• site home
  • blog home
  • galleries
  • contact
  • underwater
  • the bleeding edge

the last word

Photography meets digital computer technology. Photography wins -- most of the time.

You are here: Home / The Last Word / Artificial intelligence and camera firmware

Artificial intelligence and camera firmware

April 1, 2024 JimK 3 Comments

The folks at Lirpa Labs, the research arm of Sloof Lirpa, made a big announcement today. It’s a first for the company, which has previously developed standalone products. Lirpa will be providing firmware upgrades for Sony, Canon, Nikon, Leica, Hasselblad, and Fujifilm cameras. The Lirpa firmware will add entirely new artificial intelligence capabilities to those cameras, with the objective of improving the esthetics of the images made.

One of the beauties of the new firmware is the simplicity of the user interface. There is no on/off control; the AI features remain active all the time. There are no parameters to set; the firmware is designed well enough that it needs no tuning by the user. When the photographer depresses the shutter release, the camera analyses the scene, and decides if it’s up to snuff. If it is, the shutter is released. If not, the camera displays messages in the finder like:

  • Sorry, that ain’t gonna cut it.
  • Close, but you’re not getting the cigar.
  • Nice try, bozo.
  • You’ve got to be kidding
  • You call yourself a photographer?
  • Not happening.
  • That sucks.

Note that the camera gives the photographer no indication of what they are doing wrong. This is a conscious decision on the part of the design tem, intended to encourage deep learning on the part of the wetware behind the camera (that’s you!), as well as in the firmware inside the camera. The photographer is forced to try different framings, aperture and shutter speed settings, camera positioning, lens selection, and the like before the camera will let the image be captured. This trial and error behavior on the part of the photographer, sometimes under time pressure, serves to implant the lessons learned in memory, making it less likely that the photographer will repeat the error.

Lirpa labs prototype AI camera, before they decided to go the firmware upgrade route

There’s also a motivation for the photographer to practice. The very real possibility of the camera’s refusing to make images at a once-in-a-lifetime event means that the photographer is highly incentivized to do dry runs under every conceivable anticipated situation. As further motivation, to give the photographer time to contemplate their sins, the camera will refuse to take any pictures for an hour after 12 bad attempts in a row.

There is one matter that has concerned the Lirpa Labs development team. Many of the beta test cameras suffered mechanical damage during the trial phase. The development team was unable to ascertain the reasons for that. Much of the damage seemed to be the result of impact, as if the cameras had been thrown to the ground or against a wall. In the absence of understanding the root cause of the damage, the team has decided to ship each firmware upgrade with a sturdy plastic shock-absorbing case specific to each camera model for which the firmware was written.

There is no reversing course; once the AI firmware is installed, it cannot be removed, only upgraded as Lirpa releases new versions.

Thanks to the geniuses at Lirpa Labs, we can expect the quality of our photographs to improve immeasurably.

 

The Last Word

← Circles of confusion, and circles of the confused 105/2.8 Nikkor S on Nikon Z8, Siemens Star →

Comments

  1. JaapD says

    April 5, 2024 at 12:10 pm

    I appreciate you’ve taken the effort. Nicely created Lirpa article Jim. Okay I’ll stop here, not spoiling the fun factor …..
    All the best!

    Reply
  2. Dennis says

    April 27, 2024 at 4:49 am

    Absolutely the best April X article I’ve read! Keep all your articles coming Jim!

    Reply
  3. Deed says

    June 4, 2024 at 1:51 pm

    Here’s a thought: I would actually be interested in a camera which would pickup some of the design language. WR might be an issue though, but, what the hell: life is short!!

    Reply

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

May 2025
S M T W T F S
 123
45678910
11121314151617
18192021222324
25262728293031
« Apr    

Articles

  • About
    • Patents and papers about color
    • Who am I?
  • How to…
    • Backing up photographic images
    • How to change email providers
    • How to shoot slanted edge images for me
  • Lens screening testing
    • Equipment and Software
    • Examples
      • Bad and OK 200-600 at 600
      • Excellent 180-400 zoom
      • Fair 14-30mm zoom
      • Good 100-200 mm MF zoom
      • Good 100-400 zoom
      • Good 100mm lens on P1 P45+
      • Good 120mm MF lens
      • Good 18mm FF lens
      • Good 24-105 mm FF lens
      • Good 24-70 FF zoom
      • Good 35 mm FF lens
      • Good 35-70 MF lens
      • Good 60 mm lens on IQ3-100
      • Good 63 mm MF lens
      • Good 65 mm FF lens
      • Good 85 mm FF lens
      • Good and bad 25mm FF lenses
      • Good zoom at 24 mm
      • Marginal 18mm lens
      • Marginal 35mm FF lens
      • Mildly problematic 55 mm FF lens
      • OK 16-35mm zoom
      • OK 60mm lens on P1 P45+
      • OK Sony 600mm f/4
      • Pretty good 16-35 FF zoom
      • Pretty good 90mm FF lens
      • Problematic 400 mm FF lens
      • Tilted 20 mm f/1.8 FF lens
      • Tilted 30 mm MF lens
      • Tilted 50 mm FF lens
      • Two 15mm FF lenses
    • Found a problem – now what?
    • Goals for this test
    • Minimum target distances
      • MFT
      • APS-C
      • Full frame
      • Small medium format
    • Printable Siemens Star targets
    • Target size on sensor
      • MFT
      • APS-C
      • Full frame
      • Small medium format
    • Test instructions — postproduction
    • Test instructions — reading the images
    • Test instructions – capture
    • Theory of the test
    • What’s wrong with conventional lens screening?
  • Previsualization heresy
  • Privacy Policy
  • Recommended photographic web sites
  • Using in-camera histograms for ETTR
    • Acknowledgments
    • Why ETTR?
    • Normal in-camera histograms
    • Image processing for in-camera histograms
    • Making the in-camera histogram closely represent the raw histogram
    • Shortcuts to UniWB
    • Preparing for monitor-based UniWB
    • A one-step UniWB procedure
    • The math behind the one-step method
    • Iteration using Newton’s Method

Category List

Recent Comments

  • JimK on Goldilocks and the three flashes
  • DC Wedding Photographer on Goldilocks and the three flashes
  • Wedding Photographer in DC on The 16-Bit Fallacy: Why More Isn’t Always Better in Medium Format Cameras
  • JimK on Fujifilm GFX 100S II precision
  • Renjie Zhu on Fujifilm GFX 100S II precision
  • JimK on Fuji 20-35/4 landscape field curvature at 23mm vs 23/4 GF
  • Ivo de Man on Fuji 20-35/4 landscape field curvature at 23mm vs 23/4 GF
  • JimK on Fuji 20-35/4 landscape field curvature at 23mm vs 23/4 GF
  • JimK on Fuji 20-35/4 landscape field curvature at 23mm vs 23/4 GF
  • Ivo de Man on Fuji 20-35/4 landscape field curvature at 23mm vs 23/4 GF

Archives

Copyright © 2025 · Daily Dish Pro On Genesis Framework · WordPress · Log in

Unless otherwise noted, all images copyright Jim Kasson.