Methods and systems for defects detection and classification using X-rays
AssigneeBruker Nano, Inc.
InventorsDavid Lewis Adler, Freddie Erich Babian
Life of this patent
Estimating the term…
Abstract
In one embodiment, an automated high-speed X-ray inspection system may identify reference objects for an object of interest to be inspected. Each reference object may have a same type and components as the object of interest. The system may generate a reference model for the object of interest based on X-ray images of the reference objects. The system may determine whether the object of interest is associated with one or more defects by comparing an X-ray image of the object of interest to the reference model. The defects may be characterized by one or more pre-determined defect models and may be classified into respective defect categories based on the pre-determined defect models.
Claims21
A method comprising, by an automated high-speed X-ray inspection system:
- identifying one or more reference objects for an object of interest to be inspected, wherein each reference object has a same type and components as the object of interest;
- generating a reference model for the object of interest based on one or more X-ray images of the one or more reference objects;
- and
- determining whether the object of interest is associated with one or more defects by comparing a first X-ray image of the object of interest to the reference model, wherein the one or more defects are characterized by one or more pre-determined defect models, and wherein, when the object of interest is associated with the one or more defects, the one or more defects are classified into respective defect categories based on the one or more pre-determined defect models, wherein the reference model is generated based on a weighted average of two or more X-ray images of the one or more reference objects, the weighted average providing a pixel by pixel average of variations specific to the X-ray images based on a standard object of interest.
One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
- identify one or more reference objects for an object of interest to be inspected, wherein each reference object has a same type and components as the object of interest;
- generate a reference model for the object of interest based on one or more X-ray images of the one or more reference objects;
- and
- determine whether the object of interest is associated with one or more defects by comparing a first X-ray image of the object of interest to the reference model, wherein the one or more defects are characterized by one or more pre-determined defect models, and wherein, when the object of interest is associated with the one or more defects, the one or more defects are classified into respective defect categories based on the one or more pre-determined defect models, wherein the reference model is generated based on a weighted average of two or more X-ray images of the one or more reference objects, the weighted average providing a pixel by pixel average of variations specific to the X-ray images based on a standard object of interest.
A system comprising:
- one or more processors;
- and one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
- identify one or more reference objects for an object of interest to be inspected, wherein each reference object has a same type and components as the object of interest;
- generate a reference model for the object of interest based on one or more X-ray images of the one or more reference objects;
- and
- determine whether the object of interest is associated with one or more defects by comparing a first X-ray image of the object of interest to the reference model, wherein the one or more defects are characterized by one or more pre-determined defect models, and wherein, when the object of interest is associated with the one or more defects, the one or more defects are classified into respective defect categories based on the one or more pre-determined defect models, wherein the reference model is generated based on a weighted average of two or more X-ray images of the one or more reference objects, the weighted average providing a pixel by pixel average of variations specific to the X-ray images based on a standard object of interest.
Dependencies are inferred from the claim text.