dlau

Precious | Senior iOS Engineer | San Francisco, CA | Full-time Onsite | main@preciousapp.com

At Precious, our goal is to make families happier, healthier and stronger. We are an iPhone app that uses AI to curate your child's photos.

Parents take 1,000's of photos & videos of their kids, and our vision is to use AI to make it effortless to curate the best moments, create a digital journal, and share it with family. We have over $200,000 of monthly recurring revenue and recently raised our seed round.

We are hiring a Senior iOS Developer to join us as the first employee.

You'll get to architect, build and scale our primary product. As employee #1, you will have massive impact on the product and the company.

Email us at main@preciousapp.com

Hey Chris, you are right. I was accidentally using your categorization endpoint instead of tags endpoint. The tag results seem to be good.

Yes, that's what the website demo returns back. The full API response is what I reported.

By the way, I'm on the look-out for other image classification services or open-source projects. I know I can (and will) deep dive into Tensor Flow deep-learning, but any other suggestions are really welcome!

After trialling several image recognition and categorization API services, Watson was by far the least impressive when you use their default classifier.

For a project I've been building, I have used Clarif.ai, Google Vision API, Watson, and Imagga. From empirical tests, Watson has always provided poor, if not hilariously non-sensical, results. As an example, I use this image of a baby in a stroller (https://dl.dropboxusercontent.com/u/898689/IMG_2948.jpg). Here are the results in classification tags from the 4 services:

Clarifai: people, child, vehicle, woman, one, man, outdoors, emergency, accident, protest, adult, transportation system, carriage, portrait, wheelchair, safety, road, bike, leisure, wheel

Google: baby carriage, car seat, child, vehicle, diving equipment

Watson: performing, escalator, repairing, indoors, celebration, dancing, human, amusement arcade, bottle, baggage claim, group of people, appliance, tiger, people, big group, child, mixed color

Imagga: people portraits

These results obviously may vary depending on image subject, composition, etc., but I've basically dismissed Watson as a viable off-the-shelf visual recognition API. That being said, if you have a specific dataset of images that positively and negatively identify a concept, Watson's custom classifiers may be of interest although I haven't tried that.

I'm super glad that Professor Moerner is getting credit where credit is due. Having taken his intro seminar and interned in his lab my freshmen year, I can attest he's a really great teacher as well.

On a side note, I hope this added recognition will pump more money into his lab's equipment. Despite being a physical chemistry lab, their computers were painfully slow and outdated.

This is going to be my first time at SXSW, and my brother and I wanted to get as much knowledge and ideas from the conference as possible. The site is a bit sparse in notes right now, of course, since the conference doesn't start for another day or two. But, we would love it if other SXSW attendees want to help spread the wealth by sharing their notes. Just go here if you want to learn more: http://upword-notes.tumblr.com/post/78600992601/shareyoursxs...