A marking region image is obtained by cutting out the part corresponding to a marking region from an article image obtained by imaging an article to be inspected. Then, whether or not the marking is properly provided is determined by performing a character recognition of a marking part for a marking region image. Further, an image of an article having no marking and no defect is stored as a reference image, whereas a marking periphery image obtained by removing the image of the marking part from the marking region image is compared to the reference image. By that comparison, whether or not any defect is included in the marking peripheral part of the marking region except the marking part is determined.

The present disclosure is directed to systems and methods for identifying regions of interest (ROIs) in images. A computing system may identify an image including an annotation defining an ROI. The image may have a plurality of pixels in a first color space. The computing system may convert the plurality of pixels from the first color space to a second color space to differentiate the annotation from the ROI. The computing system may select a first subset of pixels corresponding to the annotation based at least on a color value of the first subset of pixels in the second color space. The computing system may identify a second subset of pixels included in the ROI from the image using the first subset of pixels. The computing system may store an association between the second subset of pixels and the ROI defined by the annotation in the image.

Technologies for smart bookmark synchronization may include a smart bookmark device, a bookmark server, and one or more client computing devices. The smart bookmark device transmits an identification of a book to the bookmark server, which determines a format of the book based on the identification. The smart bookmark device captures sensor data indicative of the current reading position of a user in the book and transmits the sensor data to the bookmark server. The sensor data may include image data of a current page in the book. The bookmark server determines bookmark data indicative of the current reading position based on the sensor data. The bookmark server transmits the bookmark data to the smart bookmark device and, in some embodiments, to the client computing devices and/or applications. The client computing devices may synchronize playback of a digital media book with the bookmark data. Other embodiments are described and claimed.

Described are methods and system that digitally watermark documents using an encoding scheme that embeds unique identifiers into the files by perturbing the relative heights of words to create patterns that are imperceptible to the human eye but decodable to recover the identifiers. The unique identifiers can be precoded before they are embedded in the documents.

In an approach for product compliance and certification validation, a processor, in response to receiving a product at a validation point, inspects the product using a plurality of sensors, including an image recognition system, to identify at least one certification label associated with the product. A processor correlates information received from the plurality of sensors, including image data, against information in a certification database to create correlation data. A processor validates the correlation data against destination information for the product. A processor, in response to receiving a negative validation, sends an indication of invalid to ship status to a predetermined destination. A processor reroutes the product as a rejected item to a predetermined position for inspection.

A system and method for field extraction including determining a key position of a key in an electronic file, isolating candidate key values based on a distance from the key position, selecting a key value from the candidate key values based on an output of a trained neural network, and extracting the key and the key value from the electronic file, regardless of a key-value structure.

An image processing apparatus includes an acquisition section, a marker detecting section, a text extracting section, and a markup language processing section. The marker detecting section detects, based on the image data acquired by the acquisition section, a marker assigned to an original document. The text extracting section analyzes the image data to recognize and extract a text in the original document. The markup language processing section generates markup data in which the text in the image data has the same display color as the marker.

An information processing apparatus includes: a marker extracting unit that extracts a marker from image data, and determines a marker position indicating a position of the marker; a character data extracting unit that extracts character data from the image data, and determines a character position indicating a position of the character data; an attribute data setting unit that sets character data, the character position of which has a specific relationship with the marker position, as an attribute of the marker; and a template generating unit that sets an area to be recognized, which is an area as a target of object recognition, on the basis of the marker position, and generates a template file including the marker position, the character data set as the attribute of the marker, and the area to be recognized.

Data processing method, apparatus, electronic device, and computer storage medium are provided. The data processing method is used to generate a description information file related to a target object, and includes: obtaining a description framework and multiple types of multiple materials related to the target object, the description framework including attribute selection information corresponding to the target object; performing at least one type of processing on each material to obtain attribute information of the respective material, and the attribute information including an attribute level and an attribute content; selecting target materials whose attribute content and attribute level match the attribute selection information of the description framework; and generating a description information file according to the description framework and the target materials. The data processing method may automatically generate description information files.

A system and method for classifying images of an evidence, the method including: generating an unlabeled template based on a first received image, wherein the unlabeled template includes a first set of regions of interest (ROIs); selecting a labeled template that includes a second set of ROIs from a plurality of labeled templates determined to be a best match for the unlabeled template; checking at least an ROI of the first set of ROIs for content that corresponds to a label of an equivalent ROI of the second set of ROIs; and, classifying the first image upon determination that the content checked corresponds to the label according to the labeled template.