Google Image Search

November 13, 2019 posted by

Hi everybody. My name is Peter Linsley, I’m
a product manager at Google, working on image search. Now what we thought we’d do today
was to run over some slides that I presented at SMX West in February 2009. Just a couple
of weeks ago. And the slides were very, um, sort of a high level introduction to image
search. So first of all I thought we’d run through the presentation that I gave at SMX
West and then afterwards I’ll run through some of the questions that came up that seemed
like topics of interest to the webmasters. Okay, so I’ll start the presentation. So first of all, our mission with Google Image
Search is to organize the world’s images. We put a lot of focus on satisfying the end
users. So when they come with a query, and they have an image that they’re looking for,
our goal is to provide relevant and useful images for that query. And of course the theory
here being that if they find what they’re looking for and they enjoy their experience
they’ll come back and use us again. What I wanted to get out of this talk as well was
to start to engage a little bit more with the webmaster community. If we look at what
has come out of various conferences like this. Where web search representatives from different
companies have gone out and had a conversations with the webmasters and found out what their
pain points were and we found this sort of ad hoc consortium came together and came up
with things like the Sitemaps standard or they came up with rel nofollow and well they
came up with robots wild cards and things along those lines. So one of our hopes in
Image Search is that we can try and start this dialogue and find out what sort of pain
points you guys might have as webmasters. Where we, you know, the likes of Google and
also other search engine companies can try and come together and try and enhance the
end user experience by finding easier ways for you guys to get your images both indexed
and ranked. So I’m just going to move on to the first
slide that I had. I wanted to paint a little bit of a picture of Image Searches. What they
do and why they might be slightly different to the kind of audience you might be used
to with Web Search. First of all Image Search appears in a lot of places beyond
You’ve probably seen images appear in Universal Search, so whenever you do a query like “pictures
of San Francisco” there might well be a portion of the results page that’s dedicated to showing
images for that result. And the theory here is very much in line with our goal in Image
Search which is that we’re going to show you those results when we believe that they are
very useful and informative and relevant to the query. Images also appear in other places
like on Maps. You might have seen a little row of images in Maps which come from our property, which is a really cool product if you haven’t seen it before.
So images appear everywhere across all of our properties and we’re really just trying
to align it with when they match the user intent or they enhance the user experience.
Image searches also have a very unique search behavior. They are very different animals
to web searches. If you think about the paradigm when they do a query, it’s not so much about
what’s the first result. We don’t really have this sort of I’m feeling lucky paradigm. It’s
more about saying here’s a query, well here’s 20 images that you might like. And users can
consume those images in a heartbeat. And if the image they happen to like is at the bottom
left hand corner or the bottom right hand corner than so be it. They’ll see that, there’ll
be something about that image that attracts them and they’ll click through. The other thing that they do is that they
search a lot of images. So there’s a lot of next paging going on, they’ll go very deep
looking for the image that they like. One of the reasons why this happens is that a
lot of queries we see are very subjective in nature. So if you see a query like “waterfalls”
then the waterfall that you like and the waterfall that I like might be on two very different
pages and there’s no way as a search engine we can figure out what you’re looking for.
So there’s a lot of next-paging, users can consume results very quickly and it’s just
interesting to think about what that might mean for you guys as marketers. That it’s
not all about being in first position on the first page. There’s also a lot of novel use cases in Image
Search which might not be apparent. Users use image search for inspiration. They want
to get a haircut or a tattoo and they’re looking for ideas. So “Tattoo ideas” and then they
go through the pages looking for some inspiration. Quite often they’ll refine their query, there’s
a lot of sort of exploring and this sort of browse with intent. Users also use image search
for shopping. They use it for research, health queries, or sometimes they use it just to
kill time, just for the fun of it. Another really interesting use case that we’ve seen
is using Image Search as a visual dictionary. So there’s a Googler in Germany who’s learning
German and he, if he hears a noun or a word that he’s not too sure what it is, he’ll type
it in. And he knows exactly what the word means. Even though he doesn’t look it up in
a text dictionary. Okay, so this is the slide on How Does Image
Search Works. Simply put, as a webmaster you’ll see Googlebot come along and download the
HTML as normal. Then what happens is, we pass through your page and we look for references
to images. And typically references to images can come in one of two forms. It’s either
an href where you’re linking to an image directly, or its an inline image, in an image
source tag. Then what happens is we come along and crawl the images and then go through this
process of classifying it. Now what we’re trying to do here is to figure out how to
bucketize this image correctly and one classification we do is to work out if its a photograph or
not. Another one might be “does it contain a face?” Other buckets might be things like,
is it line art? Is it black and white? Or is it an unsavory image that we want to put
under Safe Search , only show when Safe Search is disabled. So this sort of classification
goes on and the reason we do that is we found that image searchers really like to slice
and dice their results. They like to do a query and look at it and say “Well, these
images are sort of nice, but I really wanted to see just images with faces in them. ” So
if you’ve seen across the top of the results page there’s a blue bar which contains some
drop-downs where you can actually filter the results down to just photographs or just faces
or just line art and so on and so forth. And these filters tend to get used quite heavily,
so we like to try and bucketize things off so that they’re shown in a more relevant context. Finally of course the images are indexed.
And that’s where we squirrel them away and we have an index of the image with all of
the text that we associate with it, with that particular image. Another part of this process
is about identifying the duplicates. So if you think about the way images are typically
deployed online, you might put an image up and a particular page will refer to it, another
page might refer to it, you might have other pages on your site that refer to it. Every
now and again an image will get copied. And maybe it gets copied as is or maybe it gets
transformed ever so slightly. But as far as the user is concerned it’s still very much
the same image. So the next process we go through is one of trying to cluster all of
the very similar or identical images and try and treat them as one. And this is very much
the same as the way things are done in web, when web pages are analyzed for duplicates
and then one sort of canonical winner is picked out of that entire group. So the same thing
happens with image search. We try and identify all of the duplicates, and again, the main
reason for us doing this is that when somebody comes in and types blue widgets we really
don’t want to be showing them exactly the same blue widget twenty times. We want to
try and cluster those together and say, well, here’s one interpretation and here’s another
one. So there are multiple images, our goal is to try and cluster these and figure out
which is the best one. And at the same time we have multiple pages that are including
that image. And another task is at run time, at query time, to try and figure out which
one of these referrers makes the most sense for this particular image that we’ve chosen.
And the answer to this is we try and choose the best one. We try to choose the best image
that meets the user’s intent more accurately and maybe it’s about size or maybe it’s about
quality or something like that. And the referring page that includes that image is selected
based on how good it is essentially. And that could be one of many things such as its relevance
to the actual query itself. And finally, ranking is performed on a whole
lot of signals. And typically we don’t go into the details of the signals but its very
much like web, there’s more than one signal that we use to try and figure out what the
most relevant image would be. So the next slide, is on best practices. You’re sitting
there thinking, “That sounds great, I’ve got good images that I think are going to be useful
for your users. What can I do about it?” Probably the best bit of advice we can give is to really
focus on the user. Now you might be thinking what exactly does that mean? What can I go
out and do tomorrow to focus on the user? The answer is pretty simple. If you think
of a user that comes to Google Image Search and what they might be looking for, and if
we take one use case such as coloring pages. Maybe they’re looking for a site that has
a lot of coloring pages and they choose to use Image Search to get there. Then the first
thing they’re going to do is come along and type in “coloring pages” and they’re going
to look at the results. And maybe they see something they like, maybe they don’t, they
might hit next page a few times. And all of a sudden one image will catch their eye and
they like it for some reason. Maybe its just the quality of the image itself, or maybe
its the snippet, maybe there’s something about the size or host name that sort of draws their
attention. Maybe its “I know that site! I’m going to click through,
I trust it”. Then they land up on your page and the question is: What sort of experience
are you immersing them into? What sort of experience are they getting now that they’ve
come to your page, given that they were looking for coloring pages. Do they see the coloring
page they just clicked on above the fold? Is it large enough? It’s one thing to send
people to a coloring page page where you show them very small thumbnails and its another
thing to say this is what you just clicked on, here it is, here’s some descriptive text,
here is some related pictures, here is some comments from the users, ratings and all sorts
of things. It’s really about immersing the user into a very image-centric experience.
These are the kinds of landing pages and the kinds of images we’ve observed that our users
tend to like. And again, our intent is to try and match up the intent of the end-user.
So focus on the user, and high quality images are always good. If you’re taking photographs
to put on your site go and buy a digital SLR and learn how to use it, get a good lens,take
really nice high quality pictures. You don’t necessarily have to show, take up the whole
screen with the photograph or the image, but just you know large enough is usuallly what
the users like. Above the fold and plenty of descriptive text. And fundamentally the
impetus to all of Image Search is a text query and the extent to which you have a lot of
descriptive text that is on topic and talks about what is in the image, maybe you want
to expose EXIF data, maybe you want to talk about when the image was taken, maybe
it has a nice title across the top. All those sorts of things are really good clues for
us to figure out when an image is relevant or not. But more importantly its useful for
the end user. They can read the description, read the caption and learn a lot more about
the image. The last slide I talk about resources. We
have Webmaster Help Centers where you can go and read a lot more about Image Search.
We also have forums where you can post questions about Image Search. We really really encourage
webmasters to come to these forums and post all of their questions or concerns. We monitor
these very closely, we pick up these concerns, and we’ll take a look at them. There’s also
Web Search Help and Forum for end users so if you’re an end user of image search and
you have questions you can leave them there. The other thing is to monitor the Google official
blog because that’s where we typically put our announcements of new features and changes
and news and what have you, specifically around image search. So that was the end of my presentation
that I gave at SMX in a nutshell. So at the end of the presentation we had Q&A
and I wanted to pick up on a couple of questions that came up during that time. The first question
was “Hey, you guys mentioned large images are a good best practice but I have a concern
with that because I don’t want to load up the really really large version of the image
that I have because it takes the page a whole lot of time to load up. How do I manage the
trade off there?” So I think the answer to that question is to show an image that is
large enough. Typically two-thirds of a screen is one sort of rule of thumb. The point here
being that users tend to like to actually be able to see the image as opposed to it
being a very small thumbnail. So a good way to get around this, to allow users to see
the larger version if they wanted to is to turn your image into a link to either the
large image itself or another HTML page that includes a larger version of the image. Ultimately,
nobody really wants to see an image that is larger than the browser size. So, another
question that came up was about Analytics. Somebody was saying “Hey, can I get Analytics
information from the traffic that’s coming from Image Search?” The answer is “Absolutely”.
In the referrer string that we send across, well, that the browser sends across, both
the query that ranked the image plus the image itself is sent in that string. So one slight
difference with image search, of course, is that we’re not necessarily sending people
to that page as much as we’re sending people to your image on the page and there could
of course be more than one image. So by passing it by the referrer string you should get all
the analytics you need to know. What query sent the user there and what image sent the
user there. So that about wraps it up. I hope you found
this useful. By all means drop all of your questions in Webmaster and Help forums and
we’ll swing by and take a look. Thanks.


21 Replies to “Google Image Search”

  1. Robert Englebright says:

    So, all that helpful information he gave and all you can say is "Stop saying uhm!"? My guess is you probably didn't get much out of what he said if you were so focused on him saying "um."

  2. Robert Englebright says:

    Thanks for the info. As a photographer trying to get my work seen by the widest audience possible I found this video informative and worth the watch.

  3. greenvalue says:

    Good info – but soooo booooringly presented!
    And I still haven't understood WHY I would want my images to be found by any image search in the first place.
    My sites are NOT about 'being out there' and being 'famous'. I don't like my photos or graphics to be copied and re-posted on dozens of other web sites.

  4. motus says:

    maybe you should contact your marketing department then

  5. ESL Civics Lessons says:

    Great video, Peter. You didn't mention Google Labeler. I have a lot of images on my website, so I try to help out by spending some time labeling photos. The link is on Google browser page. It's fun and a bit addicting. I think it might even prevent Alzheimers?

  6. Google Doodle Videos says:

    Hi Peter, great video – thanks for sharing. (Have no problem with uhm! because the content is great)

  7. Siva Gopi says:

    Thanks Peter Linsley for your great presentation on Google Image Search.

  8. LiS Wright says:

    Dear Google help: I dragged my image into the google image search bar and it didn't work for me. Should my iphoto mage have a white or clear background for this to work?

  9. Owen Prescott says:

    How much is "large enough" for an image? My photos are high quality RAW and I reduce them to around 900px.

  10. Owen Prescott says:

    Ignore, he provided an answer as soon as I posted lol.

  11. Abdelghafour Zouane says:

    Nous voulons cette vidéo en Français ou en Arabe :/

  12. Sofiane al Baljiki says:

    Please, translate in french. Thx

  13. Cesar Augusto Ramos Martínez says:

    Favor traducir el vídeo

  14. شركة انطاليا هومز - شقق للبيع في تركيا says:

    I beleive "image search" is open for misuse of SEO tactics.

  15. Eren Mckay says:

    Thanks so much for all this useful information Peter!

  16. Dinamico studio says:

    really nice explain ,,,,,,

  17. solar cruz says:


  18. Jamil Gotcher says:

    I wish Google would put image search results before numbered organic link search results for local photographers. Most people will travel more than 5 miles for a really good photographer so ranking photographers by places and text links isn't the best user experience.

  19. Jessie Su says:

    I do the e-commerce business. i want to know that if there are eight images of one product in a page, do i need to add the alt attribute to every image? if not, how do i choose the image and add the alt attribute to it? Thank you!

  20. Kids Learning Channel says:

    please stop saying um

  21. Hapo Hoppo says:

    Watching this video in 2018. Hello people from 2009

Leave a Comment

Your email address will not be published. Required fields are marked *