Abstract: A watermark embedding method includes the following steps. The input video signal is received by a processing circuit. Grayscale information of a watermark signal is generated by the processing circuit according to a time series data and a predetermined plane. During a dark sate and a bright state in each of a plurality of consecutive periods, phases of the time series data are opposite and integral values of the grayscales of the predetermined plane are the same. The processing circuit embeds the watermark signal into the input video signal to generate an output video signal with the watermark information. The display panel displays an image according to the output video signal.

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: The present disclosure relates generally to signal encoding for elements within PDF files. One implementation encodes an artwork element under different encoding conditions, and selects a winner version based on resulting signal robustness and/or visibility. Other implementations generate PDF layer masks to help determine overall embedding robustness, including interference from layered elements. Other implementations are provided too.

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: This document discloses a method, system, and/or software configured to provide improved color rendering of an item or scene, such as an item for sale through websites or printed brochures (e.g., color catalogs). This improved color rendering can be provided through improved accuracy when rendering an online item, such as on a user's laptop, smartphone, or desktop computer showing a webpage. Further still, this document discloses ways in which to solve numerous problems in the field of online sales where an accurate rendering of an item, and even a customized rendering of an item to fit a buyer's intended use for the item, is desired. This document also describes ways in which to improve color renderings for a print item through use of a user's device to capture an image using the device's camera, and then display the item more accurately or congruently than it was originally displayed in print.

Abstract: The present disclosure relates generally to signal encoding for elements within PDF files. One implementation smooths saw-toothed edges of rasterized elements meant for encoding. Other implementations are provided too.

Abstract: An information processing apparatus includes a processor configured to: receive an electronic document generated while maintaining text information by an application program or an electronic document generated by reading an image with a document reading apparatus; perform type determination as to whether the received electronic document including a portion representing a text is generated by the application program or generated by the document reading apparatus; and determine based on a result of the type determination whether an optical character recognition process is to be performed on the electronic document.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting and decoding a visually imperceptible or perceptible watermark. A watermark detection apparatus determines whether the particular image includes a visually imperceptible or perceptible watermark using detector a machine learning model. If the watermark detection apparatus detects a watermark, the particular image is routed to a watermark decoder. If the watermark detection apparatus cannot detect a watermark in the particular image, the particular image is filtered from further processing. The watermark decoder decodes the visually imperceptible or perceptible watermark detected in the particular image. After decoding, an item depicted in the particular image is validated based data extracted from the decoded visually imperceptible or perceptible watermark.

Abstract: A gloss value of a clear topcoat (e.g., flood of varnish) on a substrate relative to a bare substrate is an indicator of digital watermark robustness for an encoded signal carried by modulating the clear topcoat. This measurement can be used to predict encoded signal robustness prior to printing. One claim is directed to an image processing method comprising: obtaining a first gloss value corresponding to a layer comprising a matte or gloss topcoat flooded over a substrate; obtaining a second gloss value corresponding to the substrate; and determining a relationship between the first gloss value and the second gloss value to determine digital watermark signal robustness of a sparse mark pattern provided on the substrate with the matte or gloss topcoat. Of course, other claims are combinations are described as well.

Abstract: Systems and methods for using machine learning to assess text legibility in an electronic document are disclosed. According to certain aspects, an electronic device may train a machine learning model using training data that includes at least a representation of a text legibility level in the training data. Additionally, the electronic device may input the electronic document into the machine learning model, which may analyze the electronic document and output a representation of the text legibility level of a set of textual content included in the electronic document. The electronic device may display the output for review and assessment by a user, who may use the electronic device to facilitate any modifications to the electronic document.

Abstract: Provided is an object recognition device including a temporary setting unit and an update processing unit. The temporary setting unit sets, based on specifications of an external information sensor that has detected an object, a position of at least one candidate point on the object. The update processing unit corrects a position of a detection point with respect to the external information sensor at a time when the external information sensor has detected the object based on the position of the candidate point on the object, and updates track data indicating a track of the object based on a position of the detection point with respect to the external information sensor after the correction.

Abstract: A computer-aided method, using a pre-operative planning software tool and patient-specific images, establishes implant parameters that customize selection of a total knee replacement prosthesis. The computer system determines from coronal, axial and sagittal image slices of a knee joint a neutral boundary axis, a set of epicondylar and trochlear features that define an elliptical cam, and a medial-lateral tibial slope, then defines from overlapping condylar and trochlear circles an ellipse with eccentricity 0.25 and focal points coincident with the circles. A knee prosthesis has a femoral component as an elliptical cam with dimensions defined by the ellipse, and has tibial and patellar components interacting with the femoral component as cam followers under knee flexion. A prosthesis is selected from a set with differing coronal asymmetry angle ? to closely match the patient a as estimated from the images.

Abstract: A method and apparatus for identifying back acupuncture points, and a moxibustion robot are provided, which belong to the technical field of identification of acupuncture points. The method includes: acquiring skeleton key feature points of a human body image, and identifying a plurality of back meridians on a back based on the skeleton key feature points; identifying a plurality of thoracic vertebra positions and a plurality of lumbar vertebra positions of the human body image based on the skeleton key feature points; and identifying back acupuncture points based on the plurality of thoracic vertebra positions, the plurality of lumbar vertebra positions, and the back meridians. Manual marking is not required, and the thoracic vertebra positions and the lumbar vertebra positions are used as references for the back acupuncture points. The accuracies of the identified back acupuncture points are improved.

Abstract: A package measuring apparatus includes a control unit and a depth sensor that picks up a package having a rectangular parallelepiped shape placed on a mounting table from substantially directly above the package. The control unit is configured to: specify data of the package in an acquired depth image data by comparing with background depth image data; calculate a height of the package and specify positions of three vertices located on a leftmost, rightmost, and uppermost or lowermost side in the depth image data; obtain two-dimensional coordinates of the three vertices based on a view angle of the depth sensor, data of a distance from the depth sensor corresponding to the three vertices, data of a position of each sensor element, and the number of sensor elements; and calculate a length of two sides defined between a third vertex and other two vertices based on the two-dimensional coordinates.

Abstract: Disclosed is a strain calculation method and system for phase-sensitive optical coherence elastography (PhS-OCE), including the following steps: obtaining interference spectra for various states during sample deformation, and extracting spectral information including multiple amplitude maps and multiple phase maps from these interference spectra. In the present disclosure, the speckle decorrelation phenomenon in PhS-OCE can be eliminated, the measurement range is expanded, and tangential displacement fields and strain fields can be measured by PhS-OCE technique while ensuring high axial sensitivity in strain measurement.

Abstract: A biological sample image collection device (100), comprising support (30) and an optical imaging assembly (50), also comprises: a plurality of movable platforms (40) for placing biological samples (20), wherein the plurality of movable platforms (40) are arranged on the support (30) in an array; the plurality of movable platforms (40) can move relative to the support (30); and forces acting on the support (30) during the movement of the movable platforms can cancel each other out, so as to avoid vibrations affecting the support (30) and the biological samples (20) are canceled. The optical imaging assembly (50) collects images of the biological samples (20) on the movable platforms (40) when the plurality of movable platforms (40) move, relative to the center of the array, in the same direction and at the same speed. Further provided is a gene sequencer including the biological sample image collection device (100).

Abstract: The present disclosure relates generally to signal encoding for printed objects such as product packaging, labels and hangtags. One implementation obtains a color image representing CMY color channels, and alters the color image to include an encoded signal by altering values representing CIELAB a* and b*, all the while keeping L* on or within a predetermined tolerance of a contour representing a constant value. Other implementations are provided.

Abstract: Systems and methods are provided for decoding watermarks in video frames. A media device may receive a video frame that includes a first predetermined region comprising a watermark and a second predetermined region having pixel values selected to reduce the perceptibility of the first predetermined region. The media device may detect the watermark in the first predetermined region of the video frame and identify one or more contiguous subsets of pixels that correspond to a first pixel value and one or more contiguous subsets of pixels that correspond to a second pixel value. The media device then assigns a first symbol to the one or more contiguous subsets of pixels that correspond to the first pixel value and second symbol the one or more contiguous subsets of pixels that correspond to the second pixel value. The media device then generates a first sequence of symbols from the assigned symbols.

Abstract: By an image forming apparatus comprising a reading unit configured to read a sheet on which a chart image is printed, the chart image including a first print pattern using a first color ink and a second print pattern using a second color ink whose color is different from the first color, containing at least part of the first print pattern, and having a predetermined density and a detection unit configured to detect deformation of the sheet in an area of the sheet based on a difference between a moisture amount in a portion corresponding to an area in which the chart image in the read image obtained by the reading unit is printed and a moisture amount in a portion corresponding to a non-printing area, determination of cockling is performed with a high accuracy.

Abstract: A method includes, by a computing system, receiving a querying image depicting a sampling area, processing the querying image using a single cluster detection model to identify one or more regions of the querying image depicting a cluster in the sampling area, processing the one or more regions using a cluster verification deep-learning model to determine whether each depicted cluster is a cell cluster, and determining that exactly one of the identified one or more regions depicts a cluster that is a cell cluster. The method further includes processing the region depicting the cell cluster using a morphology deep-learning model to determine that there is only one cell in the cell cluster and to determine that die morphology of the cell is acceptable.