Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 16 views

    Vision Robots Article

    Uploaded by

    Vamsi Reddy
    IISC scientists have found that neurons in the visual cortex of the brain dynamically process visual information over time to distinguish relevant from irrelevant variations in images. During the initial processing, neurons are sensitive to changes in viewpoint, but later ignore irrelevant stimuli. This transition allows the brain to recognize objects from different angles or perspectives. The researchers recorded neuronal activity in the monkey inferior temporal cortex, crucial for visual recognition. Their findings help explain how the brain achieves viewpoint invariance and suggest that computer vision algorithms have not achieved the human level of visual competence needed for real-world tasks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Vision Robots Article

    Uploaded by

    Vamsi Reddy
    16 views1 page
    IISC scientists have found that neurons in the visual cortex of the brain dynamically process visual information over time to distinguish relevant from irrelevant variations in images. During the initial processing, neurons are sensitive to changes in viewpoint, but later ignore irrelevant stimuli. This transition allows the brain to recognize objects from different angles or perspectives. The researchers recorded neuronal activity in the monkey inferior temporal cortex, crucial for visual recognition. Their findings help explain how the brain achieves viewpoint invariance and suggest that computer vision algorithms have not achieved the human level of visual competence needed for real-world tasks.

    Original Description:

    Robots

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    IISC scientists have found that neurons in the visual cortex of the brain dynamically process visual information over time to distinguish relevant from irrelevant variations in images. During the initial processing, neurons are sensitive to changes in viewpoint, but later ignore irrelevant stimuli. This transition allows the brain to recognize objects from different angles or perspectives. The researchers recorded neuronal activity in the monkey inferior temporal cortex, crucial for visual recognition. Their findings help explain how the brain achieves viewpoint invariance and suggest that computer vision algorithms have not achieved the human level of visual competence needed for real-world tasks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    16 views1 page

    Vision Robots Article

    Uploaded by

    Vamsi Reddy
    IISC scientists have found that neurons in the visual cortex of the brain dynamically process visual information over time to distinguish relevant from irrelevant variations in images. During the initial processing, neurons are sensitive to changes in viewpoint, but later ignore irrelevant stimuli. This transition allows the brain to recognize objects from different angles or perspectives. The researchers recorded neuronal activity in the monkey inferior temporal cortex, crucial for visual recognition. Their findings help explain how the brain achieves viewpoint invariance and suggest that computer vision algorithms have not achieved the human level of visual competence needed for real-world tasks.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 1

    1 of 1

    http://epaperbeta.timesofindia.com/Article.aspx?eid=31806&articlexml=...

    The Times of India


    Title : IISC RESEARCH - Why robots can't beat us in vision
    Author :
    Location :
    Bengaluru:
    Article Date : 02/03/2015
    Will intelligent robots replace humans some day? A team of scientists from Indian Institute of Science,
    Bengaluru, believes it won't happen anytime soon.
    This is because even the best computer algorithms can't do simple visual tasks like recognizing distorted
    letters. It is a known fact that the eye works much like a camera with neurons leaving the retina carrying
    information about the image to visual areas in the brain. Now, IISc scientists have thrown more light on what
    makes our brain so good in its vision mechanism.
    Dr SP Arun and his team, studying biological vision at the Centre for Neuroscience, IISc, ventured to find
    how the vision mechanism in humans sifts between relevant and irrelevant information from the various
    images that fall on the retina. One object can produce different images due to changes in lighting, size,
    position and three-dimensional rotations. Neurons in the visual cortex compute this. Flashing an image
    results in neural activity that builds up and drops over a period of time. During the build-up of the response,
    neurons are sensitive to irrelevant variations such as changes in the view point of an object. But during the
    drop, neurons ignore irrelevant stimuli, said Arun.
    Ratan Murty, another member of the team, said, This transition has never been shown before, and our study
    shows that neurons in this area perform this important computation dynamically over time, he added.
    The team performed recordings from the inferior temporal cortex of the monkey brain -an area crucial for
    visual object recognition.Neurons leaving the retina carry information about the image to the visual areas in
    the brain, which occupy as much as 40% of the total real estate in the brain.
    Our experiments will help understand viewpoint invariance better, something that the brain has learned to
    solve over the course of evolution. Robots may beat us at algorithmic games like chess but they are nowhere
    near human competence in real-world tasks like vision, added Arun.

    2/4/2015 12:16 AM

    You might also like