Methods and arrangements for configuring industrial inspection systems
In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed.
1. A method comprising the acts:
capturing with a camera a series of images depicting a container, each of said images depicting said container at a different position within a camera frame, a first image in the series depicting the container at a first time, a second image in the series depicting the container at a second time after the first time, and a third image in the series depicting the container at a third time after the second time;
processing the first, second and third images, including filtering said first, second and third images, to produce first, second and third filtered image data corresponding to depiction of said container at said first, second and third times;
attempting to decode a 2D indicia from said first, second and third filtered image data, using a plurality of processor cores;
for said first, second and third filtered image data, and for first, second and third cores among said plurality of processor cores:
while the first core is outputting results of decoding a 2D indicia from the first filtered image data corresponding to depiction of said container at the first time, attempting to decode, with the second core, a 2D indicia from the second filtered image data corresponding to depiction of said container at the second time after said first time; and
while attempting with the second core to decode said 2D indicia from the second filtered image data corresponding to depiction of the container at the second time, receiving, for attempted decoding of a 2D indicia by the third core, the third filtered image data corresponding to depiction of the container at the third time after said second time.
2. The method of claim 1 that includes triggering said capturing of the series of images after the container passes a trigger location.
3. The method of claim 1 in which said 2D indicia comprises a steganographic digital watermark.
4. The method of claim 3 in which the container is marked with first and second 2D steganographic digital watermarks conveying first and second different payloads, wherein the first 2D steganographic digital watermark is conveyed by printing on a label that does not convey the second 2D steganographic digital watermark.
5. The method of claim 1 in which said container is labeled with multiple different 2D indicia.
6. The method of claim 5 in which said container is labeled with a front label and a neck label.
7. The method of claim 1 , practiced on a production line that packages foodstuffs, or that applies labels to containers.
8. The method of claim 1 that includes capturing said first, second and third images under flash illumination.
9. The method of claim 1 that includes identifying a ranked list of plural image excerpts within each of the first, second and third filtered image data, on which 2D indicia decoding should be attempted.
10. The method of claim 1 that includes decoding two different 2D indicia from said container.
11. A system responsive to a container, the system comprising:
a camera that outputs a series of images depicting said container at different positions within a camera frame, a first image in the series depicting the container at a first time, a second image in the series depicting the container at a second time after the first time, and a third image in the series depicting the container at a third time after the second time;
a multi-core processing system that is configured to perform acts including:
processing the first, second and third images, including filtering said first, second and third images, to produce first, second and third filtered image data corresponding to depiction of said container at said first, second and third times;
attempting to decode a 2D indicia from said first, second and third filtered image data, using a plurality of processor cores;
for said first, second and third filtered image data, and for first, second and third cores among said plurality of processor cores:
while the first core is outputting results of decoding a 2D indicia from the first filtered image data corresponding to depiction of said container at the first time, attempting to decode, with the second core, a 2D indicia from the second filtered image data corresponding to depiction of said container at the second time after said first time; and
while attempting with the second core to decode said 2D indicia from the second filtered image data corresponding to depiction of the container at the second time, receiving, for attempted decoding of a 2D indicia by the third core, the third filtered image data corresponding to depiction of the container at the third time after said second time.
12. The system of claim 11 in which said multi-core processing system is further configured to identify a ranked list of plural image excerpts within each of the first, second and third filtered image data, on which said 2D indicia decoding should be attempted.
13. The system of claim 11 that further includes said container, said container bearing two different 2D indicia.
14. The system of claim 13 in which said two different 2D indicia are first and second digital watermarks conveying first and second different payloads.
15. The system of claim 14 in which the container includes a label printed with said first digital watermark conveying said first payload, but not printed with said second digital watermark conveying said second payload.