Abstract: An image encryption method. The method includes generating an adjusted secret image by adjusting an intensity range to be the same for each RGB channel of a secret image; generating a modulated image by repeating pixel modulation in block units on the adjusted secret image; and generating an interlaced image by interlacing odd-numbered lines of the adjusted secret image with even-numbered lines of the modulated image or interlacing even-numbered lines of the adjusted secret image with odd-numbered lines with the modulated image.

Abstract: A method includes steps of: based on training sets of gastrointestinal images, using a predetermined machine learning algorithm to obtain a preliminary model; feeding preliminary validation sets of gastrointestinal images into the preliminary model to obtain estimation results; based on the estimation results, selecting, from the preliminary validation sets of gastrointestinal images, a series of successive images as a selected validation set of gastrointestinal images; based on the selected validation set of gastrointestinal images, tuning parameters of the preliminary model to result in a speed-determining model for determining a moving speed of an endoscope camera.

Abstract: A secure image for a security document is generated by performing a rasterization process for each of a plurality of mono-color base images using a plurality of different threshold functions. For each base image, the plurality of threshold functions cover different intensity regions and result in a complex rasterization pattern depending on the intensity of the input image. The resulting binary images obtained by the rasterization process are combined using offset printing with fluorescent inks of different colors, to result in a multi-color fluorescent output image including a plurality of different complex rasterization patterns.

Abstract: Systems and methods for providing colorblind-accessible versions of a color image by generating a color translation table for color vision deficiency (CVD) corrections are disclosed. For a given image, the pixel values as would be seen by a colorblind user are determined. Using these values, a corrected rendered image that appears to colorblind users as depicting a similar color scheme as the original image is produced and presented to the colorblind user. The proposed systems can be implemented with previously captured image data, real-time video, and as an add-on to other applications.

Abstract: The present disclosure relates to signal encoding and decoding, such as digital watermarking. One aspect of the technology relates a method of evaluating print quality of a test digital watermarking patch.

Abstract: Disclosed is a method for analyzing a thickness of a cortical region, performed by a computing device. The method may include: extracting a plurality of interfaces included in a cortical region based on a mask generated from a medical image including at least one brain region; and estimating a thickness of the cortical region based on the plurality of interfaces.

Abstract: A detection sensitivity is set such that a detection sensitivity for a defect corresponding to a predetermined local pattern in a reference image, which is a reference printing result, is lower than for a region other than the predetermined local pattern in the reference image. Image data representing an image of an inspection target is acquired and the image of the inspection target is inspected based on the reference image and the set detection sensitivity.

Abstract: Various embodiments of the present technology generally relate to robotic devices, computer-vision systems, and artificial intelligence. More specifically, some embodiments relate to a computer-vision system for robotic devices. In some implementations, a computer-vision is coupled to a robotic arm for picking items from a bin and perturbing items in a bin. A computer-vision system, in accordance with the present technology, may use at least two two-dimensional (2D) images to generate three-dimensional (3D) information about the bin and items in the bin. A method of training artificial neural networks to generate 3D information from 2D images includes obtaining ground truth data for a scene, obtaining at least two images of the scene, and providing the ground truth data and the at least two images to the artificial neural network configured to generate a depth map from the images based on the ground truth data.

Abstract: Systems and methods electronically uniquely imprint a digital watermark on produced resources, such as on data or electronic documents produced by an online software platform (OSP), in nearly invisible ways that are likely to survive subsequent processing. In one embodiment the OSP stores a plurality of resource digital rules used for producing resources for respective relationship instances of primary entities with other entities; receives a dataset on behalf of a primary entity, in which the dataset includes data representing a relationship instance between the primary entity and a secondary entity; in response to the received dataset, produces a resource based on applying one or more of the plurality of resource digital rules to the dataset; and digitally watermarks the produced resource with a digital watermark such that the produced resource is identifiable via the digital watermark as having been produced by the OSP.

Abstract: Systems and methods electronically uniquely imprint a digital watermark on produced resources, such as on data or electronic documents produced by an online software platform (OSP), in nearly invisible ways that are likely to survive subsequent processing. In one embodiment the OSP stores a plurality of resource digital rules used for producing resources for respective relationship instances of primary entities with other entities; receives a dataset on behalf of a primary entity, in which the dataset includes data representing a relationship instance between the primary entity and a secondary entity; in response to the received dataset, produces a resource based on applying one or more of the plurality of resource digital rules to the dataset; and digitally watermarks the produced resource with a digital watermark such that the produced resource is identifiable via the digital watermark as having been produced by the OSP.

Abstract: A pose calibration method, a robot, and a computer readable storage medium are provided. The method includes: obtaining, through a depth camera on a robot, a depth image including a target plane (i.e., a plane where the robot is located); determining point cloud data corresponding to the depth image; and calibrating a target pose of the depth camera based on the point cloud data and a preset optimization method, that is, calibrating a pitch angle and a roll angle of the depth camera and a height of the depth camera in a coordinate system of the robot. In this manner, the accuracy of the calibration of the target pose can be effectively improved while simple in implementation and small in calculation amount, and the efficiency of the calibration of the target pose can be improved so as to improve the user experience.

Abstract: Methods and systems for associating labels between multiple sensors. One of the methods includes generating user interface presentation data that, when presented on a user device, causes the user device to display a user interface that: displays the images in the sequence of images and data identifying the first and second object tracks, and is configured to receive user inputs that associate first object tracks with second object tracks; and providing the user interface presentation data for presentation on the user device.

Abstract: This application relates to a system for compressing captured images. The system may include an image capturing device configured to continuously capture images, for example, of a location, or frame, or field of view, and convert the captured images respectively into a plurality of sets of digital data, each of the plurality of sets of digital data including at least two consecutive rows of digital data. The system may also include a processor circuit configured to combine the at least two sets of the plurality of sets of digital data to generate a pre-compression set of digital data and simultaneously compress the pre-compression set of digital data simultaneously or together in a single compression operation.

Abstract: The present disclosure provides systems and methods for improved image watermarking to improve robustness and capacity, without degrading perceptibility. Specifically, the systems and methods discussed herein allow for a higher decoding success rate, at the same distortion level and message rate; or a higher message rate, at the same distortion level and decoding success rate. Implementations of these systems utilize a side chain of additional information, available only to the decoder and not the encoder, to achieve asymptotically lossless data compression, allowing the same message to be transmitted in fewer bits.

Abstract: A vision analytics and validation (VAV) system for providing an improved inspection of robotic assembly, the VAV system comprising a trained neural network three-way classifier, to classify each component as good, bad, or do not know, and an operator station configured to enable an operator to review an output of the trained neural network, and to determine whether a board including one or more “bad” or a “do not know” classified components passes review and is classified as good, or fails review and is classified as bad. In one embodiment, a retraining trigger to utilize the output of the operator station to train the trained neural network, based on the determination received from the operator station.

Abstract: A control apparatus includes a controller. The controller obtains a job which is executed by a print apparatus and which is corresponded to document image data. The controller obtains read image data of a color sample corresponding to the document image data from a scanner. The controller determines whether correction of the scanner and/or the print apparatus is necessary based on the read image data. The controller corrects the scanner and/or the print apparatus based on a result of determination. The controller generates a color conversion parameter regarding a color conversion of the document image data based on a profile corresponding to the scanner and/or the print apparatus after correction, the document image data, and the read image data.

Abstract: An image inspection device includes a hardware processor executing an inspection for a first read image generated by reading a first sheet on which one image is formed, based on a reference image. When an operation for newly generating the reference image is performed in association with the inspection for the first read image, the hardware processor acquires second read images generated by respectively reading second sheets on each of which the one image is formed and generates the reference image using the inspection for the first read image. When an operation for using the generated reference image stored in a storage unit is performed in association with the inspection for the first read image, the hardware processor uses the reference image in the storage unit for the inspection for the first read image, without newly acquiring the second read images.

Abstract: There is provided with an image processing apparatus. An obtaining unit obtains a first image serving as a read image of an inspection target medium having undergone printing, and a second image serving as a read image of a reference medium representing a target print result. An inspection unit inspects a defect on the inspection target medium based on the first image and the second image by performing inspection at inspection settings different between a print region and a peripheral region of the inspection target medium.

Abstract: A watermarking method for a high-definition map based on invisible characters includes: firstly, establishing mapping relations between invisible characters and bit characters, a space character, and decimal digits; and combining watermark characters with corresponding positions thereof, adding Hamming code into a watermark character sequence, and converting the watermark character sequence into invisible characters to construct a composite watermark character sequence. Before watermark detection, a sequence of elements in map data is scrambled according to logistic chaotic mapping, and then the composite watermark character sequence is embedded according to the scrambled sequence. During watermark detection, the data are preprocessed, a sequence during watermark embedding is obtained, and then watermark information is extracted, errors are corrected, and an error correcting code is removed after correction to obtain final watermark information.

Abstract: Provided is a method for inserting a copyright information indication as a means for protecting the copyright of LF content which can be played back as multi-viewpoint images, wherein the copyright information indication is only inserted in images of a specific viewpoint. A method for generating multi-viewpoint images according to an embodiment of the present invention includes the steps of: generating multi-viewpoint images; inserting a specific information indication in images of a specific viewpoint among the generated multi-viewpoint images; and storing the multi-viewpoint images in which the specific information indication has been inserted. Accordingly, the copyright of LF content, which are expensive multi-viewpoint images, can be protected by inserting the copyright information indication only in the images of the specific viewpoint.