An information processing apparatus (100) includes an acquisition unit (122) that acquires a first image from which person region feature information regarding a region including other than a face of a retrieval target person is extracted, a second image in which a collation result with the person region feature information indicates a match, and a facial region is detected, and result information indicating a collation result between face information stored in a storage unit and face information extracted from the facial region, and a display processing unit (130) that displays at least two of the first image, the second image, and the result information on an identical screen.

Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

An authentication system includes first and second authentication devices. The first authentication device judges whether a relationship between a first similarity based on a captured image and a registered image between a subject of authentication that is a person in the captured image and a subject of comparison that is a person in the registered image by the first authentication device. When it is judged that a predetermined condition is satisfied, the first authentication device instructs a second authentication device to perform identification authentication. When an instruction is received from the first authentication device, the second authentication device identifies a relationship between a second similarity that is a similarity calculated based on a captured image and a registered image between the subject of authentication and the subject of comparison by the second authentication device, and performs identification authentication of the subject of authentication according to an identification result.

Techniques are disclosed for determining whether to include a bodyprint in a cluster of bodyprints associated with a recognized person. For example, a device performs facial recognition to identify the identity of a first person. The device also identifies and stores physical characteristic information of the first person, the stored information associated with the identity of the first person based on the recognized face. Subsequently, the device receives a second video feed showing an image of a second person whose face is also determined to be recognized by the device. The device then generates a quality score for physical characteristics in the image of the user. The device can then add the image with the physical characteristics to a cluster of images associated with the person if the quality score is above a threshold, or discard the image if not.

A system and method for high-confidence error overbounding of multiple optical pose solutions receives a set of candidate correspondences between 2D image features captured by an aircraft camera and 3D constellation features including at least one ambiguous correspondence. A candidate estimate of the optical pose of the camera is determined for each of a set of candidate correspondence maps (CMAP), each CMAP resolving the ambiguities differently. Each candidate pose estimate is evaluated for viability and any non-viable estimates eliminated. An individual error bound is determined for each viable candidate pose estimate and CMAP, and based on the set of individual error bounds a multiple-pose containment error bound is determined, bounding with high confidence the set of candidate CMAPs and multiple pose estimates where at least one is correct. The containment error bound may be evaluated for accuracy as required for flight operations performed by aircraft-based instruments and systems.

A visual search recommendation engine utilizes an image quality indication model for a visual search recommendation. Specifically, the visual search recommendation engine receives a search image as a search query at a search engine. The visual search recommendation engine provides the search image as an input into the image quality indication model, which is trained to output an image quality indication based on image aspects of the search image. A plurality of images are identified from an image corpus. The visual search recommendation engine determines an image similarity based on a comparison between the plurality of images from the image corpus and the search image. The image quality indication and the image similarity indicate a search query performance for the search image. A first image exceeding the search query performance is identified. The first image is provided for display at the search engine.

A medical image processing device includes an image acquisition unit that acquires a medical video image, a brightness analysis unit that analyzes brightness information of each of a plurality of specific medical images within a specific time range among a plurality of medical images constituting the medical video image to output brightness analysis information, and an image selection unit that selects a training medical image to be used for machine learning from among the plurality of specific medical images using the brightness analysis information.

The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program capable of appropriately evaluating an object recognition filter by simpler processing. A generation unit that generates teacher data of a preprocessing filter provided in a preceding stage of the object recognition filter is generated by a cyclic generative adversarial network (Cyclic GAN) that is unsupervised learning. The teacher data generated by the generated generation unit is applied to the object recognition filter, an evaluation image is generated from a difference between object recognition result images, and an evaluation filter that generates an evaluation image from the evaluation image and the teacher data is generated. The evaluation filter is applied to an input image to generate an evaluation image, and the object recognition filter is evaluated by the generated evaluation image. The present disclosure can be applied to an object recognition device.

Embodiments of the present application provide a method for fingerprint identification, and electronic device. The method includes: acquiring a first image collected by a fingerprint sensor at a first exposure time; determining whether to acquire a second image collected by the fingerprint sensor at a second exposure time according to the first image, where the second exposure time is continuous with the first exposure time, and a length of the second exposure time is greater than or equal to a length of the first exposure time; performing fingerprint identification according to the first image, or, the first image and the second image. The method, and electronic device of the embodiments of the present application can take into account an unlocking rate and unlocking time, thereby improving unlocking experience of a user.

The present disclosure provides a method, apparatus and computer program product for suppressing noise in 3D road surface reconstruction. The method includes: acquiring an image related to a road surface; extracting horizontal line information and ROI (region of interest) information from the image, wherein the horizontal line information comprises a horizontal line pixel value, and the ROI information is used to perform 3D road surface reconstruction for the road surface; judging whether the difference between the horizontal line pixel value and a preset horizontal line pixel value is greater than a pixel threshold; judging whether the horizontal line pixel value is greater than a compensation threshold when the difference is greater than the pixel threshold; determining a compensation value based on the difference when the horizontal line pixel value is not greater than the compensation threshold; and adjusting the ROI information based on the compensation value.