Systems, methods, and other embodiments for selecting, enriching and sequencing digital media content to produce a narrative-oriented, ordered sub-collection of media such as for movie creation. The method identifies, evaluates, assesses, stores, enriches, groups, and sequences content. The method identifies the content metadata. When metadata are missing or anomalous, the method attempts to populate or correct the metadata and store that new content in the database. The method evaluates content for focus quality and may exclude content based on rules. The method assesses the content storing the people and their emotional level, animals, objects, locations, landmarks and date/time in the database. The method can then enrich the remaining content by providing map, photo, video, text, and audio content. The method uses selecting criteria for grouping and sequencing content by date, time, person, etc. and compiling the sequenced groups into the final narrative ready for distribution, e.g., movie creation.

In one aspect, there is provided a method performed by one or more data processing apparatus, the method including receiving a training dataset having multiple training examples, where each training example includes: (i) an image, and (ii) a segmentation defining a target region of the image that has been classified as including pixels in a target category. The method further includes determining a respective refined segmentation for each training example, including, for each training example, processing the target region of the image defined by the segmentation for the training example using a de-noising neural network to generate a network output that defines the refined segmentation for the training example. The method further includes training a segmentation machine learning model on the training examples of the training dataset, including, for each training example training the segmentation machine learning model to process the image included in the training example to generate a model output that matches the refined segmentation for the training example.

A method of hybrid lane modeling, including, receiving a roadway image, extracting a set of lane points from the roadway image, fitting a polynomial line to the set of lane points, determining a fitted error of the fitted polynomial line, outputting the polynomial line if the fitted error is less than a predetermined threshold, selecting a set of clean lane points from the set of lane points if the fitted error is greater than the predetermined threshold and interpolating a cubic spline line to the set of clean lane points.

A determination system includes an imaging data acquisition device that captures an image of a printed surface of a printed product to acquire imaging data of the captured image, and a determination device that determines a printing method used to produce the printed surface of the printed product for capturing an image by the imaging data acquisition device. The determination device selects a determination area included in the captured image, extracts a determination end image from a portion around an end portion of a black determination image included in the determination area, acquires difference data that is a difference in gradation between two colors among gradation data of RBG colors of the extracted determination end image, acquires a determination value for determining a printing method used to produce the printed surface of the printed product, and determines a printing method used to produce the printed surface of the printed product.

An image processing method and device, and a computer-readable storage medium are disclosed. The method includes: performing a channel expansion process on the input image to obtain a first intermediate image; performing a channel decomposition process for multiple times based on the first intermediate image, wherein each time of channel decomposition process includes: decomposing an image to be processed into a first decomposition image and a second decomposition image; concatenating first decomposition images generated in each time of channel decomposition process and second decomposition image generated in the last time of channel decomposition process to obtain a concatenated image; performing a post-processing process on the concatenated image to obtain a second intermediate image; and fusing the second intermediate image with the input image to obtain the first output image.

One embodiment of the present invention sets forth a technique for generating data. The technique includes sampling from a first distribution associated with the score-based generative model to generate a first set of values. The technique also includes performing one or more denoising operations via the score-based generative model to convert the first set of values into a first set of latent variable values associated with a latent space. The technique further includes converting the first set of latent variable values into a generative output.

In a target image generated by multi-resolution processing, a pixel of interest and a group of reference pixels are designated. In a corresponding image belonging to a level that is one level above, pixel value patterns are compared between a corresponding region of interest and corresponding reference regions so as to calculate weights. A modified pixel-of-interest value is determined by means of multiplying the reference pixel values by the weights.

A system and method for detecting seatbelt positioning includes capturing, by a camera, a near infrared (NIR) image of an occupant, applying a median filter to the NIR image to remove glints; converting the NIR image to a black-and-white image, scanning across the black-and-white (B/W) image to detect a plurality of transitions between black and white segments corresponding to stripes extending lengthwise along a length of the seatbelt, and using detections of the plurality of transitions to indicate a detection of the seatbelt. Converting the NIR image to the black-and-white image may include using a localized binary threshold to determine whether a given pixel in the B/W image should be black or white based on whether a corresponding source pixel within the NIR image is brighter than an average of nearby pixels within a predetermined distance of the corresponding source pixel.

A system for removing a noise artifact from an image of a document extracts a first set of features from the image, where the first set of features represents items on the image. The system identifies noise artifact features from the first set of features representing pixel values of the noise artifact. The system generates a second set of features by removing the noise artifact features from the first set of features. The system generates a test clean image of the document based on the second set of features as an input. The system determines whether a portion of the test clean image that previously displayed the noise artifact corresponds to a counterpart portion of the training clean image. If it is determined that the portion of the test clean image corresponds to the counterpart portion of the training clean image, the system outputs the test clean image.

An Automated Teller Machine (ATM) for detecting security vulnerabilities by removing noise artifacts from documents receives a transaction request when a document is inserted into the ATM, where the document contains a noise artifact at least partially obstructing a portion of the document. The ATM generates an image of the document, where the image displays at least one data item comprising a sender's name, a receiver's name, and a number representing an amount. The ATM determines whether the noise artifact obstructs at least partially one data item. In response to determining that the noise artifact obstructs at least partially one data item, the ATM generates a test clean image of the document by removing the noise artifact from the image. In response to determining that the noise artifact is removed, the ATM approves the transaction request.