Jump to content

Watch movement recognition software


Recommended Posts

I was wondering if it is possible to create an app that can identify an unknown movement just by taking a photo of it.

There are plant identification apps available at this present moment. I think the algorithms should be similar.

So all the software designers out there, what say you?

Link to comment
Share on other sites

3 hours ago, HectorLooi said:

I was wondering if it is possible to create an app that can identify an unknown movement just by taking a photo of it.

There are plant identification apps available at this present moment. I think the algorithms should be similar.

So all the software designers out there, what say you?

You mean an app when people forget how to read?

SR - Copy.PNG

SR1 - Copy.PNG

  • Haha 1
Link to comment
Share on other sites

No expert here. Sure it is possible.

I tried googling some pictures of watch movements, it either bring me the same picture or of some other watches and occasionaly pots and pans instead, oh and an arse once by the name of Rolex.

Who else would have the required archive of pictures. 

 

 

Link to comment
Share on other sites

It would be a very useful app "Bestfit" and "Paulsons master key" are by far the best way of identifying watch movements because as anyone who has dealt with watches form the early 1900-1940 identification can be the biggest hinderance to finding parts, identifying the keyless works is the only way because we all know that a lot of  movements from that period do not have nice shiny calibre numbers engraved in prominent places to be read.

Edited by wls1971
Link to comment
Share on other sites

Ranfft has an OK advanced search feature, but it's very manual and leaves a lot to be desired. With a bit of practice, it'll give you a good list of candidates which will  include your answer or at least a similar movement from the same design, if it's in his database. You can limit your search based on the bridge layout details and some features. You can't, for example, limit your search by size or by approximate year even though this info is in the db. Sometimes this can be an advantage, if for example you've got an unspecified model that is based on an earlier or different sized design. It also seems to not work well if you input too many parameters. 

If you could take his database and improve the search querying and the sorting, plus add some image recognition to the movement ID scheme, it would be fun to try.

 

 

  • Like 1
Link to comment
Share on other sites

There are countless movements that get posted on here for I D many that don't have any markings at all, the only way is by looking at the keyless  work or going on line, not many on here have old reference books. I posted my Bestfit catalogues some time ago on here for people to download but even so they don't have everything. Its a must, so who ever you are make it happen.  

  • Like 1
Link to comment
Share on other sites

It's almost impossible (currently) to make an app like this.  The plant finder apps or similar use "convolution neural networks" that are trained on thousands of user identified pictures of the subject.  They're particularly good at this task as the subject has a fractal nature to it.  Watch movements however aren't.  The subtle differences between the size and shape of the keyless works would be hard to match to training images.

If I were tasked to program this I'd use an "expert system".  It would require more work from the user, they'd have to measure parts etc but it would be more accurate in finding the correct movement.

For example, the app might start by asking you "Does the movement have sweep seconds", and you'd answer yes, no or unknown.  From that it could half the movements it knows about a bit like playing 20 questions.

Link to comment
Share on other sites

  • 4 weeks later...

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.



  • Recently Browsing

    • No registered users viewing this page.
  • Topics

  • Posts

    • Yes, "Sold out" is difficult to understand. There doesn't seem to be a lot going on. It's been nine months since any new video was published on the Watch Repair Channel. The Level 4 course on watchfix.com has been in progress for what feels like forever (several years!?). Maybe Mark's enterprises aren't doing well or perhaps already so profitable there's nothing much to motivate him for more material. Or, perhaps these days he's more into crochet. The real reason is probably something entirely different but it would be nice/interesting to know. I don't mean to sound gloomy or pessimistic, but I wouldn't be surprised to be met by an HTTP 404. Every day feels like a gift. Speaking of watchfix.com I've been postponing the "Level 5: Servicing Chronograph Watches" course for a very, very long time. Anyway, I just enrolled on it so it's going to be very interesting to see the videos. I must say, IMO there's nothing really that can compete with Mark's courses when it comes to presentation and video quality. It's simply world-class and makes me associate with some really expensive BBC productions.
    • Steel has some funny properties, or at least counterintuitive. The modulus of elasticity is effectively (not exactly, but close enough) the same for steel that is annealed and hardened. What changes is the point of plastic deformation* . If the movement of your spring doesn't pass that, it should work fine. It looks a little thick, I would thin it a bit maybe from the main body out about halfway, maybe 10-20% thinner (not in thickness, along its form). But if it works it works!   *So- if you have two bars of the same steel, one annealed, one at 600 Vickers (general hardness watch arbors might be), clamp them to a table so the same length is hanging out, and put a weight on the ends, they will bend the same amount. But if you continue to add weight, then remove it, at a point the annealed bar won't return to its original straightness. That's the point of plastic deformation. But up to that point, as springs, they are the same. However- their wear characteristics will be very very different. And getting the hardened bar past its point of plastic deformation takes a lot more effort.
    • @JohnR725 now that you've mentioned it. This is actually the second aftermarket spring (same place and brand) I ordered as the first one broke. The eye on which the arbor pulls on, broke off on the first spring after the first wind, and also it was a bit to large for the arbor. Looked like on one the second picture in the 2nd group. The second one was exactly the same, I had to bend it a bit, to give it a more prominent curve to the end of the spring so that the arbor catches the eye.  Also I believe both were 5-10mm shorter. Not that I writing that, I feel a bit dumb, as the spring might actually been the problem all along, although its advertised as a substitute to the original...     
    • The CS70 is the only one they show as annealed.  A further search on ebay, I found CS75 and CS100 annealed carbon steel strips  e.g. https://www.ebay.co.uk/itm/314072784422
    • Aloha and thanks for catching all these small but important details, John.  I'm going to give it a shot. The good news is I have a parts movement here with a perfect complete balance.  I will place them side by side for visual reference when doing what you outlined.  It's been a while were I've had a hobby in which I joined a forum.  I forgot just how helpful everyone can be. Mahalo. Frank.
×
×
  • Create New...