What are we talking about ?
Photographers who shoot high-volume like headshots for corporation, schools or retail fashion are now using more and more integrated software based on QR code to speed up their workflow. The QR code is segmenting the shoot by subject, each being uploaded eventually on a dedicated space only accessible to the customer interested by the subject. It can be an image of the QR code shot which is synonymous with “the shoot of the subject ends here” or a device on the camera modifying the metadata adding a QR code to each image, it does not change the result: a segmentation of the shoot by subject thanks to a QR code.
There is still a catch though: the shoot is well organized by subject, fair enough, but the culling for each subject is still needed. When a photographer shoots typically a couple of dozens of images by subject, only a few to say a dozen are useful for the clients who tend to prefer having some choice but no need to browse dozens of similar images, and of course no images that are not of the quality needed in terms of sharpness, exposure, or the composition of the image.
AI can nowadays help the photographer during this culling process. But how can AI be helpful for a shoot of hundreds of images segmented by subject thanks to QR code ?
Why is it so much a problem?
High-volume is a productivity challenge for the photographer. The photo culling done by an AI software must respect the segmentation by subject, organized thanks to the QR code.
But it must also be customized to the needs of the photographer – what is sharp enough for one photographer won’t be to another one, and some photographers want to keep only 50% of the images shot, other only 20%, and so on. Whereas the thresholding of such rules is frequently implemented on AI photo culling software, the segmentation by QR code is rarely done out-of-the box.
How to fix it ?
It is a workflow challenge. What AI can do well for photo culling must respect the segmentation by subject. It is not a temporality question, nor a similarity issue (some faces – like sisters/brothers can look the same by the way), it is purely a subject segmentation, driven by the QR codes. And the way the software is culling the images must respect this.
What are the main features required:
- Detection of QR Codes (either as an image or as metadata embedded in each photo),
- Segmentation by subject,
- Culling by subject,
- File management done finally with both QR codes for identification or in metadata and in specific subfolders.
Is this available off the shelf?
Short answer : yes !
In details: Futura Photo has implemented on its enterprise edition the automated culling by subject thanks to a QR code shot at the beginning of each series of images for a given subject.
If you are using QR Codes that are saved as metadata for each image, it could be easily based on the metadata saved, FP could retrieve such metadata and organize the shoot accordingly.
If you are interested in such a solution, please contact firstname.lastname@example.org
Below a video with a demo of Futura Photo culling images of several subjects, with QR Codes images between two subjects:
Disclaimer: I am the founder of Camera Futura