A system provides intelligent gallery management for biometrics. A first gallery is obtained that includes biometric and/or other information on a population of people. An application is identified. A subset of the population of people is identified based on the application. A second gallery is derived from the first gallery by pulling the information for the subset of the population of people without pulling the information for the population of people not in the subset. Biometric identification (such as facial recognition) for the application may then be performed using the second gallery rather than the first gallery. In this way, the system is improved as less time is required for biometric identification, fewer device resources are used, and so on.

A system provides intelligent gallery management for biometrics. A first gallery is obtained that includes biometric and/or other information on a population of people. An application is identified. A subset of the population of people is identified based on the application. A second gallery is derived from the first gallery by pulling the information for the subset of the population of people without pulling the information for the population of people not in the subset. Biometric identification (such as facial recognition) for the application may then be performed using the second gallery rather than the first gallery. In this way, the system is improved as less time is required for biometric identification, fewer device resources are used, and so on.

Disclosed is a method for training shallow convolutional neural networks for infrared target detection using a two-phase learning strategy that can converge to satisfactory detection performance, even with scale-invariance capability. In the first step, the aim is to ensure that only filters in the convolutional layer produce semantic features that serve the problem of target detection. L2-norm (Euclidian norm) is used as loss function for the stable training of semantic filters obtained from the convolutional layers. In the next step, only the decision layers are trained by transferring the weight values in the convolutional layers completely and freezing the learning rate. In this step, unlike the first, the L1-norm (mean-absolute-deviation) loss function is used.

Provided are an illegal building identification method and apparatus, a device, and a storage medium, which relate to the field of cloud computing. The specific implementation scheme is: acquiring a target image and a reference image associated with the target image; extracting a target building feature of the target image and a reference building feature of the reference image, respectively; and determining, according to the target building feature and the reference building feature, an illegal building identification result of the target image.

The present disclosure relates to a method, performed by at least one processor of an information processing system, of analyzing a pathological image. The method includes receiving a pathological image, detecting an object associated with medical information, in the received pathological image by using a machine learning model, generating an analysis result on the received pathological image, based on a result of the detecting, and outputting medical information about at least one region included in the pathological image, based on the analysis result.

An object of the present disclosure is to provide an information processing apparatus, an information processing system, an information processing method, and an information processing program capable of achieving efficient use of training data. An information processing apparatus according to the present disclosure includes: a recognition unit (101) that performs object recognition processing using sensor information acquired by a sensor, the object recognition processing being performed by a first recognizer that has been pretrained; and a training data application determination unit (22d) that determines whether the sensor information is applicable as training data to a second recognizer different from the first recognizer.

In one example, an apparatus comprises: a first sensor layer, including an array of pixel cells configured to generate pixel data; and one or more semiconductor layers located beneath the first sensor layer with the one or more semiconductor layers being electrically connected to the first sensor layer via interconnects. The one or more semiconductor layers comprises on-chip compute circuits configured to receive the pixel data via the interconnects and process the pixel data, the on-chip compute circuits comprising: a machine learning (ML) model accelerator configured to implement a convolutional neural network (CNN) model to process the pixel data; a first memory to store coefficients of the CNN model and instruction codes; a second memory to store the pixel data of a frame; and a controller configured to execute the codes to control operations of the ML model accelerator, the first memory, and the second memory.

Described are examples for detecting objects in an image on a device including setting, based on a condition, a number of sparse proposals to use in performing object detection in the image, performing object detection in the image based on providing the sparse proposals as input to an object detection process to infer object location and classification of one or more objects in the image, and indicating, to an application and based on an output of the object detection process, the object location and classification of the one or more objects.

Described are examples for detecting objects in an image on a device including setting, based on a condition, a number of sparse proposals to use in performing object detection in the image, performing object detection in the image based on providing the sparse proposals as input to an object detection process to infer object location and classification of one or more objects in the image, and indicating, to an application and based on an output of the object detection process, the object location and classification of the one or more objects.

Various methods, apparatuses/systems, and media for data processing are disclosed. A processor receives a digital document; applies an optical character recognition (OCR) algorithm on said received digital document by utilizing an OCR tool; identifies defective data extracted by the OCR tool resulted from relatively inferior image quality of the received digital document; implements an auto rectification algorithm on the identified defective data; automatically generates, in response to implementing the auto rectification algorithm, corresponding auto-rectified data for each identified defective data; records the defective data and corresponding auto-rectified data at a field level; receives user input data on said recorded auto-rectified data; determines whether the auto-rectified data is correct or not; and populates, based on determining that the auto-rectified data is correct, a machine learning model with said received user input data to be utilized for subsequently received digital document.