Hacker News new | ask | show | jobs
Ask HN: What do you want your camera to understand?
3 points by Huongngtm 2030 days ago
I'm thinking over the question how broad computer vision can be applied. Or whether it is more valuable within certain fields. So, I'd like to know what's your imagination about it. If your phone camera can recognize anything and give you information about it, what do you want it to be?

Let's limit within object recognition only, for the sake of simplicity. A few examples are coffee beans, plant diseases, knitting styles.

5 comments

I believe this is one key reason why so many use FB and willing to give up their identity including others; to keep track of their pictures.

I believe with the advent of the digital picture age and $15 128GB SDCards. People have so many pictures they can't manage, they will rely on anything that gives them a bit of control with minimal effort: FB w/ facial recognition.

I believe the singular aspect of what a camera should be able id faces. Then embed that info in the metadata to be pulled later.

The caveat to that is it must be kept private, never be uploaded onto a cloud and metadata encrypted.

Although like others, I have GBytes of pictures but the only ones precious enough to keep track of are the ones with faces on them. Object recognition, yeah kool but if I could query: find all pics of my son. BAM! be very happy.

So to give up my idea I'll never implement: 1. ID faces but only locally. 2. Embed face info as metadata of the picture file. 3. Crawler that walks regularly through all your pictures AND videos and ID's faces. 4. A natural query language to find all pics by relationship, name, age, sex, time and date

Re-reading your question, failed to initially understand. sorry.

Your question has already been answered: Google Lens. Matter of fact, i just used it on a tree I couldn't ID so I took a pic of it using Googl Lens and voila with their long reach search arm, BAM! I found it. I've done this many time befores with the Lens app. So not sure what more you can add to what seem to already work as your looking for?

I'm just curious what we would love to use object recognition for, in a context as broad as possible. Plant identification is a convincing use case.

By the way, storing images with face recognition is quite convenient using Google Photos too.

> I'm just curious what we would love to use object recognition for

Mix in ML to identifying food for their nutritional content, calorie intake monitor and future projection on your health if you stay on this course.

There is an old adage; You are what you eat.

I'm in the process of doing just this. I've taken pictures of every meal/snack whatever I ingested since 2005. I have over 15,000 images of food. Now that ML and computing power has come into play. I want to create this exact thing. Then correlate with my health. I want to see if there are cause and effect to my eating.

Furthermore, I have my exercise history as well.

I am what you call: Quantify Self.

Another use-case for your ask is cataloging or inventory. Two of the hardest and only human capable things. Imagine not a neatly piled but a large heap of things. How does an AI/robot make sense of it? What is it? How many are there? Is it heavy? Moveable? etc...

Your ask is very large open ended question.

What exactly is your endgame?

> quite convenient using Google Photos too

Googl already has too much of me. The last thing I want is all of my pictures stored, triaged, scanned, archived. I'm pretty darn sure they are using them as a great ML dataset. The images you get off of general searches are junk compared to the goldmine of a personally curated gallery. Big difference.

Given camera sensors can view things we can’t (UV and IR spectrums come to mind), maybe stuff like is this person having a fever, how good is my sunscreen application on my face, how hot is this thing, etc.

Also distances could be computed from camera + gps or accelerometer?

Object recognition only and using a phone camera limits my ideas,but off the top of my head:

Actors in TV and Internet advertisements

Animal scat or Animal footprints

What the stains on someones clothes were made from (yuck)

How many jelly beans or whatever are in a jar

The freshness of produce (especially those pre-made salads that can wilt before you get them home)

Poisonous plants and mushrooms

1. What is this bug?

2. Who is this person? (With regards to event attendees, not a random girl on the train)

3. Is this chicken supposed to be this color? Is this avocado ripe?

4. Is this the russet potato my wife wanted me to buy?

When i m reading something, don't turn put the screen to sleep. That's all