A Japanese company cut 80% of the time needed to manually count pearls

Wow, this is such a simple application of ML and it is incredibly valuable. On their website, they charge $100&#x2F;month per device or $1000&#x2F;year per device [0] and I bet they&#x27;re making a killing.<p>[0] <a href="https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;" rel="nofollow">https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;</a>

I think what the CountThings app is doing is great. There are too many industries where tasks are being performed inefficiently due to a lack of applying readily available technology. They had the foresight to develop a product for a very common problem and make a business out of it.<p>I’m a bit surprised that this is making the rounds of HN though. OpenCV and other computer vision libraries have trivialized such counting applications for decades now. ML isn’t really necessary.<p>The watershed algorithm for example, comes built-in and allows segmentation which can then be followed up with blob counting: <a href="http:&#x2F;&#x2F;www.cmm.mines-paristech.fr&#x2F;~beucher&#x2F;wtshed.html" rel="nofollow">http:&#x2F;&#x2F;www.cmm.mines-paristech.fr&#x2F;~beucher&#x2F;wtshed.html</a><p>I don’t want to diminish OP’s work since the product seems to be well-developed and respond to a real need. I guess the challenge must have been making the app robust enough to support different workloads, lighting conditions, etc. I suppose the novelty factor is seeing to what extent the technology that we as developers and engineers work on every day is often disconnected from practical application.

In a an image with sufficient contrast between the foreground and the background, thresholding and using the fast radial symmetry transform[1] should do the trick. I have some really old code that I wrote a few years back that does something similar. I was able to use the same algorithm for counting objects in images captured from a Neubauer chamber [2] and saved countless man hours at my university.<p>Disclaimer: the project is really old, and from a time when I barely knew how to code. Lots of bad coding practices et al.<p>Github: <a href="https:&#x2F;&#x2F;github.com&#x2F;vibhuagrawal14&#x2F;segmentation-of-overlapping-elliptical-objects" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;vibhuagrawal14&#x2F;segmentation-of-overlappin...</a><p>[1] <a href="https:&#x2F;&#x2F;link.springer.com&#x2F;content&#x2F;pdf&#x2F;10.1007%2F3-540-47969-4_24.pdf" rel="nofollow">https:&#x2F;&#x2F;link.springer.com&#x2F;content&#x2F;pdf&#x2F;10.1007%2F3-540-47969-...</a><p>[2] <a href="https:&#x2F;&#x2F;www.researchgate.net&#x2F;figure&#x2F;Images-of-Canis-familiaris-blood-sample-in-a-Neubauer-chamber-acquired-using-focus-a_fig3_315590666" rel="nofollow">https:&#x2F;&#x2F;www.researchgate.net&#x2F;figure&#x2F;Images-of-Canis-familiar...</a>

Hi, there! I&#x27;m one of the project managers at CountThings, I&#x27;ll try to respond to comments here but I guess you can AMA.

&gt; All good apps have already been created. There is no room for innovation.<p>&gt; Hold my beer:<p>&gt; I made an app that counts.<p>Honestly, the simplicity of the idea is amazing.

For anyone who&#x27;s complaining about the price, take a look at their whole offer:<p><a href="https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates" rel="nofollow">https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates</a>

To counter other’s points on pricing - in the end it’s a question of utility vs price. 1k$ per year to cut time to count by 80% may be a great deal to many.

This is great! A really simple technical idea paired with the right business model = success.<p>I&#x27;ve often wondered if there are other instances of this pattern - a phone app which solves some niche problem and is successful commercially being sold for a high price. Can anybody give other examples?

Is ML here needed? When I was working in a lab we used the opensource ImageJ for counting cells. It seems like it&#x27;d do a great job here too.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;ImageJ" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;ImageJ</a>

As someone that has worked in food science micro labs, this is a great product that lab operations would love for CFU counting.<p>Excellent work on a great product. Best of luck to you!

They are using an app <a href="https:&#x2F;&#x2F;countthings.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;countthings.com&#x2F;</a><p>This seems rather a simple task, however, the app is expensive ($100 per month per device) and limited with the templates for things it can count [1].<p>[1] <a href="https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates" rel="nofollow">https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates</a>

As someone who was worked in Japan for 13 years, I can vouch that this is a very strong testimonial. A Japanese company will not adopt new technology like this unless it highly accurate.

so how would you go about doing this using ml? is it a classification problem? Count the number of instances. Or do we do deep learning and say here is a picture the result is 10?

The really fun challenge, is counting how many distinct domains countthings is using for their promotion. You probably need to use Hyperloglog :)

Couldn&#x27;t they use a machine like a coin counter?

This is an advertisement &#x2F; press release, which is fine, but should be disclosed as such in the HN title.

When a player rolls 38 6-sided dice in a tabletop game, I&#x27;d like to have something similar.

This page from countthings.com makes it obvious that counting things isn’t all that trivial: <a href="https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates" rel="nofollow">https:&#x2F;&#x2F;countthings.com&#x2F;en&#x2F;counting-templates</a>

The tray used in the demonstration is almost white (beige?). Wouldn’t a black tray (hence darker background and higher contrast) increase accuracy?

They could not count by weight (before ML)? For e.g - If 100 pearls weight 10 gm etc? They could also have used a machine for counting them

Okay, I&#x27;m not sure why people use software to do the work that hardware has solved decades ago. Like, I know that pearls come in various shapes, sizes, and weights but they&#x27;re discrete objects. I would have assumed a simple machine similar to an egg counter would&#x27;ve already been on patent for such uses just for pearls. I mean the ML use case is still neat but I always feel that people always grab computers for the wrong reasons for tasks that aren&#x27;t that novel. Just my two cents.

I thought the tray in the thumbnail was the solution. What about a padded tray with dimples in rows of 10?

This is very cool, well done!<p>Are you using deep segmentation models or more traditional computer vision techniques?

I cut 50% of the time needed to manually count small objects by...counting in twos.

The website copy is a bit bad, but I can see the application and business use 100%.<p>I just didn&#x27;t expect to see a website like this today, I guess. It needs more polishing, but that&#x27;s the power of marketing I guess.

Nobody cares that this is just an ad? It&#x27;s got too many paragraphs of bullshit filler for something that&#x27;s basically &quot;they&#x27;re taking pictures and counting the pearls using machine learning&quot;.

Call me naive, but wouldn&#x27;t this be a lot easier - and more low-tech, thus cheaper, to sort by size with a sieve, then weight individual size-bags, and divide by the size of one pearl?<p>Assuming all pearls have comparative density.

I am not impressed, they could cut 1000% by using: big bawl, pipe, simple mechanical sorting mechanism, and electronic counter.

Humans on the other hand are really good at looking at patterns. I imagine a tray with some recesses that would receive the pearls after a bit of shaking or a funnel that would put all the pearls in a line and then somehow group them&#x2F;count them should not be that hard to do.<p>And yes outsourcing this to someone else and employing machine learning apparently also works.

Everyone here is amazed at the ML applications.<p>You need to know that the underlying technology is really basic and old. 15 years ago, I used a free library (blob counter) to build a VB.net application that counted and &quot;sexed&quot; fruit flies. The app as presented in this website is really similar. No rocket science going on here.<p>Move along, please.

terrible example. You can just make a square from pearls and multiply. If you need to do a lot of it make a box with numbers on the side, tilt it then count and add the remaining row. The weight is probably not irregular enough to justify the tool. There are better examples on the website.<p>Pricing is just silly. I&#x27;m sure it is worth that much to some 0.001% of the potential market.

Counting elements from pictures is how old again now? 20 years? 30 years?<p>Sure, it&#x27;s more reliable and you can run it on a phone. But maybe this could have been solved 20 years ago. (Yes, it might not have been as convenient, but for something that apparently is so important, it could have been applied earlier)<p>Japan, a country which in the 80s was synonymous with technological innovation seems to have slowed down dramatically in adopting new technologies<p>Edit: of course I&#x27;m not saying it&#x27;s exclusive to Japan. My comment was more in the way of &quot;the first time I saw an actual application of CV counting things in a practical setting was 20 years ago&quot;