Detecting bCodes

Lets begin by downloading an example image that shows a lot of bees with a bCode attached to their thorax. The bCodes in this image are fairly small and are therefore difficult to detect. To improve the detection rate, we will use the scaling.factor parameter to magnify the image and the sharpening.sigma and sharpening.amount parameters to sharpen it. We will detect bCodes in the magnified and sharpened image at 8 equally spaced intensity thresholds between 40 and 110, and only report a detected bCode if at least 85% of its template (excluding the border) are preserved, by running

java -jar bcode_detector.jar scaling.factor=1.2 sharpening.sigma=1.6 \
sharpening.amount=0.9 min.intensity.threshold=40 max.intensity.threshold=110 \
intensity.step.size=10 min.template.conservation=0.85 conserve.margin=0 \
input.file=2013-07-18-13-57-25-600.jpg

This will result in a file named detected_bcodes.txt that contains raw bCode detection results.

Hints: When processing videos, the frame rate of the video must be specified with the frame.rate parameter. To process more than one image or video file, create a plain text file that lists one image or video file on each line and use this file as the input.file.

Before examining bCode detection results or processing them with another program, you should probably convert them to a more convenient format (not required for this tutorial):

java -jar converter.jar raw.bCode.file=detected_bcodes.txt \
human.readable.file=converted_bcode_detections.txt

This will produce a file named converted_bcode_detections.txt in the format described here.