Inspection method and apparatus
AssigneeCoglix Co. Ltd.
InventorsSeoung Je Jo, Jae Hun Park, Boo Han Lee
Life of this patent
Estimating the term…
Abstract
In an inspection method and apparatus, when thermal image data with respect to cap sealing of a particular container is analyzed and a low confidence score is obtained, products are classified into a user check product by a rejection-process of separating the products, without determining the products to be good products or not good products.
Claims15
A method of inspecting cap sealing of a container transferred along a process line, by using an infrared (IR) camera, the method comprising:
- photographing the cap sealing of the container located within a field of view (FOV) of the IR camera by using the IR camera;
- calculating a confidence score based on previously learned sample data and thermal image data corresponding to the photographed cap sealing;
- and
- comparing the calculated confidence score with a predefined confidence value range, and determining the cap sealing to be one of a good product, a not good product, and a user check product according to a result of the comparison,
- wherein, the previously learned sample data is generated by learning a plurality of cap sealing of the container according to the types of a good product and a not good product,
- the method further comprising predicting inspection accuracy of an object to be inspected based on the previously learned sample data;
- and displaying the predicted inspection accuracy.
An apparatus for inspecting cap sealing of a container transferred along a process line, by using an infrared (IR) camera, the apparatus comprising:
- an IR camera photographing the cap sealing of the container located within a field of view (FOV) of the IR camera;
- and
- a controller calculating a confidence score based on previously learned sample data and thermal image data corresponding to the photographed cap sealing, comparing the calculated confidence score with a predefined confidence value range, and determining the cap sealing to be one of a good product, a not good product, and a user check product according to a result of the comparison,
- wherein, the previously learned sample data is generated by learning a plurality of cap sealing of the container according to the types of a good product and a not good product,
- the controller predicting inspection accuracy of an object to be inspected based on the previously learned sample data and displaying the predicted inspection accuracy.
Dependencies are inferred from the claim text.