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.

Abstract: The system is disclosed for visual marking sensitive documents for leak prevention. Each time an action is taken with regard to a document (e.g., creation, viewing, downloading), that action is added to a distributed ledger, essentially creating a unique hash for a new instance of the document. This new hash is visually embedded in the document as a code comprising a plurality of differently shaded pixels, wherein some of the pixels directly encode information regarding the document (e.g., an account that generated the new instance of the document, a date, a time, a unique ID for the document, etc.) and some of the pixels do not encode information. The code is capable of being scanned either digitally or physically on a printed version of the document, such that the immediate source of the document, corresponding to who leaked the document, is able to be discerned.

Abstract: A non-transitory computer readable medium storing a program causing a computer, which reproduces a color tone of a printed matter and displays the color tone on a screen before printing, to realize a function of generating an image in which the color tone of the printed matter is reproduced based on a first component reflected by a metallic color material and a second component transmitted through the color material and reflected by paper.

Abstract: A machine learning based image processing architecture and associated applications are disclosed herein. In some embodiments, a machine learning framework is trained to learn low level image attributes such as object/scene types, geometries, placements, materials and textures, camera characteristics, lighting characteristics, contrast, noise statistics, etc. Thereafter, the machine learning framework may be employed to detect such attributes in other images and process the images at the attribute level.

Abstract: An information processing apparatus includes a first acquisition unit to acquire input image data, a second acquisition unit to acquire display luminance information including maximum and minimum luminance values in displaying on a display device and print luminance information including maximum and minimum luminance values to be reproduced on printed matter outputted by a printing apparatus, and a conversion unit, to cause the printing apparatus to perform the output based on the input image data for which display is performed on the display device, to convert a first luminance range of the input image data to a second luminance range that is less than the first and, then, to generate output image data having the second luminance range. The minimum luminance value of the display luminance information is greater than the minimum luminance value of the print luminance information.

Abstract: Methods, systems, and computer programs encoded on a computer storage medium, that relate to extracting digital watermarks from images, irrespective of distortions introduced into these images. Methods can include inputting a first data item into a channel encoder that can generate a first encoded data item that is greater in length than the first data item and that (1) includes the input data item and (2) new data this is redundant of the input data item. Based on the first encoded data item and a first image, an encoder model can generate a first encoded image into which the first encoded data is embedded as a digital watermark. A decoder model can decode the first encoded data item to generate a second data, which can be decoded by the channel decoder to generate data that is predicted to be the first data.

Abstract: A security apparatus, method and system for rendering a security mark, can involve providing a security mark with a metameric pair of infrared inks. A spectral reflectance of two metameric inks among the metameric pair of inks differs for CMYK for K in infrared. A first metameric ink among the metameric pair of infrared inks can be configured to include more K than a second metameric ink among the metameric pair of infrared inks, wherein when a document containing the security mark is scanned, and the number of K pixels in the first metameric ink is filtered to destroy the security mark when viewed through an infrared camera.

Abstract: Embodiments relate to a non-fungible physical (NFP) item. The non-fungible physical (NFP) item comprises an identifier. The identifier is embedded and layered within the non-fungible physical item in an unplanned pattern. The identifier in the unplanned pattern is configured to provide high security against counterfeiting of the non-fungible physical (NFP) item. The identifier comprises at least one of a random marker and a unique marker. The unplanned pattern comprises at least one of a random pattern and a unique pattern. Further the non-fungible physical (NFP) item is registered as a non-fungible token on a blockchain. The NFP item is then paired with the non-fungible token for enabling two-way mutual authentication and enhanced authenticity. The pairing of the NFP item with the non-fungible token enables tracking condition, provenance, and grading of the NFP item.

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to determine a pairwise region of interest feature similarity based on features extracted from a first cropped image portion and corresponding point cloud data and features extracted from a second cropped image portion and corresponding point cloud data. The processor is also programmed to determine a loss using a loss function based on the pairwise region of interest feature similarity, wherein the loss function corresponds to at least one a first deep neural network or a second deep neural network. The processor is also programmed to update at least one weight of the at least one of the first deep neural network or the second deep neural network based on the loss.

Abstract: According to the present invention there is provide a method of creating a landmark map comprising the steps of: capturing a plurality of frame using a camera, each frame comprising an image; assigning an image number which denotes the order in which each frame was taken; extracting features from all the images in the captured frames; assigning a distinct identifier to each respective feature which was extracted from the image belonging to the frame which was first captured; for each image belonging to the respective frames which was captured after the first frame was captured, carrying out the following steps: (i) computing a distance between, the location of each respective extracted feature in that image, and the location of each respective feature extracted from image belonging to a previously captured frame; and (ii) determining if said computed distance is less than, a predefined threshold distance; and if the computed distance is not less than said predefined threshold distance then assign that extract

Abstract: In the field of determining the three-dimensional profile of a surface, a system and a method for determining such a three-dimensional profile use a plenoptic camera and a structured lighting system. The method includes: acquiring a sequence of plenoptic images, each formed by a set of pixels each associated with a light intensity of an imaged surface element, and including a plurality of sub-images of the surface from different viewing angles, projecting onto the surface a sequence of structured images synchronised with the sequence of plenoptic images illuminating each imaged surface element by a succession of light intensities different from the successions of light intensities which illuminate the other imaged surface elements, constructing, for each pixel of the plenoptic image, an intensity vector representing the succession of light intensities, and pairing each pixel of a sub-image with a pixel of another sub-image depending on a similarity of the intensity vectors.

Abstract: A process for converting an arbitrary input digital pathology image into an output digital pathology image that shares statistical information with a reference image. The input digital pathology image is separated into two or more image sections. Each image section is encoded, using a first convolutional neural network, into one or more feature maps. The one or more feature maps of each image section are modified based on statistical information derived from a reference image. The modified feature map(s) of each image section is/are then decoded to construct a respective image section for an output image. The constructed image sections for an output image then form the output image.