Now YOU can turn black and white images and old family portraits into COLOUR photos with a free AI app that uses machine learning to transform historical snaps in seconds

  • ColouriseSG can turn old black and white photographs into images with full colour in seconds 
  • The online tool was developed to provide Singapore with a viable and easy colourisation tool  
  • It has no way of knowing what the original colours should be but is designed to give a best estimate 
  • Send Joe Pinkstone your black and white pictures with details of who is in them and when and where they were taken and we can colourise them for you! email joe.pinkstone@mailonline.co.uk 

Advertisement

An online tool has been unveiled which is capable of bringing black and white photographs to life instantaneously by adding colour to them using artificial intelligence

Colourisation of old images is a normally time consuming process which requires specialist training and expensive software.

The tool, ColouriseSG, is able to do it for free from only a single digital image and works on iconic historical photographs and old family portraits. 

Try it for yourself here or via the interactive tool below. 

Slide me

The artificial intelligence is able to colourise images for free from only a single digital image and works on iconic historical photographs and old family portraits. Pictured is Rose Williams posing with her son Billy Williams in circa 1944 

Slide me

Existing software, such as Algorithmia, was trained using 1.3 million images from ImageNet, a database of photographs developed in the US by researchers at Stanford University and Princeton University. The free-to-use AI was trained on a wider range of images. Pictured is Katharine (left) and Maria Kinsella (right) circa 1958 

It is trained on a back catalogue of old images and uses machine learning to guess what it thinks the image would have looked like in colour. 

'The purpose of colourisation is to generate an image with colours that are plausible,' the tool's developers claim.  

'It by no means guarantees that the colourised image is an accurate representation of the actual snapshot in time.'

It is also more adept at colourising images of human subjects with natural landscape and can struggle with more complex pictures. 

The free-to-use tool was developed to provide an accurate way for people from Singapore to edit their monochrome images. 

Existing software, such as Algorithmia, are trained using 1.3 million images from ImageNet, a database of photographs developed in the US by researchers at Stanford University and Princeton University.

The idea of ColouriseSG was to provide a large enough data-set to be relevant to the residents of Singapore. 

It is effective at colourising images and works better for high-resolution images but appears to provide a sepia effect opposed to a true life-like colouration. 

Tech firm NVIDIA have released several different image editing tools that are powered by artificial intelligence. 

DOES THE AI COLOURISER WORK FOR YOU? 

Journalist Stephen Matthews uploaded a black and white picture of himself as a child, taken in around 2000. He remembers the colour of his jumper and says the AI tool, while impressive, does not prove entirely accurate.

He said: 'The tool did not appear to work on the black-and-white picture of me as a child, despite proving more successful for the more historical snaps.

'Instead of showing my primary school jumper as a vibrant yellow, it depicts it as being somewhat a mix of pink and grey. The navy blue symbol also appears black.

'You can tell the polo shirt I was wearing at the time was white, though my skin is arguably much more tanned than it would have been at the time.

'The picture was taken in around 2000, when I was six years old. My parents say they were not offered the option of having the photograph in colour.'  

Advertisement
Slide me

Pictured is Stephen Matthews circa 2000. An online tool has been unveiled which is capable of bringing black and white photographs to life instantaneously by adding colour to them using artificial intelligence

Slide me

This vintage photograph from Edwardian era features two teenage girls at the seaside, one with a Lifebuoy round her neck, circa 1910. The AI-powered technology colourises monochrome images in seconds 

Slide me

A group portrait of a policeman and his family, Warwickshire, 1905. A uniformed policeman poses with his wife and baby outside an unidentified house

Slide me

An European migrant boy is held by his mother on ship arriving in New York Harbour with the lower Manhattan skyline in background in June 1950. The developers say the purpose of colourisation is to generate an image with colours that are plausible and not necessarily an accurate representation of the actual snapshot in time

Slide me

1950s family of four walking towards the camera with baskets, beach balls and an umbrella in tow. The free-to-use tool was initially developed to provide an accurate way for people from Singapore to edit their monochrome images

Slide me

A 1950s American family pictured by a riverside enjoying a picnic. The image was colourised and edited using the tool available at www.colourise.sg and  says it learns form a database of images how a black and white photograph may have looked if it was taken in colour 

Slide me

Female child with mother and aunt in 1951. It is more adept at colourising images of human subjects with natural landscape and can struggle with more complex pictures

Slide me

Crowds in punts on the Thames watching the Henley Regatta showing off the fashion of the day. Colourisation of old images is a normally time consuming process which requires specialist training and expensive software but the online tool is a far quicker method 

Its latest release is software which uses deep-learning to elevate even the roughest sketches into works of art.

WHAT IS MACHINE LEARNING?

Artificial intelligence systems rely on neural networks, which try to simulate the way the brain works in order to learn.

These networks can be trained to recognise patterns in information - including speech, text data, or visual images - and are the basis for a large number of the developments in AI.

They use input from the digital world to learn, with practical applications like Google's language translation services, Facebook's facial recognition software and Snapchat's image altering live filters.

But the process of inputting this data can be extremely time consuming, and is limited to one type of knowledge.

Advertisement

The new program, dubbed GauGAN, after famous French impressionist Paul Gaugin, uses a tool called generative adversarial networks (GAN) to interpret simple lines and convert them into hyper-realistic images.

Its application could help professionals across a range of disciplines such as architecture and urban planning render images and visualisations faster and with greater accuracy, according to the company.

'It's much easier to brainstorm designs with simple sketches, and this technology is able to convert sketches into highly realistic images,' said Bryan Catanzaro, vice president of applied deep learning research at NVIDIA.

What separates GauGAN from other rendering software, beyond its seemingly simple interface and application, is just how the tool was developed.

According to NVIDIA, GauGAN was trained to mimic different types of landscapes by employing the use of deep-learning software to pore over 1 million different images.  

Tech firm NVIDIA have released several different image editing tools that are powered by artificial intelligence.  Its latest release is software which uses deep-learning to elevate even the roughest sketches into works of art. The new program, dubbed GauGAN, after famous French impressionist Paul Gaugin, uses a tool called generative adversarial networks (GAN) to interpret simple lines and convert them into hyper-realistic images

Tech firm NVIDIA have released several different image editing tools that are powered by artificial intelligence.  Its latest release is software which uses deep-learning to elevate even the roughest sketches into works of art. The new program, dubbed GauGAN, after famous French impressionist Paul Gaugin, uses a tool called generative adversarial networks (GAN) to interpret simple lines and convert them into hyper-realistic images

The comments below have not been moderated.

The views expressed in the contents above are those of our users and do not necessarily reflect the views of MailOnline.

We are no longer accepting comments on this article.