Cool idea! Not sure exactly when it could come in use, maybe to get things translated when you travel if it's accurate enough (and you don't like speaking to the locals). It's only stating one thing in a picture, could it say all objects identified in the picture?
@mikaellowgren neat thought, when you want to know what something is in your home language but there is no one around you can translate it for you. You can't use Google translate because you don't know what the word is in the first place... Maybe it could suggest where you can buy one of those things?
This is very cool. In fact, out of the 5 tests I did with it, it got 4 of them right. Did you build your own training model for image recognition?
Also, what are some key use-cases that you can see people using this bot for? I can see the value of identifying clothes but creating an accurate systems also seems like a very hard computer vision problem.
@jonathanzwhite no, I am using 3rd party image recognition services to begin with. Right now I am focusing on how to make the bot aspect better, e.g. getting user feedback, or even allowing the users to help identify difficult images.
Identifying clothes is something I've got a lot of positive feedback on, but yes, it's a very difficult computer vision problem. Exploring ways to tackle that, maybe people is the answer :)
Well, the recognition algorithm is not perfect. But I know a way you can improve it.
I uploaded an image of a potato soup in a plate (the file from Wikipedia had a name Romanian_potato_soup.jpg). At first I thought to rename the file because it would be too easy to know what was there even without looking at the picture. But the answer was too general - "A white plate". It means that the algorithm doesn't take file names into account, when they could be really useful.
@techno246 Very cool concept - I dig it. As mentioned by other commenters, it's pretty accurate in giving a very generalized identification (e.g., photo of a jade plant returned something like "leafy green potted plant"), which is cool, but I'm guessing most people know the generalized identification already -- getting more granular is key.
And while I do like the name, you should consider changing it to something a bit more kid-friendly, maybe just "WIT" (What Is That). Gotta love a good double-entendre!! Good luck.
@adammash Thanks for the feedback. Once we get experts on board the platform, we might be able to begin identifying specific traits of objects like species, etc. The community can patch up things. Out of interest, how willing would you be to contribute back to tagging images? For example if the bot hit you up an image, would you help identify it if you knew what it was? Something we are currently exploring.
Oh yes, I have thought about how to make it more kid friendly. Though it's a fun name and resonates with a lot of people, I wonder if I can keep it as a double entendre but have a kid friendly meaning of the acronym. WIT could work... Given W can still be expanded to it's original form, if needed :)
@techno246 I definitely think asking experts to contribute to tagging is a smart idea. It's how Google images tagged their images -- they had a "game" where people could flip through images and add any tags they think are relevant. I'm guessing they showed each image to multiple people and kept the tags that were suggested more than once. WIT! 😎
Awesome! I second (or third ... fourth ... etc) the suggestion to ID the actual brand / item in the picture. My parent's have this awesome shower head but haven't been able to find any model # / brand on it.
@scottcents I see the usefulness in that, especially with objects like that where there aren't big players and recognisable brand names/models. Thanks!
Remind Me At
Gift Insights
All or Nothing
Gift Insights
Bagel
Gift Insights
NotAnEasyChoice
Gift Insights
AI Starter | An AI "Biz-in-a-Box"
AI Starter | An AI "Biz-in-a-Box"
AI Starter | An AI "Biz-in-a-Box"
Being
Gift Insights
Being
Emojifs
Gift Insights