Abstract: Content conversion verification, includes: converting, at a first computer system, an original content file to a target format, generating a converted content file in the target format; generating a checksum for the converted content file; and sending the original content file and the checksum to a second computer system. Key words include content verification and checksum.

Abstract: Improving the accuracy of predicted segmentation masks, including: extracting a ground-truth RGB image buffer and a binary contour image buffer from a ground-truth RGB image container for segmentation training; generating predicted segmentation masks from the ground-truth RGB image buffer; generating second binary contours from the predicted segmentation masks using a particular algorithm; computing a segmentation loss between manually-segmented masks of the ground-truth RGB image buffer and the predicted segmentation masks; computing a contour accuracy loss between contours of the binary contour image buffer and the binary contours of the predicted segmentation masks; computing a total loss as a weighted average of the segmentation loss and the contour accuracy loss; and generating improved binary contours by compensating the contours of the binary contour image buffer with the computed total loss, wherein the improved binary contours are used to improve the accuracy of the predicted segmentation masks.

Abstract: Enhancing color reproduction of an image in an upscaling process, the method comprising: converting RGB-formatted data into luminance channel formatted data and color channel formatted data; converting RGB-predicted data into luminance channel predicted data and a color channel predicted data; computing a first loss between the RGB-formatted data and the RGB-predicted data; computing a second loss between the color channel formatted data and the color channel predicted data; and outputting a weighted average value of the first loss and the second loss to enhance the color reproduction of the image.

Abstract: Methods and systems including: applying a gamma adjustment to frames of an input video with particular values of parameters to generate at least one set of gamma-adjusted frames to generate at least one set of gamma-adjusted frames; applying a segmentation technique to the at least one set of gamma-adjusted frames to generate segmentation masks; applying an optical flow technique to the at least one set of the gamma-adjusted frames to generate optical flow maps; and combining the segmentation masks and the optical flow maps to generate hybrid segmentation masks.

Abstract: An automatic door system is configured to allow a signal to unfailingly reach a smartphone or the like carried by a customer in various places. The automatic door system includes a BLE module configured such that, in a predetermined direction from a surface of a door, a signal that contains information based on which the BLE module can be identified transmitted from the BLE module reaches an area beyond a person sensing area covered by a sensor.

Abstract: Analyzing text data and social media. posts to acquire accurate measure of audience interest level including business target features, including: collecting the text data based on each business target feature; extracting information including metadata, actions and entities with associated connections from the text data; identifying intent based on the extracted information that includes related entities using an intent identifier; filtering and recognizing related input data based on intent criteria using the extracted information; and providing aggregated data about each business target feature as a feedback regarding the intent.

Abstract: Frame handling an input image in an ML-based upscaling process to produce an output image, including: detecting and extracting boxing edge regions from edges of an active picture area of the input image; extending the extracted boxing edge regions by adding extra pixels around each of the boxing edge regions to produce padded edge regions; upscaling the padded edge regions to produce upscaled padded edge regions; cropping each of the upscaled padded edge regions to a size corresponding to the size of each of the boxing edge regions prior to the upscaling multiplied by an upscaling factor; inserting the cropped edge regions into the edges of the output image; and upscaling a non-edge region of the input image and inserting the upscaled non-edge region into the output image.

Abstract: Enabling adjustment of sharpness and details of an input image in upscaling, including: applying a Fourier transform function on a brightness channel of the input image to generate a 2-D frequency map; adjusting the 2-D frequency map to control a target amount of sharpness and details in an upscaled output image; and using the adjusted 2-D frequency map as an additional input channel along with standard color image data for a training and upscaling process.

Abstract: Training and upscaling a large-sized input image, including: dividing the large-sized input image into a plurality of small-sized sub-pictures; expanding each sub-picture of the plurality of small-sized sub-pictures using target padding pixels to produce an expanded sub-picture; upscaling each sub-picture using an ML-based upscaler to produce an expanded upscaled sub-picture; cropping the expanded upscaled sub-picture to an upscaled size equal to an original size of each sub-picture multiplied by an upscaling factor; repeating expanding, upscaling, and cropping for the plurality of sub-pictures; and concatenating the plurality of cropped sub-pictures to produce an output image.

Abstract: Methods and systems including: applying a gamma adjustment to frames of an input video with particular values of parameters to generate at least one set of gamma-adjusted frames to generate at least one set of gamma-adjusted frames; applying a segmentation technique to the at least one set of gamma-adjusted frames to generate segmentation masks; applying an optical flow technique to the at least one set of the gamma-adjusted frames to generate optical flow maps; and combining the segmentation masks and the optical flow maps to generate hybrid segmentation masks.

Abstract: Improving the accuracy of predicted segmentation masks, including: extracting a ground-truth RGB image buffer and a binary contour image buffer from a ground-truth RGB image container for segmentation training; generating predicted segmentation masks from the ground-truth RGB image buffer; generating second binary contours from the predicted segmentation masks using a particular algorithm; computing a segmentation loss between manually-segmented masks of the ground-truth RGB image buffer and the predicted segmentation masks; computing a contour accuracy loss between contours of the binary contour image buffer and the binary contours of the predicted segmentation masks; computing a total loss as a weighted average of the segmentation loss and the contour accuracy loss; and generating improved binary contours by compensating the contours of the binary contour image buffer with the computed total loss, wherein the improved binary contours are used to improve the accuracy of the predicted segmentation masks.

Abstract: Enhancing color reproduction of an image in an upscaling process, the method comprising: converting RGB-formatted data into luminance channel formatted data and color channel formatted data; converting RGB-predicted data into luminance channel predicted data and a color channel predicted data; computing a first loss between the RGB-formatted data and the RGB-predicted data; computing a second loss between the color channel formatted data and the color channel predicted data; and outputting a weighted average value of the first loss and the second loss to enhance the color reproduction of the image.

Abstract: Content conversion verification, includes: converting, at a first computer system, an original content file to a target format, generating a converted content file in the target format; generating a checksum for the converted content file; and sending the original content file and the checksum to a second computer system. Key words include content verification and checksum.

Abstract: A method for enhancing color reproduction in an upscaling process, including: converting RGB-formatted data to color-space-separable-formatted data; sending the RGB-formatted data to a neural network for training to generate RGB-predicted data; converting the RGB-predicted data to color-space-separable-predicted data; computing a first loss function by calculating a first difference between the RGB-formatted data and the RGB-predicted data; extracting color-formatted data from the color-space-separable-formatted data; extracting color-predicted data from the color-space-separable-predicted data; computing a second loss function by calculating a second difference between the color-formatted data and the color-predicted data; and adjusting a balance between the first and second loss functions.

Abstract: Content individualization, including: encrypting a first part of a source data set using a first key creating a first encrypted data set; encrypting a second part of the source data set using a second key creating a second encrypted data set; encrypting the second part of the source data set using a third key creating a third encrypted data set; and combining the first encrypted data set, the second encrypted data set, and the third encrypted data set to form a final encrypted data set. Key words include watermarking and content individualization.

Abstract: An object is to allow a signal to unfailingly reach a smartphone or the like carried by a customer in various places. An automatic door system (10) includes a BLE module (16) configured such that, in a predetermined direction from a surface of a door, a signal (containing information based on which the BLE module (16) can be identified) transmitted from the BLE module (16) reaches an area beyond a person sensing area covered by a sensor.

Abstract: Frame handling an input image in an ML-based upscaling process to produce an output image, including: detecting and extracting boxing edge regions from edges of an active picture area of the input image; extending the extracted boxing edge regions by adding extra pixels around each of the boxing edge regions to produce padded edge regions; upscaling the padded edge regions to produce upscaled padded edge regions; cropping each of the upscaled padded edge regions to a size corresponding to the size of each of the boxing edge regions prior to the upscaling multiplied by an upscaling factor; inserting the cropped edge regions into the edges of the output image; and upscaling a non-edge region of the input image and inserting the upscaled non-edge region into the output image.

Abstract: Training and upscaling a large-sized input image, including: dividing the large-sized input image into a plurality of small-sized sub-pictures; expanding each sub-picture of the plurality of small-sized sub-pictures using target padding pixels to produce an expanded sub-picture; upscaling each sub-picture using an ML-based upscaler to produce an expanded upscaled sub-picture; cropping the expanded upscaled sub-picture to an upscaled size equal to an original size of each sub-picture multiplied by an upscaling factor; repeating expanding, upscaling, and cropping for the plurality of sub-pictures; and concatenating the plurality of cropped sub-pictures to produce an output image.

Abstract: Enabling adjustment of sharpness and details of an input image in upscaling, including: applying a Fourier transform function on a brightness channel of the input image to generate a 2-D frequency map; adjusting the 2-D frequency map to control a target amount of sharpness and details in an upscaled output image; and using the adjusted 2-D frequency map as an additional input channel along with standard color image data for a training and upscaling process.

Abstract: A method for enhancing color reproduction in an upscaling process, including: converting RGB-formatted data to color-space-separable-formatted data; sending the RGB-formatted data to a neural network for training to generate RGB-predicted data; converting the RGB-predicted data to color-space-separable-predicted data; computing a first loss function by calculating a first difference between the RGB-formatted data and the RGB-predicted data; extracting color-formatted data from the color-space-separable-formatted data; extracting color-predicted data from the color-space-separable-predicted data; computing a second loss function by calculating a second difference between the color-formatted data and the color-predicted data; and adjusting a balance between the first and second loss functions.