Abstract: In embodiments of event image curation, a computing device includes memory that stores a collection of digital images associated with a type of event, such as a digital photo album of digital photos associated with the event, or a video of image frames and the video is associated with the event. A curation application implements a convolutional neural network, which receives the digital images and a designation of the type of event. The convolutional neural network can then determine an importance rating of each digital image within the collection of the digital images based on the type of the event. The importance rating of a digital image is representative of an importance of the digital image to a person in context of the type of the event. The convolutional neural network generates an output of representative digital images from the collection based on the importance rating of each digital image.

Abstract: An image processing apparatus in an image processing system configured to generate a virtual point image using a plurality of images captured by a plurality of image capturing apparatus receives a first difference image being based on a difference between a third image based on image capturing performed by a third image capturing apparatus of the plurality of image capturing apparatuses and a second image based on image capturing performed by a second image capturing apparatus of the plurality of image capturing apparatuses and has a smaller data amount than that of the third image, and acquires a foreground image by extracting a predetermined object from the second image, using the received first difference image and a second difference image between a first image based on image capturing performed by a first image capturing apparatus of the plurality of image capturing apparatus and the second image.

Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.

Abstract: A plurality of source image pixels of a subset of image pixels of a source image cell of a selected color component of a digitized image are processed to generate a corresponding color component for each corresponding processed image pixel of a corresponding processed image cell, wherein the processed image pixels of the processed image cell are in one-to-one correspondence with the source image pixels of the source image cell, a bit length of the color component of each processed image pixel of the processed image cell exceeds a bit length of color component of each source image pixel the source image cell, the processed image cell contains substantial color information in excess of what could be contained within a bit length equal to the bit length of each the source image pixel of the color component of the source image cell.

Abstract: A computing device, programmed to: acquire a color image and transform the color image into a color-component map. The computer can be further programmed to process the color-component map to detect a traffic sign by determining spatial coincidence and determining temporal consistency between the color-component map and the traffic sign.

Abstract: Processing an image includes acquiring, by the image processing apparatus, a target image, extracting a shape of a target object included in the target image, determining a category including the target object based on the extracted shape, and storing the target image by mapping the target image with additional information including at least one keyword related to the category.

Abstract: A method for identifying and enumerating candidate target cells within a biological fluid specimen is described. The method includes obtaining a biological fluid specimen, preparing the biological fluid specimen by staining cell features in the biological fluid specimen, capturing a digital image having a plurality of color channels of the biological fluid specimen, and applying image analysis to the digital image. A computer program product for identifying candidate target cells within a biological fluid specimen is also described. The computer program comprises instructions to cause a processor to carry out the image analysis.

Abstract: A method and system for improving an automated facial recognition software system is provided. The method includes automatically detecting a face of a user via an IOT device. An image of the face is retrieved and image portions are extracted from the image and represented as a vector. The user is classified via determined facial feature attributes with respect to a plurality of user type weights stored in a cache and an initial user type of the user is determined. The vector and data indicating the initial user type are transmitted to a server and a process for inferring with respect to the initial user type, the vector, and images in a specified database associated with the initial user type, a final user type of the user s performed. An identity of the user is determined based on the inferring and the identity is transmitted to the IOT device.

Abstract: A system, method and computer program product cooperate to extract a building footprint from other data associated with a property. Imagery data of real property is input to a computing device, the imagery data containing a plurality of parcels. A processing circuit detects contrasts of candidate man-made structures on a parcel of the plurality of parcels. The candidate man-made structures are then associated with the parcel. A building footprint is then extracted by distinguishing a man-made structure on said parcel from natural terrain, recognizing that man-made structures when viewed from above generally show a strong contrast from background terrain. Remaining candidate man-made structures are removed by observing that they having features inconsistent with predetermined extraction logic.

Abstract: According to various embodiments, a light-field image may be compressed and/or decompressed to facilitate storage, transmission, or other functions related to the light-field image. A light-field image may be captured by a light-field image capture device having an image sensor and a microlens array. The light-field image may be received in a data store. A processor may generate a first refocus image pool with a plurality of refocus images based on the light-field image. The processor may further use the first refocus image pool to compress the light-field image to generate a bitstream, smaller than the light-field image, which is representative of the light-field image. The processor or a different processor may also be used to generate a second refocus image pool with a second plurality of images based on the bitstream. The second refocus image pool may be used to decompress the bitstream to generate a reconstructed light-field image.

Abstract: A fingerprint verification method includes selecting one or more first fingerprint groups from among a plurality of fingerprint groups based on an input fingerprint image, each fingerprint group of the plurality of fingerprint groups including partial fingerprint images; and determining whether verification is successful based on the input fingerprint image and each of the partial fingerprint images included in the one or more first fingerprint groups.

Abstract: Comprehensive 2D learning images are collected for learning subjects. Standardized 2D gallery images of many gallery subjects are collected, one per gallery subject. A 2D query image of a query subject is collected, of arbitrary viewing aspect, illumination, etc. 3D learning models, 3D gallery models, and a 3D query model are determined from the learning, gallery, and query images. A transform is determined for the selected learning model and each gallery model that yields or approximates the query image. The transform is at least partly 3D, such as 3D illumination transfer or 3D orientation alignment. The transform is applied to each gallery model so that the transformed gallery models more closely resemble the query model. 2D transformed gallery images are produced from the transformed gallery models, and are compared against the 2D query image to identify whether the query subject is also any of the gallery subjects.

Abstract: Techniques for compressing images based on context are provided. A first image and a second image may be identified for display on a client device. One or more contexts of the first image may be identified. One or more contexts of the second image may be identified. A first image quality for the first image may be determined based on the one or more contexts of the first image. A second image quality for the second image may be determined based on the one or more contexts of the second image. The first image may be compressed at the first image quality and the second image at the second image quality. The compressed first image and the compressed second image may be transmitted to the client device.

Abstract: Systems, methods, and non-transitory computer-readable media can acquire a first media content item. First mage dimensions associated with the first media content item can be determined. A first compression amount to be applied to the first media content item can be determined based on the first image dimensions associated with the first media content item. The first compression amount can be variable based on the first image dimensions associated with the first media content item. The first media content item can be compressed based on the first compression amount.

Abstract: In an embodiment, the disclosure includes an object detecting device. The object detecting device is configured to execute the instructions to: obtain a first picture comprising a first object at a first time instant; determine a first feature pattern of the first object based on the first picture; generate a first feature map of the first object based on the first feature pattern; generate a first feature vector of the first object based on the first feature map; and send the first feature vector to a server. In this embodiment, the first feature vector is generated based on the first feature map by the object detecting device rather than starting another process of directly generating the first feature map based on the first picture. Therefore, the speed and the computing resource cost of generating the feature vector may be better.

Abstract: An image processing system comprises: an image recognizing unit which performs image recognition to an image; a rule setting unit which sets a sorting rule to be used in case of transmitting the image recognized by the image recognizing unit to an external web service; and a transmitting unit which transmits, according to the sorting rule having a condition conforming to the image among the sorting rules set by the rule setting unit, information concerning the image to the corresponding external web service, thereby enabling to cooperate a still image/moving image sharing service and various web services with others.

Abstract: A system for multifunction peripheral assisted optical mark recognition uses a scanner to scan at least one printed page to generate a scanned image of the at least one printed page and to optically detect a presence of a visible label on the scanned image. Then, the multifunction peripheral may extract a model identification and a template identification from the visible label, select a template, identifying locations from which image data is to be extracted from the scanned image, select a model, specifically identifying at least two types of acceptable marks within the image data to be extracted from the scanned image, and perform optical mark recognition on the location from which image data is to be extracted identified by the template using the at least two types of acceptable marks identified by the model to extract useful data from the image data.

Abstract: A compression method for high-resolution light field display is disclosed for applications in which computer memory constraints and latency are critical. The disclosed compression algorithm takes advantage of the 3D structure of a light field to compress the raw light field information with a fixed compression ratio and simple decoding instructions. The compressed high-resolution light field achieves a reduced bandwidth with acceptable quality, and is packed in a way that can be transmitted using common interfaces. In a preferred embodiment, the compression algorithm is used as a post-processing stage after light field information acquisition or after rendering. In a further preferred embodiment, the compression algorithm is incorporated into the acquisition or rendering procedure to reduce memory and rendering processing. These and further embodiments generate a compressed light field with all information required for direct display.

Abstract: In one example implementation, a system for aligning of images of a three-dimensional (3D) object includes a select engine to select a first image and a second image from a sequence of images of a 3D object taken at different object orientations from a capture cycle of a scanner, a combine engine to combine first metadata from the first image and second metadata from the second image to form combined metadata, an orientation engine to select a third image from the sequence of images, where the third image is from an opposite object orientation relative to a first object orientation of the first image or a second object orientation of the second image, and an align engine to align the sequence of images based on the combined metadata and third metadata from the third image.

Abstract: Some implementations can include a computer-implemented method and/or system for automatic suggestion to share images. The method can include identifying a plurality of images associated with a user and detecting one or more entities in the plurality of images. The method can also include constructing an aggregate feature vector for the plurality of images based on the one or more entities in the plurality of images and determining that the aggregate feature vector matches a first cluster. The method can further include, in response to determining that the aggregate feature vector matches the first cluster, providing a suggestion to the user for an image composition based on the plurality of images.