Apple Support: How to hear image descriptions in the Camera app | Hacker News Reader

Apple Support: How to hear image descriptions in the Camera app

youtube.com

172 pointscolinprince47 comments

The descriptions are shockingly detailed. I wish there was a way you could add these descriptions to the metadata of all the photos in your library, it would be an amazing way to add rich searchable data.

In particular, asking Siri to "show me photos of <x>" where x is a thing that the photo descriptions does recognize, doesn't always work.

I do this all the time in google photos. It's so #%^^ing incredible.

"Waterloo patios with friendname" - me looking for when I last saw that person remembering it was on a patio.

"Driveway or sidewalk"

"cottage docks"

"receipts"

"Memes with Ted Cruz fleeing to Mexico"

Same here. Blew me away when I realized you could do it a couple years ago!

Just so you know, you can search the photos libraries with all sorts of ML-generated metadata (eg mountains).

Yes but the things that the image descriptions recognizes is a far longer and more detailed list than the searchable objects.

If you get stuck in VoiceOver, you can ask Siri to "turn off VoiceOver". The touch gestures are completely different to normal iPhone usage, with it turned on.

Quick guide: Single-tap to highlight a widget, double-tap to click, swipe with three fingers to scroll (after first highlighting the part of the screen you want to scroll). To go home, swipe up from the bottom and hold until it vibrates.

Turning on voice over to investigate this has to have been one of my worst decisions in life. Please do not repeat.

Haha I remember having to test apps, and being completely confused by it in the beginning too. First thing I did was add VoiceOver toggle to Control Center.

Once you get used to it, it's actually kinda amazing. Apple has put so much effort into iOS to make this work well, and there are a ton of features packed into VoiceOver mode.

Most have no idea this even exists, if you're bored you should play around with it a bit more.

Here's the cheat sheet to gestures you have to use to control your phone once it's turned on, which I guess was your problem. https://support.apple.com/en-au/guide/iphone/iph3e2e2329/ios

The YouTube channel by Kristy Viers has been helpful in understanding how they use an iPhone and other devices. Here’s a video on VoiceOver in the Camera app: https://youtu.be/8CAafjodkyE

That’s amazing, I wonder if it constantly doing ML classification is more draining on the battery.

Probably balanced by the fact that you can turn the screen off completely when navigating with VO.

https://support.apple.com/en-ca/HT201443

Word of warning, if you lock your phone and you're not familiar with the voice over input it can be really annoying to unlock your phone...Seems to turn off face id as well?

You can ask Siri to turn off voice over and all is well.

My phone is set to use the “accessibility shortcut” function, with is mapped to triple-click side button toggles VoiceOver.

Right down the bottom of Settings > Accessibility.

Edit: you can also enable screen curtain in iOS (and watchOS!), which means your phone can operate with the screen completely off when in VoiceOver.

Good for privacy / battery!

If you have tagged people in photos from your camera roll it will also say “maybe (person name)” when it sees a match in the viewfinder. Pretty neat.

The cautions not to use it in navigation or circumstances where you might be harmed ("yellow car driving directly at you at a high rate of speed!") or diagnoses of medical conditions ("might want to get that wart looked at, dude") made me laugh.

Also pretty cool for learning languages?

If it would also show the written text of what it said, faded in as soon as the word is spoken, overlaid on the object it describes, that would help a lot.

Makes the phone virtually unusable if you’re not familiar with voiceover gestures

Gestures are listed here https://support.apple.com/en-au/guide/iphone/iph3e2e2329/ios

You can ask Siri to turn off Voiceover thankfully, can turn it on and off inside of the Camera app this way.

On my phone I get a pretty stern warning about that before enabling it

Microsoft Seeing AI has similar features; might be of interest to visually impaired people as it’s made more specifically for identifying objects or reading documents

Sound recognition is also another very cool accessibility feature: https://www.loopinsight.com/2021/05/11/apple-support-how-to-...

Though I'm not sure if it comes at the cost of increased battery usage.

In my anecdotal experience it makes no difference on my 11 Pro. It presumably uses the same hardware that’s already awake all the time listening for “Hey Siri”.

It seems to basically be using an image captioning model like this one: https://deepai.org/machine-learning-model/neuraltalk , but possibly trained on more data? I wonder what dataset they’ve used, or if they created it themselves and won’t share it.

Neat. Is my phone classifying all this stuff, or is it sending all my photos to some Apple server to do it? I watched the video in the OP but it didn't go into any technical details.

It runs on the phone, no doubt using whatever model they use to enable the keyword searching in the camera-roll. Just verified it all works in airplane mode.

I don't know of any ML stuff that Apple does serverside. That is why they have invested so much in ML processing on their devices.

All ML on device definitely seems like a goal for Apple[1]. However, right now Siri doesn't work in airplane mode.

Maybe its still too power hungry to run locally? Maybe they still need the data from the requests server side to improve the model?

I hope both Siri and Maps, and especially their integration, i.e. "Siri navigate to ____." "Siri find restaurants nearby (or along the way)" works on device in the near future. Its annoying for the CarPlay integration to stop working when you're in a remote area and need the navigational help.

[1] https://appleinsider.com/articles/18/11/15/apple-considering...

Siri’s voice translation works in your phone but the answers it needs are all calculated from the server (on the whole). Maps, for example, are all stored server side and route calculation are server side processes as well, as are the locations of restaurants.

There’s a difference been decoding voice requests and being able to answer any questions you may have; you wouldn’t expect Google web search or Wikipedia to work in offline mode, so why do you expect it to work for Siri?

I don’t expect it to work :)

I expect that it will one day soon work offline. Likely not a full web search.

By 202X, while offline my device should have:

1. Enough storage for voice to text models, translation models, local Maps data auto-downloaded when I have reception (including restaurants, reviews, image thumbnails, etc), Wikipedia, wallets (car keys, credit cards, concert/movie tickets, email, daily news, music/podcasts/YouTube that I’ve subscribed to. All of this should be automatically synced when I have reception (podcasts and music already do es this).

2. Enough compute to translate voice to text (and between languages), set a simple timer/alarm, unlock my car, search through Wikipedia, search for restaurants, directions between points on the map (without using traffic data), open an App or play downloaded music/podcasts/YouTube (including the option to chrome-cast without wifi - using BlueTooth (or similar with high bandwidth), NFC/UWB for simple pairing).

3. Auto-upgrade to use the network when it’s available, like use current traffic data for directions, hi-res images/audio/video.

Bonus: When offline, Apps like Spotify, Gmail, etc should also run some local search options for downloaded data.

Bonus: When offline/online, restaurants should have NFC/UWB servers for their menu. My iPhone should just “download” the menu from the POS system. No need for “signal” or wifi.

1. Some are possible now: https://apps.apple.com/us/app/minipedia-offline-wikipedia/id.... 2. Airplay doesn't require a wifi network. Just wifi on, it uses the same thing as Airdrop.

Bonus 1: you can search your offline library in spotify. Bonus 2: this used to be common back in the 00s but it was generally decided to be mostly spam. Bonus: local search for downloaded spotify stuff works without a connection.

I guess Siri does work at least partially serverside?

The ML part is local for the voice transcription but the questions almost always need to be answered from the server. But if you ask to play music or set a timer for example that is all local. Also works in Airplane mode.

yet they can't manage offline Maps and directions without internet connectivity.

It's your phone.

I just tried this as it was really bad. Kept saying everything was a picture of the night sky, only one of many many descriptions was correct.

Interesting, I pointed it at my son and it immediately accurately described "a child sitting at a white table doing a jigsaw puzzle". I pointed at one of his Lego creations, and immediately "a multi-colour lego construction sitting on a wooden shelf". I was blown away.

I tried to get Voice Over working but scroll broke once enabled. It says three fingers to scroll but that just won't work for me.

VoiceOver is a completely different UI. You need to learn how it works before attempting to use it.

Turns out iOS was broken and a reboot made the three finger scrolling work.

Put three fingers next to each other on the screen and move them up to scroll down.

Tried this over and over again. No luck. Weird!

You have to tap the part of the screen you want to scroll, first.

It looks like it doesn't work with non-english languages.

Well that sucks in this day and age.

Does VO in general not work for non-English?

Url changed from https://www.loopinsight.com/2021/05/13/apple-support-how-to-..., which points to this.

Reply on news.ycombinator.com