144 comments

[ 3.0 ms ] story [ 193 ms ] thread
When I have time later, I might feed it some images from the Magnum (the agency) corpus and see what feedback I get.

Once upon a time, in certain newbie photo critique forums, pranksters would upload a renowned photographers image for critique... Hilarious feedback from new photographers showing off their critiquing prowess.

I tried it with a couple of photos that got me awards in prestigious international competitions. They were assessed as being OK (~5/10)
I tried an Ansel Adams photo - "This landscape is good, but it could be great. Let's give it a 7.5/10"
Adams was a pretty straight forward photographer, so I suspect his example might fare better than say a Winogrand or D'Agata, for example.
I got it to give me a 9.7/10 but I seriously doubt I'm a better photographer than Ansel Adams I'm betting it has an unintentional bias against black and white photography.
I got it to give me a 9.7/10 but I seriously doubt I'm a better photographer than Ansel Adams I'm betting it has an unintentional bias against black and white photography.
I am chuckling at the idea of an art critic version of this and feeding it famous works.
What do you think this is?

Weird to imply such a strict delineation between photography and art.

Keegan seems to be judging the mechanics of photographic skill and not the artistry derived from it.

The humor is from imagining a robot pan great works because of implementation flaws. "Mona Lisa. Muddy and drab. 2/10"

Nothing really to do with me trying to classify what is/isn't art.

Actually it likes some pictures of the famous paintings :) "Simple but it's good" https://keegan.regaind.io/p/z7gQYuFxTTWTK00kHMuaPg
Truly impressive. I've been putting in pictures of my daughter from my phone and I think Keegan really shines at evaluating the pictures I take of my life. Sorta like a writing coach for a diary.
Thanks! This is exactly the use case :)
The difficulty will be understanding context. Was blurr intended for effect? Same with a fuzzy picture, or a dark one, or one with no apparent subject, or was it informational only, etc.
Some photography is presented as contemporary art, some isn't. "Fine art photography" is usually not credible contemporary art. It's often black and white, formalistic, maybe a female nude... I can imagine an AI that only understands formal qualities becoming pretty good at rating it.

What you might call conceptual photography, on the other hand, is "AI-complete". It's as hard as literature to appreciate, you definitely need a full human-equivalent AI. Roland Barthes' ideas of the studium and the punctum start to open up the intellectual depth of that kind of photo.

This kind of project is possibly credible as a rater of formal quality against some ideal norm, maybe stretching to understanding composition in a crude sense. But everyone knows that it's the unexpected but visually compelling feature that makes an image good. (Or alternatively the significance of its content.) Standard strategies like the "rule of thirds" can only produce formulaic images.

I just tried a famous Cartier-Bresson image...

"It's not super amazing. It's…something I guess; you could do better. Try improving your colors. This is at most 3.9/10. #boring"

Yeah, Henri, improve your colors you lazy hack! ;)

Poor D'agata: https://keegan.regaind.io/p/4ez2sHM5QDOT4nR6rzqU2g

and Autio: https://keegan.regaind.io/p/qzqjM1CPRxGtkL1GQ4KL0g

But I get it. It's a great tool for beginners to see their rookie faults and address the basics [1]before they can foray into more intermediate photography. And then break the basics [2] in order to know why breaking the rules work and sometimes don't.

Semi-related (to the optics/mechanics) is this tool[3]

[1]https://www.flickr.com/photos/msc72/3184463442

[2]https://www.flickr.com/groups/1271834@N25/

[3]http://camerasim.com/apps/original-camerasim/web/

I'm impressed with the ability to recognize different scenes and subject matters. There are achievements that include photographing waterfalls and beaches! How cool is this?

Side note: Is this bot on Facebook Messenger as well? Or did I misunderstand?

Yes, I was surprised by this too; I uploaded a photo of mostly just sand (no sea visible) and it recognized it as a beach. Amazing.
I was nothing is wrong but could be more. More what?
Hey there! Do you have Keegan's URL for the picture on which you got that comment ?
Uploaded the 2016 Pulitzer Prize photograph of migrants from Turkey landing on Lesbos in October after battling rough seas:

...This photo is alright! I give you a 7.1/10. That's a very decent photo for a start! Can you show me something even better?

(comment deleted)
That's a great example of the 'third element': composition, exposure and opportunity.

Sometimes you can make opportunity "happen" through equipment with more reach or foreknolwedge. But sometimes things just happen and a mediocre shot is more powerful than none at all.

Sadly we cut Keegan off internet a while ago to train, and he is not quite aware of the global context which makes this photo extremely taking :(
Algorithm seems to really like portraits. Every one I uploaded, it scored very highly. Threw in Afghan Girl by Steve McCurry https://keegan.regaind.io/p/yBJXfxHeTEWtvtGDxgupaA to see what would happen.
That's been my experience as well. It must use face detection rather heavily. It also doesn't like photos with no central subject.
Actually there's absolutely no face detection in there !
But it loves contrast, no? Global contrast as well as local contrast.
Normal BW portrait, 8.5:

https://keegan.regaind.io/p/YLzqGGvuSFOv7PwLl8qC8A

Same image with clarity upped to 100% (horrible, IMHO), 8.6:

https://keegan.regaind.io/p/JbMQUyfBTNuoAWveabPCwg

It does like contrast! Hm, the score change is sufficiently low to be within the error bars I'd say. I agree that the upped clarity is less beautiful, but it adds a nice touch of sharpness which Keegan likes a lot as well!
The first one looks too blurry to me and the second too sharp; did you try an intermediate one?
You can do a lot worse with contrast/clarity than that.
"You need to invest in some studio lighting… The pic is not very interesting… It's flawed, but you'll get there: keep working on your lighting, framing, and composition. It's only a 3.2/10."

Uploaded the second picture of this fantastic set by a 1950's photographer from Hong Kong: http://designyoutrust.com/2016/02/hong-kong-in-the-1950s-cap...

Many of them get labeled as #badcolors or #boring, I guess it might be related to the lack of color features...

I think the fact that the AI is developed by Regaind (https://regaind.io/) must be taken into account. Their service is not intended for artsy pictures. It is rather targeted at people who have 1000 photos on their reflex from their last vacations and want to make a relevant and beautiful album of 50 photos to remember their trip, but don't want to spend two weeks comparing and selecting the right ones.

See for instance their demo here : https://regaind.io/demo/.

Exactly =) The target is not professional photographers but pretty much everyone else taking pictures everyday with their smartphones. Artsy photos are more often than not wonderful for reasons which are not way too semantic for us for now - situations, etc, and which are way beyond what standard photographers do!
That's actually a really great idea! Gonna have to check this out more.
In my experience, even amongst vacation snapshots, the best tend to be of the accidentally artsy variety. I suppose this algorithm would completely fail to recognize the hilarity of the mirroring sphere of a tourist's perfectly bowling-ball-bald head in front of an apse, hovering under the blob of light that is the eye of the pantheon dome on a phone snap. I know I did, (miss it) on the first few times I scrolled through the series.

Generally I feel tempted to file this site under fun with phrase generators, with some ML thrown in to make it slightly more interesting than purely random phrase generator toys. But are there really no use cases for automated checks of aesthetic conventions? Sifting through the data dump of a full day of wedding shots maybe? I know I would be tempted to start with a computer generated shortlist. Mate it with face detection so that you can cluster by subset of attendees (each combination of faces captured must be present at least once in the final set) and... well I guess they already use systems like that, it's 2016.

An entirely unrelated idea in the general area of photography, algorithms and human learning that I still miss is this: an option in manual mode that takes a full auto shot right after the manual one, exposing how good or bad the algorithms are vs the operator. Or do some cameras have something like that? Do manufacturers omit it to not expose deficiencies in their algorithms? Do they omit it to not hurt the feelings of customers when they are worse than auto mode?

This is indeed a "fun" project which showcases the technology and provides (I think) fairly relevant comments (trust me - a random generator is much worse, we had terrible comments at the beginning of the project). The other technology modules you describe (face recognition etc) are indeed requirements for a semi or fully automated curation system.
That demo is pretty impressive. Removes duplicates, and you get a pretty good result going down to the top 25. Nice stuff.
Thanks for the link. I love these.
Indeed, it does not like my 4x5s, but it does like some anime figure pictures I took with my cell phone.

I think it basically looks to see if something is in focus, and you know the "rule of thirds", which it must have learned from custom-cropped photos uploaded to 500px.

(comment deleted)
On top of that, it hates post-sunset landscape.
Here I played with colors and color temp on a post-sunset landscape, and the resulting image, while really not great --in fact, plain weird-- is rated 9.3

https://keegan.regaind.io/p/04t9ZlbZRDqbc2mPx-4CvA

Does the system have a notion of how sure it is of the rating it gives? [Edit: should it say "without a doubt"? There should be some doubt.]

(Also, is it deterministic (same image always get the same rating); it sure appears to be and it's certainly what people expect of a bot, but that's not how humans rate things...)

To be honest, I kinda like the image. It might not be great to you but it has a nice spooky fantasy air to it to me. As to wether it should be considered a good picture, I have no idea.
It loves this image (9.4):

https://keegan.regaind.io/p/BRINmnczQ-yY7wLn0xbaYA

but says that The background really adds something special. The background is... full black?

And it hates this image (4.7):

https://keegan.regaind.io/p/nWu-YSRgSrWWfwxUgUorcQ

and gives it a "good timing" of 35%. The timing is what makes this photograph ;-)

Also, while direct links work, the back button doesn't seem to update the content of the page?

Fun how it saw the good timing but put such a low score. Keegan is tough with low-light photos overall. Gotta improve that!

What's your browser? (re: back button problem)

Chrome 53.0.2785.143 m on Win7 64bits (with Ublock Origin).
Thanks, gotta investigate :)
I've emailed them to mention that low lit photos seem to score much lower than they should, and they plan to look into improving that.
wow, thanks for the link! those are really nice photographs, beautifully framed and very artistic (for pure art - that woman leaning on a wall, with the triangular shadow across the building, come on - wow!) and obviously even more informative to us 66 years later than when they were made - that is true art, wow.

one quick question - the page you linked starts with a top picture and then a set, by "the second picture of this fantastic set" did you mean the second picture on the page (gondolier in dark canal with tight ray of light from above) or second in the "set" (guy crossing tracks running with empty rickshaw)

Posted a masterpiece by Stephen Shore, Keegan didn't care for it.

Static composition, my eyes don't really know where to look and the pic is not very exciting… It's flawed, but you'll get there: keep working on your composition and lighting. This is at most 3.8/10. #messy#boring

Here is the photo http://www.fubiz.net/wp-content/uploads/2015/07/stephenshore...

I have a DSLR and several fairly good lenses and like taking pictures, but I'm by all accounts a layman, and seeing as I'm unfamiliar with that photo, obviously not well versed in the industry.

But honest question: Is that a good picture? I don't assume that the AI is trained enough to give accurate critique on all photos, but in this case I might agree with it.

I'm not trolling nor mean any offense, but is there quantifiable skill behind that photo, or is it just as subjective as painted art? A simple example would be a Pollock painting which I don't care for at all.

Art MA holder here: Pollock is a really good example of the hard-to-pin-down quality of optical balance or energy or "eye". It's a learned thing like most aspects of culture. There are personal variations in "eye" judgement but enough consensus to keep the art market afloat. It does also have something to do with hierarchical structure, fractals etc., especially in Pollock's structurally simple drop paintings. His idea was a conceptual innovation but now does look pretty boring.

You might also dislike Pollock not only for being boring but for being associated with a tedious CIA-sponsored moment in art in the 50s, in which case I applaud you.

I mean, is that a masterpiece? I ask as someone who is unaware of Stephen Shore and has never seen this picture before. As someone living in 2016, that looks like a random picture of a gas station someone took on a road trip. I agree with Keegan here, it's boring.

I'm sure there's some historical context or something I'm missing out on here, but that's just my take looking at the picture.

Stephen Shore is one of my favourites. It might help to think of this image as representative of a body of work, which makes it legible. (and, let's not forget, financially valuable). It's not the greatest Shore image.

Shore has a good "eye", which is something subjective that needs training to develop and recognize. It's very plausible that the particularity of a given artist's "eye" will be quantifiable by AI systems soon.

Shore wrote a popular book called "The Nature of Photographs". Recommended.

I am also unaware of Stephen Shore, and have not seen this picture before. I guess we can chalk it up to different tastes - I think this picture is amazing. It captures the feeling of the place.
How do you know what the feeling of the place is? Have you ever been to that gas station?
It doesn't matter, the point is that a feeling is captured.

Many people seem to think that photography is solely documentary, but that is only one possible aspect. You also have control over what is in and out of the picture, where objects are relative to each other, the relative tones and brightness of objects, etc., and can use that to tell a story that's not strictly true. If you've ever been composing a shot, noticed that there is a big pile of garbage in the frame, and shifted the angle slightly, you're already doing this.

Well...a feeling is captured, not the feeling.
Like all forms of art, the idea is to show the artist's feeling, not to tell you what you would personally feel.
Definitely fun to play with. Seems to really like bokeh...

https://keegan.regaind.io/p/sqs8Z8RgSsuaSG3gLxo0bQ

https://keegan.regaind.io/p/dNMYqs3aSpa_x0fYMU_AhA

I'm not really seeing it couching me though:

https://keegan.regaind.io/p/6QD0ycG3QTK1uM2IbIslSw

"This landscape is good, but could be great". Not really sure what to do with that.

https://keegan.regaind.io/p/lhCz67aBTnmI5GB9sWO4cQ

Seems like a low score. Again though, it's not really clear why. "Bad lighting" seems odd, because maybe I have no taste but the lighting is the reason for the shot in the first place. For reference, here's the original: https://www.flickr.com/photos/stefandufresne/16091643487/in/...

So far, AFAICT, it is a big fan of single focus thing in foreground with lots of blur in the background.

Edit: I'm having trouble getting it to ever like black and white shots: https://keegan.regaind.io/p/-NZR7e1FTJGtpMN3BPYlAg

Edit 2: Okay whaaaaaaatttt I'm really disagreeing with a lot here. Maybe I just think some of my shots are better than they really are, but 4.1 for this is crazy https://keegan.regaind.io/p/y3LaI_J0R6a33eJ_fOQfew

Yes, single focus, bokeh, and the point about colors is a good one, too. It likes lots of colors. That monochrome landscape is beautiful, by the way.
Indeed, my seashell-in-the-sand picture with lots of blur got a 9.2. Also most of the hall of fame is subject+blur.

Didn't try B&W yet, don't have many pictures like that.

(comment deleted)
Trying to figure out how to make a comparison of this to Professor Oak's photo critique in Pokemon Snap without beckoning all the HN downvotes...

"Well done!"

To me, Keegan misses out on the art of photography and is focusing more on the "rules" of photography.

That being said, it's fun to see where photos fall in its grading system, even if I personally disagree with it.

For example, this portrait by Vivian Maier gets a 4.2 https://keegan.regaind.io/p/9VJdlageRTusSf7Z2qDQPA

If you click the slightly hidden "get more feedback" button it shows:

Subject well framed: 100% Super sharp subject: 71% Great composition: 68% Pleasant blur: 57% Great lightning: 35% Well chosen background: 33% Interesting/original subject: 32% Good timing: 26%

So it's not very happy with half the categories but scores 9.4/10, so the score is definitely not an unweighted mean! (geometric or arithmetic).

Thanks for the feedback! Any tip on how to make that button more salient?
I think it heavily dislikes the obstruding object at the bottom. Not his tastes :(
(comment deleted)
On a side note, is it just me or does the character at the top of the page look ominous/creepy?
that's because Keegan can be witty and a bit harsh at times :) but yeah now that you say it I can imagine some creepy memes with him xD
Is he good friends with the Incognito guy?
I tried it with my favorite, Alex Webb. It didn't break 5/10 and received solid #mess and #boring tags on all of the photos. Fun none the less.
As amazing as the advancements to image recognition technology have been, I'm equally astonished of the progress corresponding language generation.

I would be interested to see a Turing test with this tool versus a real photographer analysis.

Restrict the "analysis" to 3 or 4 sentences along with a score. The participant goal would be to figure out which analysis came from the AI and which came from the photographer. Would be interesting to see the results...

Thanks ^_^ as mentioned in the about modal we received a lot of quality help to polish Keegan's language :)
Are you based in Paris? That's great!
We do! We're at Agoranov near Luco, feel free to drop by if you want to have a chat :)
I'd love to! Are you Guillaume?

Are you working on more than classification? What about automatic improvements, including not just lightning but also straightening, cropping, etc.

I'm! You can get in touch with us at hello /at/ regaind.io

You can have a look at your webpage for all that we do (https://regaind.io), but yeah, automatic improvement is on the list of potential things we would like to do :)

Tip: you can click the "Get more feedback!" button for a detailed breakdown of scores.
I think the subject was hiding in my portrait due to me uploaded a landscape.
Haha do you have the link for that fail?
One of the issues is sometimes, it's okay to do things in a non-standard way for effect. The other issue is it seems to think the only thing that matters in photography is depth of field.

For example, this kind of generic picture of my son during the fall got an 8.2: http://imgur.com/a/SOFE0

Where as this other picture I took, one I think is technically superior recently got a 7.1: http://imgur.com/a/VeEL9

And then there was this one I took in Rome, which got a comment of "not enough blur" which is the exact opposite of what I wanted. This is a fiat in rome, the background is the entire point. rated at 6.2 http://imgur.com/a/zLStt

Compared to this pretty generic musuem pic... that's not really interesting in any way, but managed to get an 8.2 (probably because of the blur) http://imgur.com/a/Szc9I

Can't wait for the next AI winter...
My test photo got classified as “not a photo”. Keegan may be artificial, but certainly not “intelligent”.
Judge on a single sample, do you ? :) That's a fairly strong statement based on a fairly small dataset :( But yeah, our heuristics to ignore some content (e.g. websites screenshots) sometimes trip on real pictures. There's still a lot of room for improvement :)
Judging by the tags, it recognizes this as a street sign (which is great and amazing), and yet says it's "not a photo".

A photo of a street sign is definitely a photo ;-)

https://keegan.regaind.io/p/v5bCFkeRRYSvendxCM73yA

Yeah it's super harsh with street signs or that kind of large text on pictures. The protection is there to avoid saying really silly stuff on utilities bills and other kinds of paperwork. I'll add this example to the ones we should accept.
(comment deleted)
(comment deleted)
"Great color and amazing angle. It's okay, but I want to see more; keep working on your composition! A solid 5.7/10. Not bad, but I'm sure you can do better!"

How the heck is this feedback supposed to be useful / helpful / actionable?