A delivery management server, connected to a sender terminal and a carrier terminal over a network, includes a registration means for writing destination information of a delivery object received from the sender terminal and a first image in which a random pattern on a surface of the delivery object is captured, into a storage means in association with each other; a matching means for performing matching between a second image in which a random pattern on a surface of the delivery object is captured, received from the carrier terminal, and the first image stored in the storage means; and a presentation means for displaying the destination information associated with the first image stored in the storage means on a terminal screen of the carrier terminal, on the basis of a result of the matching.

A method may include determining, based at least on an image of a document, a plurality of text bounding boxes enclosing lines of text present in the document. A machine learning model may be trained to determine, based at least on the coordinates defining the text bounding boxes, the coordinates of a document bounding box enclosing the text bounding boxes. The document bounding box may encapsulate the visual aberrations that are present in the image of the document. As such, one or more transformations may be determined based on the coordinates of the document bounding box. The image of the document may be deskewed by applying the transformations. One or more downstream tasks may be performed based on the deskewed image of the document. Related methods and articles of manufacture are also disclosed.

Information about a drug-containing vessel is determined by capturing image data of the curved surface of a cylindrical portion of a drug-containing vessel. The image data is unfurled from around the curved surface, binarised, and a template matching algorithm employed to determine that the label information comprises candidate information about the vessel and/or the drug.

In a scene where a pseudo character image is generated by performing deformation processing for a character image, a character image that impedes training is suppressed from being generated. Based on a condition relating to a parameter that is used for the deformation processing and associated with a first class, a parameter of the deformation processing is determined and the deformation processing is performed for a character image belonging to the first class using the determined parameter. Then, whether or not the deformed character image generated by the deformation processing is similar to a character image belonging to a class different from the first class is determined and in a case where similarity is determined, the condition associated with the first class is updated.

A video text tracking method and an electronic device are disclosed. In the method, a text line region is split into sub-regions, the sub-regions are tracked and then processed, and processed sub-regions are combined into a new text line. The technical solutions provided in this application are not only applicable to a straight-line text scenario or a curved text scenario, but also present a good tracking effect for a deformable text line.

A text recognition method and apparatus, a storage medium, and an electronic device. Said method comprises: acquiring a text image (S101); determining at least one text box from the text image, each text box corresponding to at least one word (S102); determining, from the at least one text box, a text box to be recognized (S103); determining, from the text image, a picture unit corresponding to the text box to be recognized (S104); rotating the picture unit to a target pose (S105); and performing text recognition on the picture unit in the target pose, and acquiring a target recognition result (S106). The method, apparatus, storage medium, and electronic device can recognize a text unit in a text having a large inclination angle.

A method of rectifying a text image, a training method, an electronic device, and a medium, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, deep learning technology, intelligent transportation and high-precision maps. An exemplary implementation includes: performing, based on a gating strategy, a plurality of first layer-wise processing on a text image to be rectified, so as to obtain respective feature maps of a plurality of layer levels, wherein each of the feature maps includes a text structural feature related to the text image to be rectified, and the gating strategy is configured to increase an attention to the text structural feature; and performing a plurality of second layer-wise processing on the respective feature maps of the plurality of layer levels, so as to obtain a rectified text image corresponding to the text image to be rectified.

A computer-readable, non-transitory recording medium contains therein an image processing program. The image processing program is for generating learning data of a character detection model that at least detects, to recognize a character in a document contained in an image, a position of the character in the image, and configured to cause a computer to generate a cropped image by cropping the image, and adopt the cropped image not containing an image representing a split character as the learning data, instead of adopting the cropped image containing the image representing the split character as the learning data.

The invention provides an edge detection method and a device of an object in an image, an electronic equipment, and a computer-readable storage medium. The method includes: a line drawing of a grayscale contour in the image is obtained; similar lines in the line drawing are merged to obtain initial merged lines, and a boundary matrix is determined according to the initial merged lines; similar lines in the initial merged lines are merged to obtain target lines, and unmerged initial merged lines are also used as target lines; reference boundary lines are determined from the target lines according to the boundary matrix; boundary line regions of the object in the image are obtained; a target boundary line corresponding to the boundary line region is determined from the reference boundary lines; an edge of the object in the image is determined according to the determined target boundary lines.

Methods for managing notes, either digital notes or images of physical notes. The methods use optical character recognition to convert handwritten content into characters and icons. The methods also determine sizes of non-square physical notes when imaged by a camera from various angles. For curled notes or damaged notes such as a note missing a corner, the methods detect and process edges of a physical note in an image and, using the detected edges, convert the image of the physical note into a corresponding digital note without curl or damage.