AI finally understands primitive sketches – aka marketing presentations

Welcome to our Hell, computers

24 Reg comments Got Tips?

Artificial intelligence scientists have developed a neural-network that understands incomprehensible scrawled drawings of the sort created by children, marketing departments, architects, design creatives, and so on.

The academic developers of the "Sketch-a-Net" software proudly boast that their brainchild is actually better at working out the meaning of such primitive scrawls than normal humans.

“It’s exciting that our computer program can solve the task even better than humans can," enthuses Timothy Hospedales, a specialist in Neuroinformatics at Queen Mary's in London. "Sketches are an interesting area to study because they have been used since pre-historic times for communication and now, with the increase in use of touchscreens, they are becoming a much more common communication tool again."

Credit: Yang, Song, Xiang, Hospedales

Get me a child of three in here, I can't make head or tail of this

Sketch-a-Net is a so-called deep neural network, an application designed to simulate the way human brains work. We are told:

The program is capable of correctly identifying the subject of sketches 74.9 per cent of the time compared to humans that only managed a success rate of 73.1 per cent ... the program [also] performed better at determining finer details in sketches. For example, it was able to successfully distinguish the specific bird variants "seagull", "flying-bird", "standing-bird" and "pigeon" with 42.5 per cent accuracy compared to humans that only achieved 24.8 per cent.

Unfortunately it seems that Sketch-a-Net can't be applied retrospectively to such things as ancient cave art, finger paintings or similar. It seemingly achieves its improved results by exploiting the fact that it knows what order the lines in sketches were drawn, which means it is primarily suited to interpreting pictures scribbled on touchscreens, electronic whiteboards and similar devices.

Hospedales and his colleagues see such kit being used to carry out internet or database searches by means of sketch input (a boon for pornography searches, clearly) or to match mugshots or CCTV pics to portraits drawn by police artists.

It seems at least as likely, however, that it will be used by bemused executives to work out what in hell the guys from marketing were trying to convey in their last presentation, or engineers attempting to extract information from excitingly chunky imagery produced by architects or design departments.

The research is to be presented at the 26th British Machine Vision Conference on Tuesday 8 September 2015, and can be read in full here (PDF). ®


Keep Reading

Machine-learning models trained on pre-COVID data are now completely out of whack, says Gartner

That AI-powered product and price recommendation engine? Useless now

Want to hear our beloved David Attenborough narrate your life? Thanks to the power of machine learning, you can

In brief Plus: AI app for the visually impaired – and Clearview lawyers up

Machine learning helps geoboffins spot huge beds of hot rocks 1,000km across deep below Earth's surface

Large structures were detected as anomalies in seismic waves processed by an algorithm

So many stars, so little time: Machine learning helps astroboffins spot the most oxygen-starved galaxy yet

Don't bother packing your bags for HSC J1631+4426 just yet, it's 430 million light years away

AI in the enterprise: AI may as well stand for automatic idiot – but that doesn't mean all machine learning is bad

Register Debate Is AI just a rebrand of yesterday's dumb algorithms? We present the argument against this motion – and don't forget to vote

Hey, Sparky: Confused by data science governance and security in the cloud? Databricks promises to ease machine learning pipelines

You know the one, that pothole ridden journey from on-prem to the fluffy white stuff

AI startup accuses Facebook of stealing code designed to speed up machine learning models on ordinary CPUs

Neural Magic claims algos in social network's open-source compiler on GitHub look awfully familiar

Europe is falling behind in AI, we need to launch our second machine learning-powered satellite soon, says ESA

Hot on the heels of ɸ-sat-1, the space agency is planning to launch ɸ-sat-2

Biting the hand that feeds IT © 1998–2020