Back to results
US 12,770,242 B2Granted
Semiconductor image processing apparatus and semiconductor image processing method
AssigneeKioxia Corporation
InventorsShuhei Iijima, Osamu Yamane, Youyang Ng, Yuchieh Lin, Takuji Ohashi, Takeshi Fujiwara
Life of this patent
Estimating the term…
Abstract
A semiconductor image processing apparatus including a processing circuitry, the processing circuitry configured to identify a label corresponding to a feature amount included in an input image by using an identifier, learn a model for inferring the feature amount included in the input image and learns the identifier, and perform additional learning of the model based on the input image and the learned identifier.
Claims20
A semiconductor image processing apparatus comprising a processing circuitry, the processing circuitry configured to:
- perform learning a model for inferring a feature amount included in an input image and learning an identifier identifying a label corresponding to the feature amount included in the input image on the basis of an output of the model;
- and
- perform additional learning of the model based on the input image and the learned identifier, wherein
- the input image includes a simulated image having a known true answer label or a real image having an unknown label, and
- the additional learning includes
- calculating a first loss function value based on a label corresponding to a first inference image inferred by inputting the simulated image to the model and the true answer label of the simulated image,
- calculating a second loss function value based on the label predicted by inputting a second inference image inferred by inputting the real image to the model to the identifier, and
- updating a parameter of the model based on a third loss function value obtained by adding the first loss function value and the second loss function value.
5 more elements
A semiconductor image processing apparatus comprising a processing circuitry, the processing circuitry configured to:
- perform a learning a model for inferring a feature amount included in an input image and a learning an identifier identifying a label corresponding to the feature amount included in the input image on the basis of an output of the model;
- and
- perform an additional learning of the model based on the input image and the learned identifier, wherein the processing circuitry is further configured to:
- generate a background difference image obtained by removing a background pattern from the input image;
- calculate an average pixel value for each first pixel region in a first direction of an input image,
- generate a first simulated background image based on the average pixel value for each first pixel region in the first direction of the input image,
- generate a second simulated background image based on a pixel value obtained by subtracting, for each pixel, the average pixel value of the input image from a pixel value obtained by adding, for each pixel, the average pixel value for each first pixel region in the first direction of the input image and an average pixel value for each second pixel region in a second direction intersecting the first direction of the input image, and
- generate the background difference image of the input image by a difference between the input image and the first simulated background image or a difference between the input image and the second simulated background image, and
- generate a feature emphasis-processed image based on the feature amount included in the background difference image.
6 more elements
A semiconductor image processing method comprising:
- performing learning a model for inferring a feature amount included in an input image and learning an identifier identifying a label corresponding to the feature amount included in the input image on the basis of an output of the model;
- and
- performing additional learning of the model based on the input image and the learned identifier, wherein
- the input image includes a simulated image having a known true answer label or a real image having an unknown label, and
- the additional learning includes
- calculating a first loss function value based on a label corresponding to a first inference image inferred by inputting the simulated image to the model and the true answer label of the simulated image,
- calculating a second loss function value based on the label predicted by inputting a second inference image inferred by inputting the real image to the model to the identifier, and
- updating a parameter of the model based on a third loss function value obtained by adding the first loss function value and the second loss function value.
5 more elements
A semiconductor image processing method comprising:
- performing a learning a model for inferring a feature amount included in an input image and a learning an identifier identifying a label corresponding to the feature amount included in the input image on the basis of an output of the model;
- performing an additional learning of the model based on the input image and the learned identifier;
- generating a background difference image obtained by removing a background pattern from the input image;
- calculating an average pixel value for each first pixel region in a first direction of an input image,
- generating a first simulated background image based on the average pixel value for each first pixel region in the first direction of the input image,
- generating a second simulated background image based on a pixel value obtained by subtracting, for each pixel, the average pixel value of the input image from a pixel value obtained by adding, for each pixel, the average pixel value for each first pixel region in the first direction of the input image and an average pixel value for each second pixel region in a second direction intersecting the first direction of the input image, and
- generating the background difference image of the input image by a difference between the input image and the first simulated background image or a difference between the input image and the second simulated background image, and
- generating a feature emphasis-processed image based on the feature amount included in the background difference image.
5 more elements
Dependencies are inferred from the claim text.