An image recognition method includes a feature amount extracting step of generating, from an input image, a base feature map group including a plurality of base feature maps; an inferring step of deriving a plurality of inference results using each of a plurality of machine-learned inference devices for a plurality of inference inputs based on the base feature map group; and an integrating step of integrating the plurality of inference results by a specific manner to derive a final inference result, where each of the plurality of inference inputs has some or all base feature maps of the plurality of base feature maps, and each of the plurality of inference inputs has the some or all base feature maps that are different in part or whole from the some or all base feature maps of another inference input in the plurality of inference inputs.

A teaching data correction device sets, for teaching data indicating an object area where an object of interest exists in a training image, a correction candidate area which is an area to be a correction candidate of the object area, the training image being used for learning. The teaching data correction device generates an output machine based on the correction candidate area, the output machine being learned to output, when an image is inputted thereto, an identification result or a regression result relating to the object of the interest. Then, the teaching data correction device updates the teaching data by the correction candidate area based on an accuracy of the output machine, the accuracy being calculated based on the identification result or the regression result outputted by the output machine.

A teaching data correction device sets, for teaching data indicating an object area where an object of interest exists in a training image, a correction candidate area which is an area to be a correction candidate of the object area, the training image being used for learning. The teaching data correction device generates an output machine based on the correction candidate area, the output machine being learned to output, when an image is inputted thereto, an identification result or a regression result relating to the object of the interest. Then, the teaching data correction device updates the teaching data by the correction candidate area based on an accuracy of the output machine, the accuracy being calculated based on the identification result or the regression result outputted by the output machine.

Provided is a method of recognizing a business card by a terminal through federated learning, including receiving an image of the business card; extracting a feature value from the image including text related to a field of an address book set in the terminal; inputting the feature value into a first common prediction model and determining first text information from an output of the first common prediction model; analyzing a pattern of the first text information and inputting the first text information into the field; caching the first text information and second text information received for error correction of the first text information from a user; and training the first common prediction model using the image, the first text information, and the second text information, whereby each terminal may train and share the first common prediction model.

Systems and methods for generating and tracking shapes of a target may be provided. The method may include obtaining at least one first resolution image corresponding to at least one of a sequence of time frames of a medical scan. The method may include determining, according to a predictive model, one or more shape parameters regarding a shape of a target from the at least one first resolution image. The method may include determining, based on the one or more shape parameters and a shape model, at least one shape of the target from the at least one first resolution image. The method may further include generating a second resolution visual representation of the target by rendering the determined shape of the target.

An authentication device 100 of the present invention includes a registration unit 121 and a collation unit 122. The registration unit 121 acquires person identification information for identifying a registration requesting person who requests registration of authentication information, and individual identification information with which an individual can be identified, the individual identification information using a surface pattern of an object from an object image for registration in which the object held by the registration requesting person is captured, and registers the person identification information and the individual identification information in association with each other as registration data. The collation unit 122 acquires the individual identification information of the object from an object image for authentication in which the object held by the authentication requesting person who requests authentication is captured, checks whether or not the individual identification information is registered in the registration data, and when the individual identification information is registered, acquires, from the registration data, the person identification information associated with the individual identification information in the registration data, as the person identification information of the authentication requesting person.

An authentication device 100 of the present invention includes a registration unit 121 and a collation unit 122. The registration unit 121 acquires person identification information for identifying a registration requesting person who requests registration of authentication information, and individual identification information with which an individual can be identified, the individual identification information using a surface pattern of an object from an object image for registration in which the object held by the registration requesting person is captured, and registers the person identification information and the individual identification information in association with each other as registration data. The collation unit 122 acquires the individual identification information of the object from an object image for authentication in which the object held by the authentication requesting person who requests authentication is captured, checks whether or not the individual identification information is registered in the registration data, and when the individual identification information is registered, acquires, from the registration data, the person identification information associated with the individual identification information in the registration data, as the person identification information of the authentication requesting person.

A method of a defect detection of a plurality of semiconductor structures arranged on a wafer includes obtaining a microscopic image of the wafer. The microscopic image depicts the plurality of semiconductor structures. The method also includes obtaining, from a database, fingerprint data for each base pattern class of a set of base pattern classes associated with respective one or more semiconductor structures of the plurality of semiconductor structures. The method further includes performing the defect detection based on the fingerprint data and the microscopic image.

A three-dimensional shape descriptor extractor is implemented by collecting surface data from a three-dimensional shape as learning data and training a set of a prescribed encoder and a prescribed decoder by using the learning data, wherein the training extracts a three-dimensional shape descriptor from the learning data by using the encoder, undoes the three-dimensional shape descriptor by using the decoder, evaluates a difference between a state before using the encoding and a state after using the decoding, and adjusts the encoder and the decoder so as to reduce the difference, and mesh data is collected from the three-dimensional shape as the surface data and made to have a prescribed scale, so as to train the encoder and the decoder.

An image processor includes an edge detection portion for scanning an image and detecting, as edges, an arrangement of pixels in which brightness value difference or color parameter difference between the pixels is equal to or greater than a threshold; a grouping portion for grouping the detected edge based on edge length, a distance between endpoints of the edges, and an angle between the edges; a determination portion for determining the grouped edges as a dashed line edge group when a pattern, in which the brightness value difference or the color parameter difference between the pixels is detected, matches a predetermined pattern; a correction portion for performing a linear approximation process on the dashed line edge group to correct a coordinate value of an endpoint of the dashed line edge; and a parking frame setting portion for setting a parking frame using the corrected dashed line edge.