Abstract: One or more embodiments of the present disclosure provide an intelligent vase system, a flower recognition and presentation method for an intelligent vase system, and an electronic apparatus. The intelligent vase system includes: a vase body; a flower recognition device configured to: acquire a flower image of a flower inserted into the vase body, perform an object extraction on the flower image to obtain at least one object flower image, perform a flower recognition on the object flower image to obtain a flower recognition result, and acquire presentation information of an object flower based on the flower recognition result; and a display device, which is on the vase body, in communication with the flower recognition device, and configured to display the presentation information.

Abstract: An example computing device includes: a three-dimensional (3D) sensor configured to capture point cloud data from a field of view; an auxiliary sensor configured to capture a reference depth measurement corresponding to a surface within the field of view; a processor interconnected with the 3D sensor and the auxiliary sensor, the processor configured to: control the 3D sensor and the auxiliary sensor to capture the point cloud data and the reference depth measurement; select a region of the point could data including a position of the reference depth measurement; determine a representative depth value of the region of the point cloud data to compare to the reference depth measurement; determine whether the representative depth value is within a similarity threshold to the reference depth measurement; and determine, based on whether the representative depth value is within the similarity threshold to the reference depth measurement, whether to use the point cloud data for a dimensioning operation.

Abstract: Embodiments described herein provide methods and systems for facilitating actively-learned context modeling. In one embodiment, a subset of data is selected from a training dataset corresponding with an image to be compressed, the subset of data corresponding with a subset of data of pixels of the image. A context model is generated using the selected subset of data. The context model is generally in the form of a decision tree having a set of leaf nodes. Entropy values corresponding with each leaf node of the set of leaf nodes are determined. Each entropy value indicates an extent of diversity of context associated with the corresponding leaf node. Additional data from the training dataset is selected based on the entropy values corresponding with the leaf nodes. The updated subset of data is used to generate an updated context model for use in performing compression of the image.

Abstract: Various systems and methods for controlling surgical devices are disclosed. A computer system, such as a surgical hub, can be configured to be communicably coupled to a surgical device and a camera configured to view an operating room. The computer system can be programmed to receive images of surgical staff members and surgical devices within the operating room during a surgical procedure. The computer system can further determine conditions or characteristics associated with the surgical staff members and surgical devices, such as whether a surgical staff member is performing a particular gesture or the pose of a surgical device, such as a surgical instrument, during a surgical procedure. The computer system can then control the paired surgical devices accordingly.

Abstract: A method of encoding or decoding a point cloud for representing a three-dimensional location of an object, the point cloud being generated by a device comprising a plurality of beam emitters. The method comprises using information from the beam emitter such as the angle of each beam emitter, and the azimuthal distance between each point capture, to more efficiently represent the point cloud data.

Abstract: A smart cache implementation for image warping is provided by dividing an output image into a plurality of blocks corresponding to initial coordinates in the output image; dividing an input image into at least a first and second regions of pixels, where the first region overlaps the second region; generating an unsorted remap vector of the plurality of blocks for image warping the input image; identifying a first and second subsets of blocks from the plurality of blocks that can be reconstructed using the first and second regions respectively; generating a region-based sorting, a line-based sorting of the region-based sorting, a column-based sorting of the line-based sorting based on the initial x-coordinates of the blocks in the unsorted remap vector, and a sorted remap vector by sorting the column-based sorting based on initial y-coordinates of the blocks in the unsorted remap vector.

Abstract: Depth information is extracted from a stereoscopic image pait by an image processing system. For each pixel of a target image of the stereoscopic image pair, a final disparity cost vector is computed having cost components corresponding to different disparities. The final disparity cost vector is stored in association with that pixel. That pixel is assigned the disparity corresponding to the lowest cost component of the final disparity cost vector, wherein the extracted depth information comprises the disparities assigned to the pixels of the target image. For at least a subset of the pixels of the target image, the final disparity cost vector is computed for each of those pixels by computing, with respect to the reference image, a set of matching costs for that pixel and the different disparities, and combining the matching costs with the one or more final disparity cost vectors stored in association with one or more of the adjacent pixels of the target image.

Abstract: Systems, apparatuses, and methods for detecting and mitigating scaling artifacts caused by high chromatic colors in adjacent pixels are disclosed. A blend factor calculation circuit determines if high chromatic colors are in close proximity to each other in a set of pixel data of an image or frame. The blend factor calculation circuit generates a blend factor value to suppress artifacts which are introduced when filtering the set of pixel data when the set of pixel data has high chromatic colors in close proximity. In one scenario, the blend factor calculation circuit calculates pixel component difference values of adjacent pixels and uses a value calculated based on the difference values as an input to a transfer function. The output of the transfer function is a blend factor value which determines how filtering is blended between a plurality of filters.

Abstract: A system and method for correcting image data is disclosed. The method includes receiving one or more documents from one or more electronic mediums. The method further includes determining a primary character and one or more alternate characters corresponding to the mis-captured character image, extracting one or more confident instances of the primary character and the one or more alternate characters from the one or more documents and generating one or more scores corresponding to the primary character and the one or more alternate characters. Further, the method includes predicting a correct character corresponding to the mis-captured character image by using a trained image prediction-based ML model and automatically replacing the mis-captured character image with the predicted correct character.

Abstract: An inspection system is provided and includes a camera and controller. The controller can include one or more processors in communication with the camera and receive a plurality of images of a target captured by the camera. The controller can also determine, using a first computer vision algorithm, a first prediction and corresponding confidence level for substantially all of the images. The controller can select a subset of the images having the first prediction confidence level greater than or equal to a first prediction threshold value. The controller can additionally determine, using a second computer vision algorithm, a second prediction and corresponding second prediction confidence level for each of the selected images. The at least one second prediction can require more time to determine than the at least one first prediction. The controller can output the second prediction and the second prediction confidence level for each of the selected images.

Abstract: An industrial tomography apparatus comprising a tomography scan device configured to perform tomography scans of the products placed in the scanning zone and an electronic processing unit programmed to generate a virtual three-dimensional tomography model of a product scanned by the tomography scan device, and to perform a procedure for inspecting industrial products of known type, each comprising a packet or a container. During the inspection procedure the electronic processing unit inspects the virtual three-dimensional tomography model to assess internal features of the product and/or the shape of the product at predetermined zones and determines whether or not those internal features and/or respectively that shape, correspond to a product with intact packet or container. The apparatus implements a corresponding method for checking the integrity of packets or containers of industrial products which have known features.

Abstract: A system for automated surface anomaly detection includes at least one processor which is configured to retrieve from non-volatile memory a 3D control image; capture a 3D target image depicting at least the portion of the exterior of a target object; generate 2D target planar images of the target object based on the 3D target image, using a first plurality of virtual cameras; generate 2D control planar images of the control object based on the 3D control image using a second plurality of virtual cameras, the 2D control planar images corresponding to the 2D target planar images of the target object; detect at least one difference between the 2D target planar images and the 2D control planar images; and generate and cause to be displayed an output image comprising a depiction of the target object with the at least one difference indicated.

Abstract: An imaging system of the present disclosure includes: an event detection sensor that detects an event; an object recognition unit that performs recognition processing for an object detected as the event on the basis of an event signal output from the event detection sensor; a motion vector estimation unit that estimates a motion vector of the object on the basis of a recognition result by the object recognition unit; and a control unit that outputs warning information for warning that a dangerous state has occurred on the basis of an estimation result by the motion vector estimation unit.

Abstract: A method and system are provided. The method includes receiving an input frame, performing high frequency noise reduction (HFNR) on the received input frame, performing low frequency noise reduction (LFNR) on the received input frame, and obtaining a hybrid denoised clean frame by fusing an output of the performed HFNR and an output of the performed LFNR.

Abstract: The invention addresses the problem of improving labor of a registration operation of a product and enabling a checkout operator to recognize a recognition result. In order to solve the problem, the invention provides a registration apparatus (10) including: an image acquisition unit (11) that acquires an image obtained by imaging a placement surface of a table, on which a product is placed; an analysis unit (12) that recognizes the product included in the image, a registration unit (14) that registers the recognized product as a checkout target, and an output unit (13) that outputs a name of the recognized product by voice.

Abstract: A method for reconstructing a MRI image may include: receiving MRI measurement data sets f1 to fN, each data set being acquired from an examination object based on a different MRI protocol of an MRI system; receiving MRI images u10 to uN0 corresponding to the MRI measurement data sets f1 to fN; performing one or more translation and rotation transformations on the MRI images u10 to uN0; applying one or more trained functions: to the transformed MRI images u10 to uN0, using a neural network, and to the MRI images u10 to uN0, using a forward-sampling operator; performing one or more inverse translation and rotation transformations on an output of the neural network; and generating at least one output MRI image uT based on an output of the forward-sampling operator, the inversely transformed output of the neural network, and the input MRI images u10 to uN0.

Abstract: A method for accelerating hyperspectral video reconstruction includes steps of: acquiring, according to a spectral video and an RGB video captured by a hyperspectral video camera, a calibration matrix of the spectral video and the RGB video; sorting the calibration matrix to generate an ordered calibration matrix; converting, according to the ordered calibration matrix, the spectral video and the RGB video into a data matrix in a parallel manner; acquiring all related calibration points of a reconstruction region according to the ordered calibration matrix; and, reconstructing a hyperspectral video in a parallel manner according to the related calibration points and the data matrix. The related calibration points are acquired by sorting the calibration matrix, such that the number of times the calibration matrix is traverse is reduced, and the computation amount of hyperspectral video reconstruction is decreased.

Abstract: A system and method for generating a stained image including the steps of obtaining a first image of a key sample section; and processing the first image with a multi-modal stain learning engine arranged to generate at least one stained image, wherein the at least one stained image represents the key sample section stained with at least one stain.

Abstract: A method for determining authenticity of a video in a surveillance system, whereby a sequence of image frames of a scene is captured, and an object is tracked. A current image quality measure in an image area corresponding to the tracked object is determined in at least a first and second image frame. chosen such that the object has moved at least a predetermined distance between the first and second image frames. A current image quality measure variation for the object is determined, the image quality measure variation describing the image quality measure as a function of position of the object in the image frames. The current image quality measure variation is compared to a known image quality measure variation. In response to the current image quality measure variation deviating from the known pixel density variation by less than a predetermined amount, it is determined that the video is authentic.

Abstract: An image processing method, a device and a non-transitory computer-readable storage medium thereof are provided. The method includes that a first image of a target object, a second image of the target object, and a third image of the target object are acquired. Exposure of the first image is less than exposure of the second image. The exposure of the second image is less than exposure of the third image. Further, brightness of the first image is increased to acquire a fourth image. Moreover, ghost elimination is performed on the second image and the fourth image is taken as a first reference frame to acquire a second reference frame. Furthermore, ghost elimination is performed on the third image based on the second reference frame to acquire a fifth image.