Will we ever see an intelligent AI for picture content searches?

xboxist

Diamond Member
Jun 25, 2002
3,026
1
71
Do you think that technology will ever surface that will allow a user to search a database of pictures using a random set of criteria and be successful? For example...

Say that I needed to locate a graphic of:

1) a young boy

2) wearing shorts

3) outside on a sunny day

4) holding a red balloon


Now, currently there is no easy way to do this. You typically have to visually search an archive for a graphic like this. This can take hours, and often you can't even find what you're looking for at all. You could try simply searching using "balloon" in an internet image search, which obviously is wildly unpredictable.

What I'm wondering is if we will ever create the means to have the search engine/program identify elements of an image by itself. I'm not talking about using a set of tags embedded into a picture file ("balloon", "child") but simply being able to "look" at each picture and pulling out some possible candidates to fit your criteria. In other words, having human-like eyes search the CONTENT of an archive of millions of picture files in a matter of seconds/minutes. Not based on file names, tags, etc.

Does this sound even remotely possible? Perhaps it's so far-fetched that we can look forward to being able to efficiently travel between solar systems before we ever see this? But the idea intrigues me, and I am curious of your opinions on this possibility.
 

James Bond

Diamond Member
Jan 21, 2005
6,023
0
0
My girlfriend showed me a website not too long ago... I can't remember what the link was now, but it was showcasing photo recognition software.

You would upload a picture, then it would locate the faces of anyone in the picture. It would then compare the faces in your picture, and match you up with celebrities that look the "most" like you. It would also match you up to other random people who had also gone through the same process.

At first when she showed me, I completely thought it was a hoax. I played around with it for like an hour, and it seems that they might actually be on to something.

Anyone know what I'm talking about?

Edit: Here it is: http://www.myheritage.com/FP/Company/tryFaceRecognition.php
 

Matthias99

Diamond Member
Oct 7, 2003
8,808
0
0
Facial recognition has been studied pretty well.

The problem with trying to generalize any approach to 'smart' image processing is that it very quickly becomes enormously complex. Unless the objects you are looking for are very distinctive or have common features that can be used to pick them out in a variety of positions or lighting conditions, it rapidly becomes an intractable problem (at least for our current level of computing ability).

What I'm wondering is if we will ever create the means to have the search engine/program identify elements of an image by itself. I'm not talking about using a set of tags embedded into a picture file ("balloon", "child") but simply being able to "look" at each picture and pulling out some possible candidates to fit your criteria. In other words, having human-like eyes search the CONTENT of an archive of millions of files in a matter of seconds/minutes. Not based on file names, tags, etc.

It will be a REALLY long time before you can do something like this in real time (unless you're interested in something very specific, like people's faces). More likely as a first step would be something with the ability to (slowly) analyze a database of pictures and tag them, and then you could search based on the tags.
 
Dec 29, 2005
89
0
0
to your original question:

currently neural networks can be used for pattern recognition (facial recognition in pictures). as matthias mentioned in order for it to generalize you need to give it pictures that have common features. but after the network is trained it can categorize/recognize the inputs.

to handle your query, however would probably be the more difficult part (currently). current natural language processing (NLP) is not very advanced. however if you restrict the query grammar you could avoid the NLP problem.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |