Computerized tomography detection of microbial damage of plant tissues
View Patent ↗The present disclosure encompasses embodiments of X-ray computed tomography-based methods for the detection of onion quality factors. Such methods are advantageous in detecting internal damage to onion bulbs due to bacterial and fungal rots and mechanical damage while also providing for the overall assessment of onion bulb quality and market value. Because CT images provide cross-sectional reconstructions of the subject under study, CT scans of onion bulbs can be used not only to detect damage from disease, but also cuts and bruises that increase an onion bulb's susceptibility to disease, and the presence of shoots or seed stems and overall shape of the bulbs.
1. A non-transitory computer-readable medium embodying a program executable in at least one computing device, comprising code that:
accesses a computed tomography (CT) image of an onion bulb;
processes the image of the CT image to adjust a quality of the CT image;
identifies an outline of the onion bulb in the CT image;
identifies a plurality of interior voids of the onion bulb;
generates a shape description of the onion bulb based at least in part on the plurality of interior voids, the outline of the onion bulb, or a combination thereof;
generates a plurality of measurements for the interior voids of the onion bulb; and
generates a classification for the onion bulb describing a condition of the onion bulb based at least in part on the plurality of measurements, the shape description, or a combination thereof, wherein performing image processing further comprises generating a modified image of the onion bulb comprising only the plurality of interior voids of the onion bulb, wherein the classification is generated based at least in part on the modified image.
2. A system, comprising:
at least one computing device; and
an onion classification application executed in the at least one computing device, the onion classification application comprising logic that:
accesses a computed tomography (CT) image of an onion bulb;
processes of the CT image to adjust a quality of the CT image;
identifies an outline of the onion bulb in the CT image;
identifies a plurality of interior voids of the onion bulb;
generates a shape description of the onion bulb based at least in part on the plurality of interior voids, the outline of the onion bulb, or a combination thereof;
generates a plurality of measurements for the interior voids of the onion bulb; and
generates a classification for the onion bulb describing a condition of the onion bulb based at least in part on the plurality of measurements, the shape description, or a combination thereof, wherein performing image processing further comprises generating a modified image of the onion bulb comprising only the plurality of interior voids of the onion bulb, wherein the classification is generated based at least in part on the modified image.
3. A computer-implemented method, comprising:
accessing, by at least one computing device comprising at least one hardware processor, a computed tomography (CT) image of an onion bulb;
performing, by the at least one computing device, image processing of the CT image to adjust a quality of the CT image;
identifying, by the at least one computing device, an outline of the onion bulb in the CT image;
identifying, by the at least one computing device, a plurality of interior voids of the onion bulb;
generating, by the at least one computing device, a shape description of the onion bulb based at least in part on the plurality of interior voids, the outline of the onion bulb, or a combination thereof;
generating, by the at least one computing device, a plurality of measurements for the interior voids of the onion bulb; and
generating, by the at least one computing device, a classification for the onion bulb describing a condition of the onion bulb based at least in part on the plurality of measurements, the shape description, or a combination thereof, and wherein performing image processing further comprises generating, by the at least one computing device, a modified image of the onion bulb comprising only the plurality of interior voids of the onion bulb, wherein the classification is generated based at least in part on the modified image.