AI finally understands primitive sketches – aka marketing presentations

Welcome to our Hell, computers


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 http://arxiv.org/pdf/1501.07873v2.pdf

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). ®

Similar topics


Other stories you might like

  • It's primed and full of fuel, the James Webb Space Telescope is ready to be packed up prior to launch

    Fingers crossed the telescope will finally take to space on 22 December

    Engineers have finished pumping the James Webb Space Telescope with fuel, and are now preparing to carefully place the folded instrument inside the top of a rocket, expected to blast off later this month.

    “Propellant tanks were filled separately with 79.5 [liters] of dinitrogen tetroxide oxidiser and 159 [liters of] hydrazine,” the European Space Agency confirmed on Monday. “Oxidiser improves the burn efficiency of the hydrazine fuel.” The fuelling process took ten days and finished on 3 December.

    All eyes are on the JWST as it enters the last leg of its journey to space; astronomers have been waiting for this moment since development for the world’s largest space telescope began in 1996.

    Continue reading
  • China to upgrade mainstream RISC-V chips every six months

    Home-baked silicon is the way forward

    China is gut punching Moore's Law and the roughly one-year cadence for major chip releases adopted by the Intel, AMD, Nvidia and others.

    The government-backed Chinese Academy of Sciences, which is developing open-source RISC-V performance processor, says it will release major design upgrades every six months. CAS is hoping that the accelerated release of chip designs will build up momentum and support for its open-source project.

    RISC-V is based on an open-source instruction architecture, and is royalty free, meaning companies can adopt designs without paying licensing fees.

    Continue reading
  • The SEC is investigating whistleblower claims that Tesla was reckless as its solar panels go up in smoke

    Tens of thousands of homeowners and hundreds of businesses were at risk, lawsuit claims

    The Securities and Exchange Commission has launched an investigation into whether Tesla failed to tell investors and customers about the fire risks of its faulty solar panels.

    Whistleblower and ex-employee, Steven Henkes, accused the company of flouting safety issues in a complaint with the SEC in 2019. He filed a freedom of information request to regulators and asked to see records relating to the case in September, earlier this year. An SEC official declined to hand over documents, and confirmed its probe into the company is still in progress.

    “We have confirmed with Division of Enforcement staff that the investigation from which you seek records is still active and ongoing," a letter from the SEC said in a reply to Henkes’ request, according to Reuters. Active SEC complaints and investigations are typically confidential. “The SEC does not comment on the existence or nonexistence of a possible investigation,” a spokesperson from the regulatory agency told The Register.

    Continue reading

Biting the hand that feeds IT © 1998–2021