An image processing apparatus having a processor configured to: select a reference frame from a frame group including a plurality of images; acquire a reference correct answer frame representing a region of interest in the selected reference frame; generate a complementary correct answer frame corresponding to a frame other than the reference frame included in the frame group based on at least one reference correct answer frame; and generate a correct answer image group for machine learning from the reference correct answer frame and the complementary correct answer frame.

An image processing apparatus having a processor configured to: select a reference frame from a frame group including a plurality of images; acquire a reference correct answer frame representing a region of interest in the selected reference frame; generate a complementary correct answer frame corresponding to a frame other than the reference frame included in the frame group based on at least one reference correct answer frame; and generate a correct answer image group for machine learning from the reference correct answer frame and the complementary correct answer frame.

Methods and systems disclosed herein relate generally to systems and methods for generating simulated images for enhancing socio-demographic diversity. An image-generating application receives a request that includes a set of target socio-demographic attributes. The set of target socio-demographic attributes can define a gender, age, and/or race of a subject that are non-stereotypical for a particular occupation. The image-generating application applies the a machine-learning model to the set of target socio-demographic attributes. The machine-learning model generates a simulated image depicts a subject having visual characteristics that are defined by the set of target socio-demographic attributes.

A method for estimating parameters of an object which is to be estimated in a digital image which represents real imaged content, comprising at least: a) an initial step comprising the production of a dictionary of content components and the production of a dictionary of object components, the content components and the object components having the same dimensions as the digital image; b) a step of establishing, at the same time, the magnitude of each of the content components of the dictionary of content components and of the object components of the dictionary of object components present in the digital image; c) a step of establishing, from the magnitude of each of the object components, the value of at least one parameter which characterizes the object to be estimated.

Provided is a learning method, a learning program, a learning device, and a learning system, for training a classification model, to further raise the correct answer rate of classification by the classification model. The learning method includes execution of generating one piece of composite data by compositing a plurality of pieces of training data of which classification has each been set, or a plurality of pieces of converted data obtained by converting the plurality of pieces of training data, at a predetermined ratio, inputting one or a plurality of pieces of the composite data into the classification model, and updating a parameter of the classification model so that classification of the plurality of pieces of training data included in the composite data is replicated at the predetermined ratio by output of the classification model, by a computer provided with at least one hardware processor and at least one memory.

A method is provided for watermarking a machine learning model used for object detection. In the method, a first subset of a labeled set of ML training samples is selected. Each of one or more objects in the first subset includes a class label. A pixel pattern is selected to use as a watermark in the first subset of images. The pixel pattern is made partially transparent. A target class label is selected. One or more objects of the first subset of images are relabeled with the target class label. In another embodiment, the class labels are removed from objects in the subset of images instead of relabeling them. Each of the first subset of images is overlaid with the partially transparent and scaled pixel pattern. The ML model is trained with the set of training images and the first subset of images to produce a trained and watermarked ML model.

A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Provided is an abnormal data generation device capable of generating highly accurate abnormal data. The abnormal data generation device includes an abnormal data generation unit for generating pseudo generated data of abnormal data that has, in the same latent space, a normal distribution as a normal data generation model and an abnormal distribution expressed as a complementary set of the normal distribution and that is optimized such that pseudo generated data cannot be discriminated from observed actual abnormal data by a latent variable sampled from the abnormal distribution.

Helper neural network can play a role in augmenting authentication services that are based on neural network architectures. For example, helper networks are configured to operate as a gateway on identification information used to identify users, enroll users, and/or construct authentication models (e.g., embedding and/or prediction networks). Assuming, that both good and bad identification information samples are taken as part of identification information capture, the helper networks operate to filter out bad identification information prior to training, which prevents, for example, identification information that is valid but poorly captured from impacting identification, training, and/or prediction using various neural networks. Additionally, helper networks can also identify and prevent presentation attacks or submission of spoofed identification information as part of processing and/or validation.

An object of the present invention is to provide an image recognition system, an image recognition server, and an image recognition method having a new high security framework that can achieve utilization of multi-device diversity. The image recognition system according to the present disclosure includes a computationally non-intensive encryption algorithm based on random unitary transformation and achieves a high level of security. In addition, the image recognition system achieves high recognition performance by using ensemble learning to integrate recognition results based on the dictionaries of 4 different devices.