For image quality scoring of an image from a medical scanner, a generative model of an expected good quality image may be created using deep machine-learning. The deviation of an input image from the generative model is used as an input feature vector for a discriminative model. The discriminative model may also operate on another input feature vector derived from the input image. Based on these input feature vectors, the discriminative model outputs an image quality score.

A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

Methods and computer readable media for facilitating training of a recognition model. An embodiment includes generating media items based on information associated with a representation of a graphic, the information including content other than the graphic, content based on at least one transformation parameter set, and content comprising the graphic integrated with the other content, then using a recognition model to process the media items to generate predictions related to recognition of the graphic for the media items, the generated predictions including an indication of a predicted location of the graphic in a first media item. The process also includes presenting an indication of the predicted location on an area of the first media item via a user interface to a user, then obtaining a reference feedback set that includes reference indications related to recognition of the graphic for the media items and including user feedback concerning the indication of the predicted location of the graphic, and then updating the recognition model based on the reference feedback.

A learning computer system may include a data processing system and a hardware processor and may estimate parameters and states of a stochastic or uncertain system. The system may receive data from a user or other source. Parameters and states of the stochastic or uncertain system are estimated using the received data, numerical perturbations, and previous parameters and states of the stochastic or uncertain system. It is determined whether the generated numerical perturbations satisfy a condition. If the numerical perturbations satisfy the condition, the numerical perturbations are injected into the estimated parameters or states, the received data, the processed data, the masked or filtered data, or the processing units.

Disclosed is a method and system for processing images from an aerial imaging device. An image of an object of interest is received from the aerial imaging device. A parameter vector is extracted from the image. Image analysis is performed on the image to determine a height and a width of the object of interest. Idealized images of the object of interest are generated using the extracted parameter vector, the determined height, and the determined width of the object of interest. Each idealized image corresponds to a distinct filled volume of the object of interest. The received image of the object of interest is matched to each idealized image to determine a filled volume of the object of interest. Information corresponding to the determined filled volume of the object of interest is transmitted to a user device.

An information processing device according to the present invention includes: a proper identifier output unit which outputs proper identifiers for identifying learning images; a feature vector calculation unit which calculates feature vectors of at least a part of patches included in registered patches that are registered in a dictionary for compositing a restored image; and a search similarity calculation unit which calculates a similarity calculation method that classifies the proper identifiers to be given to the registered patches based on the feature vectors.

An image processing device including an object detection unit for detecting one or more images of objects from an input picture image, on the basis of a model pattern of the object, and a detection result display unit for graphically superimposing and displaying a detection result. The detection result display unit includes a first frame for displaying the entire input picture image and a second frame for listing and displaying one or more partial picture images each including an image detected. In the input picture image displayed in the first frame, a detection result is superimposed and displayed on all the detected images, and in the partial picture image displayed in the second frame, a detection result of an image corresponding to each partial picture image is superimposed and displayed.

A method includes passing an original text document through distortion filter generators to generate a training dataset that includes distorted text documents. Each distortion filter generator is configured to distort words or letters of words in phrases of text of a facsimile image in a respective unique manner. A neural network model is trained to recognize each respective distortion and match each respective distortion with each respective distortion filter generator based on the training dataset and the original text document. Image data of one facsimile having at least one text distortion is received and inputted to the trained neural network model. The output of the trained neural network model is coupled to an input of an optical character recognition (OCR) engine. The trained neural network model and the OCR engine convert the received image data of the incoming facsimile corrected for the at least one text distortion to machine-encoded text.

A determination method for determining the structure of a convolutional neural network includes acquiring N filters having the weights trained using a training image group as the initial values, where N is a natural number greater than or equal to 1, and increasing the number of the filters from N to M, where M is a natural number greater than or equal to 2 and is greater than N, by adding a filter obtained by performing a transformation used in image processing fields on at least one of the N filters.

The present disclosure discloses a method for training an adversarial network model, a method for building a character library, an electronic device and a storage medium, which relate to a field of artificial intelligence, in particular to a field of computer vision and deep learning technologies, and are applicable in a scene of image processing and image recognition. The method for training includes: generating a new character by using the generation model based on a stroke character sample and a line character sample; discriminating a reality of the generated new character by using the discrimination model; calculating a basic loss based on the new character and a discrimination result; calculating a track consistency loss based on a track consistency between the line character sample and the new character; and adjusting a parameter of the generation model according to the basic loss and the track consistency loss.