A cabinet that has manually reconfigurable shelves, that can automatically detect the configuration of compartments in a shelf, and that can automatically detect if a user is accessing or restocking the right compartment is contemplated. The shelf can be reconfigured using one or more dividers to divide the shelf into two or more compartments. The compartments can have different sizes and store different items. The compartments can be physically reconfigured by the user and the cabinet can automatically detect the specifics of the reconfiguration and adjust compartment size and availability. A surface of the shelf includes a plurality of visual markers. The cabinet has cameras mounted to it and uses visual markers to determine if a compartment contains an item and other information.

The technology described herein generates a unique identifier for a visual media that comprises pre-printed visual indications on the visual media and a user's handwritten signature. The location of the signature on the visual media can be determined by including preprinted fiducial marks on the visual media. The fiducial markers act as landmarks that allow the size and location of the signature to be determined in absolute terms. The unique identifier is then stored in computer memory on a user-experience server. The user-experience server can associate the unique identifier with a digital asset, such as an image or video, designated by the user. When the unique identifier is provided to the user-experience server a second time, the digital asset can be retrieved and output to the computing device that provided the unique identifier.

An information processing apparatus includes a recognition unit. The recognition unit has image recognition methods of plural types. The recognition unit recognizes, in a case where image data of a first document and image data of a second document are generated by a generation unit that reads a document and generates image data of the document, the type of the first document from the image data of the first document and recognizing the type of the second document from the image data of the second document using an image recognition method corresponding to the type of the first document among the image recognition methods of the plural types, the first document and the second document being included in plural documents.

A method of generating a semi transparent QR code in which a QR code image and an ordinary color background image are synthesized, and a QR code detection method of separating a QR code and a normal color image from an image obtained by capturing a semi transparent QR code are disclosed.

Some embodiments of the present disclosure relate to a processing tool. The tool includes a housing enclosing a processing chamber, and an input/output port configured to pass a wafer through the housing into and out of the processing chamber. A back-side macro-inspection system is arranged within the processing chamber and is configured to image a back side of the wafer. A front-side macro-inspection system is arranged within the processing chamber and is configured to image a front side of the wafer according to a first image resolution. A front-side micro-inspection system is arranged within the processing chamber and is configured to image the front side of the wafer according to a second image resolution which is higher than the first image resolution.

When marks all align with a mark alignment region in an image, an image is acquired for an embroidery frame and embroidery design sewn to a portion of a cloth mounted on the frame. Image analysis is performed based on correspondence between acquired information for the embroidery frame and for the marks. The embroidery region of the embroidery frame is determined based on analysis results. Acquired images of the cloth having the embroidery design portion and an embroidery design to be sewn to it are displayed. The embroidery design image to be sewn is edited to connect it to the image of the embroidery design already sewn to the portion in the displayed image. This prevents the occurrence of overlapping or gaps between embroidery design units even if accumulated shrinkage occurs in sewing, or slight alignment errors occur in position or rotation when cloth is mounted on the embroidery frame.

Systems for identifying threat materials such as CBRNE threats and locations are provided. The systems can include a data acquisition component configured to determine the presence of a CBRNE threat; data storage media; and processing circuitry operatively coupled to the data acquisition device and the storage media. Methods for identifying a CBRNE threat are provided. The methods can include: determining the presence of a CBRNE threat using a data acquisition component; and acquiring an image while determining the presence of the CBRNE threat. Methods for augmenting a real-time display to include the location and/or type of CBRNE threat previously identified are also provided. Methods for identifying and responding to CBRNE threats are provided as well.

an optical sensing system comprising: a processing circuit; a first calibration optical sensor, comprising a first sensor edge and a second sensor edge opposite to the first sensor edge; and a second calibration optical sensor, away from the first calibration optical sensor for a first distance, comprising a third sensor edge and a fourth sensor edge opposite to the third sensor edge. The processing circuit determines a target object has moved for a target distance if an object pattern of the target object moves from a first location in the first calibration sensor to a second location in the second calibration sensor, wherein a first sum of a second distance which is between the first location and the first sensor edge and a third distance between the second location and the third sensor edge equals to a reference distance.

A method and a system for detecting a scene text may include extracting a first feature map for a scene image input based on a convolutional neural network, and delivering the first feature map to a sequential deformation module; obtaining sampled feature maps corresponding to sampling positions by performing iterative sampling for the first feature map, obtaining a second feature map by performing a concatenation operation in deep learning according to a channel dimension for the first feature map and the sampled feature maps; obtaining a third feature map by performing a feature aggregation operation for the second feature map in the channel dimension, and delivering the third feature map to the object detection baseline network; and performing text area candidate box extraction for the third feature map and obtaining a text area prediction result as a scene text detection result through regression fitting.

A method for document discovery includes receiving a scan of a physical copy of a document with a non-text object, determining a tag for the non-text object defining a portion of the non-text object in an original file, and generating, based on the tag, non-text object metadata with composition information of the non-text object. The method further includes searching, using the non-text object metadata, electronic documents stored in a data repository, where each of the electronic documents has an object and searchable metadata associated with the object, comparing the non-text object metadata with the searchable metadata, and providing a location of the original file to a user when the non-text object metadata matches the searchable metadata.