h a l f b a k e r yactual product may differ from illustration
add, search, annotate, link, view, overview, recent, by name, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
|
|
|
Please log in.
Before you can vote, you need to register.
Please log in or create an account.
|
With voice recognition becoming more and more accurate - digital cameras could be made to recognise your voice as you take the picture and convert the speech into a caption.
The caption can then be overlayed as per your prior settings onto your image.
My inspiration
http://www.halfbake...om/idea/Stegocamera [Trodden, Oct 05 2004]
[link]
|
|
I had a primordial idea where this technique plus translation would be used to display a caption under the speaker's head, live. Like watching a subtitled film, one could understand the foreigner's speech. |
|
|
Why voice recognition? Why not just capture the audio and post process to add the text caption (if you really want it) later when you have reviewed the images and output of the voice recognition engine? |
|
|
Given the error rate of voice recognition, it'd be sad to have the only copy of your seaside photo emblazoned with the caption "it will wreck a nice beach" when what you said at the time was "it will recognize speech." |
|
|
Besides, you might want a scrap of the ambient audio to go along with your photo. |
|
|
If you must have voice recognition, store the results in the EXIF header, or other metadata spot, of the photo . . . just don't have it sully the original image. |
|
|
Another possibility might be to, at the time of download from the camera to computer or storage, have two copies of each image come down: one with the caption and one without. |
|
| |