Feed on
Posts
Comments

Sample analysis of visual magnetism in an advertisement from Olay. Warmer colours denote more magnetic parts of the image, and are more likely to attract attention.

In an ever increasingly complex and crowded visual environment, what do we actually pay attention to? As all should know by now, visual attention comes in at least two specific forms: bottom-up and top-down.

While top-down attention is typically viewed as volitional, effortful and motivated, bottom-up attention is the term for conditions in which sensory stimuli automatically attract attention. One way to conceptualise this, especially in terms of vision, is visual magnetism. A magnetic item is a piece of information that has specific properties that inherently attract attention more or less automatically. This could be due to intensity, specific colouring, positioning or overt changes in e.g. an image.

Eye-tracking is known to measure visual attention, but part of the limitation of this method is that it has a hard time in disambiguating between top-down and bottom-up attention.

But there is is (obviously) good news: I’ve devised a method that can determine visual magnetism in an image. By relying on decades of research on the visual system – and a decent amount of time gone in testing, adjusting and validating models, I have made an analytic tool that models visual attention to a degree that it is almost spooky.

Yes, you read right: you can now know where people will look, even without testing a single subject.

The method is (somewhat humouristically) labelled eye2D2, and you can go to this page to see more documentation emerging these days.

The model has been tested against eye-tracking studies of many different kinds of images, including ads, outdoor banners, in-store layouts, newspaper layouts, and much much more.

The method has an accuracy that is 80% compared to traditional eye-tracking. It can do the analysis at a fraction of the time (hours) and cost (5 images = $10.000). This is a huge improvement compared to traditional eye-tracking which uses 2-4 weeks (or more) and at a much higher price ($20.000 per image). Even better, since eye2D2 does not remember images, one can run multiple versions/tweaks of the same image

Below you can see some direct comparisons between traditional eye-tracking (left) and the new automatic measure of visual magnetism (right).

Want to know more? Visit www.eye2D2.com or write me an email.

-Thomas

Inline images 1

Inline images 2
Inline images 3
Inline images 4
Inline images 5
Inline images 6
Inline images 7

7 Responses to “Visual magnetism – what draws you into an image?”

  1. Daniel Castro says:

    Hi,

    Thanks for the publication; however
    It does not contain highlights on what are the
    Elements generating visual magnetism or drawing the visual attention,

    What are them in your knowledge ?

  2. tzramsoy says:

    Hi Daniel,

    Thanks for your interest and comment!

    In the model, visual magnetism is defined by the elements in the picture that are known to attract attention based on their low-level features. This means that it is not about recognition of faces or words, but more basic than this. The elements include colour, brightness and contrast, and several other parameters that point to specific items in relation to the complex visual images that we see in e.g. ads and store layouts. The actual combination is proprietary and has been established through multiple validation trials with hundreds of images of this kind.

    Put simply, this model predicts very accurately what parts of images will get initial attention. One example is very simple: what will people notice in the few seconds they visit a webpage? This tool will have a very high accuracy on this, but at the fraction of the time and cost.

    I believe it should be used in any kind of process where we want to know what people pay attention to in a visual display. This could be in ads, webpages, in a magazine, but also store shelves, outdoor banners, store layouts, and much more.

    -Thomas

  3. per corell says:

    Looks for me like a camera have followed eye movements and highlighted the arears that attracted the interest. Typical looking at a face the eyes and mouth, a page the text, and those arears where links often are placed, , an interesting app. if it can be used with a phone and the program first callibrate the eyes towerds the image, to follow them like pointed out to show what people look at. Still as you say there are many other parameters ; most people are good reading a face so the weak color indicating the eyes as a focus area do not say anything about that person’s skill in terms of expression reconition, one glimps could be enough to judge for average person, where what is interesting in another image, are the small area looked at round the mouth, a place that often uncover the persons attitude. Great idea for an App. if it’s what it say it is and used in a clever way proberly a great tool.

  4. [...] Visual magnetism – what draws you into an image? So does neuromarketing work? [...]

  5. i purchased them at my neighborhood pharmacy in this article in the big apple these are white and blue and on the net i saw they had been white and eco-friendly. is my pharmacy promoting pretend fruta planta capsules

  6. Trish says:

    Wow! I can learn to replicate what this product does because I AM the subject — a typical set of eyeballs with a typical human brain — that the product strives to predict. I am both mineral and miner — why not cut out the middle man? If I stay conscious as I review content, and track the split-second breakdowns in my own attention, I save myself $1,000 per month. :-)

  7. Tatiana says:

    I loved as much as you’ll receive carried out right here.
    The sketch is tasteful, your authored material stylish.
    nonetheless, you command get got an impatience over that you wish be delivering the following.
    unwell unquestionably come more formerly again as exactly the same nearly a lot often inside case you shield this hike.

Leave a Reply

Sharing Buttons by Linksku