Abstract: Described herein are systems, methods and instrumentalities associated with image segmentation. The systems, methods and instrumentalities have a hierarchical structure for producing a coarse segmentation of an anatomical structure and then refining the coarse segmentation based on a shape prior of the anatomical structure. The coarse segmentation may be generated using a multi-task neural network and based on both a segmentation loss and a regression loss. The refined segmentation may be obtained by deforming the shape prior using one or more of a shape-based model or a learning-based model.

Abstract: A flexible, artifact-free, and lensless fiber-based imaging system for biological objects. This system combines image reconstruction by a trained deep neural network with low-loss image transmission through disordered glass-air Anderson localized optical fiber. High quality images of biological objects can be obtained using short (few centimeters) or long (more than one meter) segments of disordered fiber with and without fiber bending. The deep neural network can also be designed to perform image classification. The system provides the unique property that the training performed within a straight fiber setup can be utilized for high fidelity reconstruction/classification of images that are transported through either straight or bent fiber making retraining for different bending situations unnecessary.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for testing performance of a biometric characteristic recognition device. One of the methods includes obtaining a target simulated component for testing performance of the biometric characteristic recognition device from a plurality of simulated components. A mechanical arm is controlled, based on a camera component arranged on the mechanical arm, to input biometric characteristic information of the target simulated component to the biometric characteristic recognition device. A recognition result is obtained from the biometric characteristic recognition device and a performance test result of the biometric characteristic recognition device is determined based on the recognition result.

Abstract: A computer-implemented system for processing image data. The system comprises: a sensor operable to capture image data comprising an image of an environment of the sensor; and a processing circuit comprising: a processor; and a computer-readable storage medium comprising computer-readable instructions which, when executed, cause the processor to: receive the image data from the sensor; process the image data using a first path through a neural network to obtain first data, the first path configured to indicate a presence in the environment of one or more objects of a predetermined object type; process the image data using a second path through a neural network to obtain second data, the second path configured to indicate a presence in the environment of one or more object characteristics corresponding to the predetermined object type; and generate output data using the first and second data, wherein the first and second paths are arranged to be enable the first and second data to be obtained in parallel.

Abstract: Disclosed is a computer program stored in a computer readable storage medium according to an exemplary embodiment of the present disclosure. When the computer program is executed by one or more processors of a computing device, the computer program may perform operations for managing a model, and the operations may include: generating an anomaly detection model including a plurality of anomaly detection sub models having a pre-learned network function through using a plurality of training data subsets included in a training data set; determining one or more anomaly detection sub models for calculating an input data among the generated anomaly detection sub models; and judging whether or not the anomaly is existed in the input data through using the one or more determined anomaly detection sub models.

Abstract: Techniques for recognizing text in an image are described. An exemplary method may include receiving a request to recognize text in an image; extracting features from the image and generating a visual feature sequence from the extracted features; performing selective contextual refinement at least one selective contextual refinement block of a stack of selective contextual refinement blocks to generate a text prediction by: generating a contextual feature map and combining the contextual feature map with the visual feature sequence into a visual feature space, and applying a selective decoder that utilizes a two-step attention on the visual feature space to generate a text prediction, wherein the two-step attention includes performing a 1-D self-attention computation to generate attentional features and decoding the attentional features to generate the text prediction; and outputting the generated text prediction.

Abstract: A method implemented by a client device includes accessing a plurality of image frames captured by one or more cameras of the client device and generating a working image frame based at least in part on one or more of the plurality of image frames. The method further includes classifying one or more first objects detected in the working image frame based at least in part on a determined desirability of the one or more first objects. The one or more first objects are determined to be undesirable. The method further includes applying a pixel filtering process to the working image frame to replace one or more first pixel sets associated with the first objects with pixels from one or more image frames of the plurality of image frames to generate a final image frame, and displaying the final image frame on a display of the client device.

Abstract: An anchor determination includes: performing feature extraction on an image to be processed to obtain a first feature map of the image to be processed; performing anchor prediction on the first feature map via an anchor prediction network to obtain position information of anchors and shape information of the anchors in the first feature map, the position information of the anchors referring to information about positions in the first feature map where the anchors are generated. A corresponding anchor determination apparatus and a storage medium are also provided.

Abstract: In a computer-implemented method and system for capturing the condition of a structure, the structure is scanned with an unmanned aerial vehicle (UAV). Data collected by the UAV corresponding to points on a surface of a structure is received and a 3D point cloud is generated for the structure, where the 3D point cloud is generated based at least in part on the received UAV data. A 3D model of the surface of the structure is reconstructed using the 3D point cloud.

Abstract: A system and method are described for enhancing readability of document images by operating on each document individually. Monochromatic light sources operating at different wavelengths of light can be used to obtain greyscale images. The greyscale images can then be used in any desired image enhancement algorithm. In one example algorithm, an automated method removes image background noise and improves sharpness of the scripts and characters using edge detection and local color contrast computation.

Abstract: The present invention generally relates to a method for authenticating a finger of a user of an electronic device comprising a fingerprint sensor for sensing a fingerprint pattern, the method comprising the steps of: acquiring a candidate fingerprint image; determining, based on the candidate fingerprint image, a humidity level indication indicative of the humidity level of the finger; performing an authentication pre-process based on the humidity level indication; performing a fingerprint authentication process based on the pre-process to authenticate the user.

Abstract: Systems and methods for detecting, counting and analyzing the blood content of a surgical textile are provided, utilizing an infrared or depth camera in conjunction with a color image.

Abstract: Provided are a method for fingerprint recognition, an electronic device, and a non-transitory computer-readable storage medium. The method is applicable to the electronic device. The method includes the following. An image of a user's finger placed on a fingerprint collecting region of a display screen of the electronic device is collected as an original fingerprint image. A corrected fingerprint image is obtained according to the original fingerprint image and a predetermined foreign material image, where the predetermined foreign material image is obtained when the user's finger is not placed on the fingerprint collecting region and indicative of a foreign material on the fingerprint collecting region. Determine whether a match between the corrected fingerprint image and a pre-stored fingerprint image exists by comparing the corrected fingerprint image with the pre-stored fingerprint image. The electronic device is triggered to perform a preset action in response to that the match exists.

Abstract: The present invention concerns a method of classification of an input image representative of a biometric trait by means of a first convolutional neural network, CNN, characterized in that it comprises the implementation by data processing means (21) of a client (2) of steps of: (c) Estimation of a transformation parameter vector of said input image, by means of a second CNN, the parameters of the vector being representative of a geometric transformation enabling the biometric trait represented by the input image to be registered in a common reference frame; (d) Application to said input image of a transformation defined by said estimated transformation parameter vector, so as to obtain a registered input image; (e) Classification of the registered input image by means of the first CNN.

Abstract: An elongated biometric device provides a slim solution for capturing biometric data, and may be placed on a portion of an electronic device having limited space, such as a side of the electronic device. The elongated biometric device may include a force sensor, which may be positioned within a housing of the electronic device and actuated through posts extending from the elongated biometric device through the housing to transfer an applied force to the force sensor.

Abstract: A learning device comprises: an acquisition unit that acquires a first feature amount derived by an encoder from data with an identification object recorded therein, the encoder being configured so as to derive, from data with the identical object in various forms recorded therein, feature amounts which are mutually convertible by a conversion using a conversion parameter that takes a value according to the difference in the forms; a conversion unit that generates a second feature amount by performing a conversion on the first feature amount using the conversion parameter value; and a parameter updating unit that updates the value of a sorting parameter used in sorting by a sorting means, which is configured to sort second feature amounts as input, such that if the second feature amount has been input, the sorting means outputs a result indicating, as a sorting destination, a class associated with the identification object.

Abstract: In a computer-implemented method and system for capturing the condition of a structure, the structure is scanned with an unmanned aerial vehicle (UAV). The UAV receives an instruction to collect information on at least one aspect of a property, and identifies one or more onboard sensors of the UAV to collect the information on the at least one aspect of the property, where the UAV is configured to identify a first set of one or more onboard sensors to collect a first type of data and to identify a second set of one or more onboard sensors to collect a second type of data. The UAV also collects the information on the at least one aspect of the property using the one or more onboard sensors, and identifies, based on the collected information, a type of damage incurred on the at least one aspect of the property.

Abstract: A biometric analysis structure, method and neural network with coded mask are provided. The biometric analysis structure includes a display panel, a light source, and a sensor. The sensor is disposed on the optical path of light from the light source and reflected by the display panel. The biometric analysis structure includes an coded mask. The coded mask is disposed on the optical path in front of the sensor. the coded mask is represented as a first matrix in a matrix form and the first matrix is a delta function after satisfying an autocorrelation operation. The resulting image can be inversely resolved based on the image of the coded mask. Thus, the security of the fingerprint recognition method is improved, and the thickness of the entire imaging structure is reduced.

Abstract: Systems and methods for training a neural keypoint detection network are disclosed herein. One embodiment extracts a portion of an input image; applies a transformation to the portion of the input image to produce a transformed portion of the input image; processes the portion of the input image and the transformed portion of the input image using the neural keypoint detection network to identify one or more candidate keypoint pairs between the portion of the input image and the transformed portion of the input image; and processes the one or more candidate keypoint pairs using an inlier-outlier neural network, the inlier-outlier neural network producing an indirect supervisory signal to train the neural keypoint detection network to identify one or more candidate keypoint pairs between the portion of the input image and the transformed portion of the input image.

Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.