then zoom into individual components, you need to single out a face and work on it independently of the rest of the photo or the other way ’round. 
Identifying objects is easy to our eyes, but it is quite complex for a computer. This is why I was curious, when I first saw Photo Lemur claim of using Artificial Intelligence to enhance photos, to try it out. 
I got the Beta version and I dug into it.
Photo Lemur let you perform some photo enhancement in a very easy way. You can have the program make colours more vibrant, straighten the horizon bent by lens , enhance the sky and remove haze, reduce noise and do some exposure compensation.
To do this Photo Lemur uses artificial intelligence in recognising the various components on a photo and applies specific enhancement to each of them. As an example, enhancements to the sky are not applied to the rest of the photo.  So far it is not really working of faces to enhance the skin, the eyes… but it will do so in the future.
There is a simple slider to let you "grade" the level of enhancement you want and you can immediately compare the original photo with the enhanced one.
Interestingly, the program learns on the way when its enhancements are successful (the enhanced photo is saved) or not. This way it learns both what people on the average consider a better photo and what you consider a better photo. Again this is an application of Artificial Intelligence.
I am not going to abandon my other tools for Photo Lemur, but I reckon it is doing a good job and for some quick enhancement I will likely use it. Over time, it may eventually win me out, once its brain will get a bit smarter, which I am sure will happen once it gets more experience.
I find this approach to use artificial intelligence to learn and become smarter by getting experience from thousands, millions of users the new wave in machine smartness, and I bet it will make a difference in the next decade.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.

Home | Contact & Support | Accessibility | Nondiscrimination Policy | IEEE Ethics Reporting | IEEE Privacy Policy | Terms
© Copyright 2024 IEEE – All rights reserved.
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.