[HN Gopher] When memory was measured in kilobytes: The art of ef...
___________________________________________________________________
When memory was measured in kilobytes: The art of efficient vision
Author : todsacerdoti
Score : 138 points
Date : 2025-06-04 16:46 UTC (1 days ago)
(HTM) web link (www.softwareheritage.org)
(TXT) w3m dump (www.softwareheritage.org)
| alightsoul wrote:
| Amazing. Wonder how fast it would be on a modern computer
| Hydration9044 wrote:
| +1, which is faster when compare to OpenCV findContours
| kmoser wrote:
| I want to believe that however obsolete these old algorithms are
| today, at least some aspects of the underlying code and/or logic
| should prove useful to LLMs as they try to generate modern code.
| klodolph wrote:
| Maybe... some of these algorithms from the 1980s struggled to
| do basic OCR, so they may need a lot of modification to be
| useful.
| PaulHoule wrote:
| That whole approach of "find edges, convert to line drawing,
| process a line drawing" in the 1980s struggled to do anything
| at all.
| Retric wrote:
| There was a surprising amount of useful OCR happening in
| the 70's.
|
| High error rates and significant manual rescanning can be
| acceptable in some applications, as long as there's no
| better alternative.
| GuB-42 wrote:
| I find that modern OCR, audio transcription, etc... are
| beginning to have the opposite problem: they are too
| smart.
|
| It means that they make a lot fewer mistakes, but when
| they do, it can be subtle. For example, if the text is
| "the bat escaped by the window", a dumb OCR can write
| "dat" instead of "bat". When you read the resulting text,
| you notice it and using outside clues, recover the
| original word. An smart OCR will notice that "dat" isn't
| a word and can change it for "cat", and indeed "the cat
| escaped by the window" is a perfectly good sentence,
| unfortunately, it is wrong and confusing.
| devilbunny wrote:
| Thankfully, most speech misrecognition events are still
| obvious. I have seen this in OCR and, as you say, it is
| bad. There are enough mistakes in the sources; let us not
| compound them.
| taeric wrote:
| I'm not sure I can sign on to this. In particular, this
| sounds kind of like an indictment of many algorithms. But,
| how many where there? And did any go on to give good results?
|
| Considers, OCR was a very new field, such that a lot of the
| struggle was getting data into a place you could even try
| recognition against it. It should be no surprise that they
| were not able to succeed that often. It would be more
| surprising if they had a lot of different algorithms.
| monkeyelite wrote:
| The idea that ML is the only way to do computer vision is a
| myth.
|
| Yes, it may not make sense to use classical algorithms to try
| to recognize a cat in a photo.
|
| But there are often virtual or synthetic images which are
| produced by other means or sensors for which classical
| algorithms are applicable and efficient.
| thatcat wrote:
| Any recommendations on background reading for classical CV
| for radar?
| monkeyelite wrote:
| I don't know anything about radar. I have a book called
| "machine vision" (Shmuck, Jain, Kasturi) easy undergrad
| level, but also very useful. It's $6 on Amazon.
| ipunchghosts wrote:
| Kasturi was my undergraduate honors advisor!
| monkeyelite wrote:
| Small world! These are always just names on a book to me.
| sceadu wrote:
| Don't know about radar but here's a good book on classical
| CV https://udlbook.github.io/cvbook/
|
| even though I think Simon admits that most of it is
| obsolete after DL computer vision came about
| sokoloff wrote:
| I worked (as an intern) on autonomous vehicles at Daimler in
| 1991. My main project was the vision system, running on a
| network of transputer nodes programmed in Occam.
|
| The core of the approach was "find prominent horizontal
| lines, which exhibit symmetry about a vertical axis, and
| frame-to-frame consistency".
|
| Finding horizontal lines was done by computing variances in
| value. Finding symmetry about a vertical axis was relatively
| easy. Ultimately, a Kalman filter worked best for frame-to-
| frame tracking. (We processed video in around 120x90 output
| from variance algorithm, which ran on a PAL video stream.)
|
| There's probably more computing power on a $10 ESP32 now, but
| I really enjoyed the experience and challenge.
|
| This was our vehicle: https://mercedes-benz-
| publicarchive.com/marsClassic/en/insta...
| digdugdirk wrote:
| That's awesome! What kind of hardware was needed to pull
| that off? And was the size of the bus any indication of the
| answer?
| cyberax wrote:
| One approach that blew my mind was the use of FFT to recognize
| objects.
|
| FFT has this property that object orientation or location doesn't
| matter. As long as you have the signature of an object, you can
| recognize it anywhere!
| changoplatanero wrote:
| I believe orientation still matters but you're right that
| position doesn't.
| Legend2440 wrote:
| FFT is equivalent to convolution, which is widely used today
| for object recognition in CNNs.
| bobmcnamara wrote:
| > FFT is equivalent to convolution
|
| What do you mean by that? Could you give me an example?
| timewizard wrote:
| The basic convolution theorem.
|
| https://en.wikipedia.org/wiki/Convolution_theorem
| bobmcnamara wrote:
| That is something else entirely.
| timewizard wrote:
| Then if you know what the OP meant why did you ask?
| kragen wrote:
| The FFT, composed with pointwise multiplication, composed
| with the inverse FFT, is equivalent to convolution. The FFT
| is not.
| mrheosuper wrote:
| I still deal with <128kb ram system everyday
| weareregigigas wrote:
| I too need a coffee in the morning before I can do anyhting
| DaSHacka wrote:
| Ah, Mac user?
___________________________________________________________________
(page generated 2025-06-05 23:01 UTC)