Abstract: In some examples, an imaging device can include a processing resource and a memory resource storing instructions to cause the processing resource to perform a feature extraction process to extract a gamut-based feature included in a plurality of pixels of a scanned image to determine whether the scanned image includes a particular marking, apply a classification model to the scanned image, and optimize the scanned image based on the classification of the scanned image.

Abstract: A first machine learning model is applied to an image of a person and a stationary object to generate a first intermediate image including a simplified pose representation of the person in the image corresponding to a pose of the person. A simplified representation of the stationary object in the image is added to the first intermediate image. The simplified representation includes key points of the stationary object in the image. A second machine learning model is applied to a second intermediate image corresponding to the first intermediate image to determine a state of the person relative to the stationary object in the image as either a first state or a second state.

Abstract: In some examples, a computing device can include a processor resource and a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to: identify a plurality of regions within a captured document, determine a quantity of vertical transitions and horizontal transitions within the plurality of regions, and select an output resolution for the plurality of regions based on the quantity of vertical transitions and horizontal transitions within the plurality of regions.

Abstract: In some examples, an imaging device can include a processing resource and a memory resource storing instructions to cause the processing resource to perform a feature extraction process to extract a gamut-based feature included in a plurality of pixels of a scanned image to determine whether the scanned image includes a particular marking, apply a classification model to the scanned image, and optimize the scanned image based on the classification of the scanned image.

Abstract: A saliency map of an image is generated. Saliency regions of the saliency map are identified. The saliency regions are merged into a combined saliency region. Candidate image crops of the image are generated based on the combined saliency region. An image crop of the image is selected from the candidate image crops using a machine learning model.

Abstract: An example system includes a landmark engine to detect a facial landmark in an image of a face. The system includes a comparison engine to determine a difference between the facial landmark in the image and a facial landmark of a neutral face. The system also includes an action engine to determine whether a facial action unit occurred based on whether the difference satisfies a condition.

Abstract: In some examples, an electronic device comprises an interface to receive a video of a human face, a memory storing executable code, and a processor coupled to the interface and to the memory. As a result of executing the executable code, the processor is to receive the video from the interface, use a facial detection technique to produce a sequence of images of the human face based on the video, use a neural network to predict a photoplethysmographic (PPG) signal based on the sequence of images, convert the PPG signal to a frequency domain signal, and determine a heart rate by performing a frequency analysis on the frequency domain signal.

Abstract: In some examples, a non-transitory computer-readable medium stores executable code, which, when executed by a processor, causes the processor to receive a video of at least part of a human torso, use a neural network to produce multiple vector fields based on the video, the multiple vector fields representing movement of the human torso, and determine a respiration rate of the human torso using the multiple vector fields.

Abstract: Examples disclosed herein relate to identifying a plurality of content areas of a document to be scanned, classifying each of the plurality of content areas into a content type, determining a minimum scanning resolution to maintain readability for each of the plurality of content areas according to the classified content type, and performing a scan of the document to a digital file, wherein each of the plurality of content areas is scanned at least at the determined minimum scanning resolution to maintain readability of the respective content area.

Abstract: A system generates a prediction model for makeup color matching. The system includes a data storage device and a modeling engine. The data storage device stores a plurality of color sets comprising a skin color set, a makeup color set, and a target color set. The modeling engine is coupled to the data storage device and configured to generate a prediction model and an output color set. The prediction model models generation of the target color set based on inputs from the skin color set and the makeup color set. The output color set approximates the target color set with a predictable accuracy.

Abstract: An example system includes a feature extraction engine to identify features in a compressed image at a plurality of scales. The features include features corresponding to compression artifacts and features corresponding to image content to be upsampled. The feature extraction engine is to identify the features in the compressed image at a first scale based on noncontiguous pixels. The system also includes a reconstruction engine to refine the features corresponding to the image content to be upsampled and mitigate the features corresponding to the compression artifacts. The system includes an upsampling engine to generate an upsampled version of the compressed image based on the refined and mitigated features.

Abstract: A method is disclosed. In the method, color differences are calculated between a current video frame and a motion predicted version of the current video frame based on a human visual system's ability to perceive the color differences. Also, information in a difference frame is discarded based on the color differences. The difference frame includes differences between the current video frame and the motion predicted version of the current video frame.

Abstract: A system generates a prediction model for makeup color matching. The system includes a data storage device and a modeling engine. The data storage device stores a plurality of color sets comprising a skin color set, a makeup color set, and a target color set. The modeling engine is coupled to the data storage device and configured to generate a prediction model and an output color set. The prediction model models generation of the target color set based on inputs from the skin color set and the makeup color set. The output color set approximates the target color set with a predictable accuracy.

Abstract: Example implementations relate to audio samples to detect device anomalies. For example, computing device, comprising: a processing resource and a non-transitory computer readable medium storing instructions executable by the processing resource to: generate a matrix of audio information for a plurality of audio samples of a device, select audio information from one of the plurality of audio samples, generate a plurality of principal components for the selected audio information utilizing a principal component expansion, select a principal component from the plurality of principal components based on a quantity of variance, and detect an anomaly of the device based on a comparison between a real time audio sample of the device and the selected principal component.

Abstract: In some examples, a device includes a printing device to generate an image on a substrate from a digital image, and a processor to: receive a scanned image of the image on the substrate, identify a plurality of image portions of the scanned image, identify horizontal color changes across a horizontal portion of the plurality of image portions, identify vertical color changes across a vertical portion of the plurality of image portions, compare the horizontal color changes and vertical color changes to corresponding horizontal color changes and corresponding vertical color changes of the digital image, and measure a presence of color plane misregistration, and the color, direction and magnitude of misregistration based on the comparison.

Abstract: Examples disclosed herein relate to identifying a plurality of content areas of a document to be scanned, classifying each of the plurality of content areas into a content type, determining a minimum scanning resolution to maintain readability for each of the plurality of content areas according to the classified content type, and performing a scan of the document to a digital file, wherein each of the plurality of content areas is scanned at least at the determined minimum scanning resolution to maintain readability of the respective content area.

Abstract: For each of a number of regions of interest (ROI) types, ROIs are extracted from a reference image based on an object map distinguishing symbol, raster, and vector objects within the reference image. Whether print quality of a printing device has degraded below a specified acceptable print quality level is assessed based on a comparison of the extracted ROIs within the reference image to corresponding ROIs within a test image corresponding to the reference image and printed by the printing device.

Abstract: For each region of interest (ROI) type of a number of ROI types, ROIs of the ROI type within a reference image are compared to corresponding ROIs within a test image corresponding to the reference image and printed by a printing device. For each ROI type, a feature vector characterizing image quality defects within the test image for the ROI type is generated based on results of the comparing for the ROI type. Whether print quality of the printing device has degraded below a specified acceptable print quality level can be assessed based on the feature vectors for the ROI types.

Abstract: In an example method, an image of a printed document is descreened. The descreened image is separated into blocks. A smooth area of the descreened image is selected based on an averaging of localized color distance values of pixels in each of the blocks. A streak in a block of the smooth area is detected in response to detecting that a magnitude of a color distance projection of the block exceeds a threshold value.

Abstract: Examples of methods are described herein. In some examples, a method includes calculating a first cost function measure based on band defects in an image. In some examples, the method also includes calculating a second cost function measure based on the band defects and a synthetic band. In some examples, the method further includes detecting a missing band based on a comparison of the first cost function measure and the second cost function measure.