A reference line setting device includes an image acquisition means to acquire an image containing a character region, a recognition means to recognize characters from the character region of the image by a specified recognition method, a line position information acquisition means to acquire line position information of a plurality of characters out of the characters recognized by the recognition means with reference to a storage means storing, for each character, line position information concerning a position which at least two reference lines pass through in a vertical direction of characters, the reference lines being lines drawn in an alignment direction of characters, along which a certain part of each character is to be placed, and a setting means to set each of the reference lines to the image based on a plurality of line position information for each reference line acquired by the line position information acquisition means.

Systems and methods for automatically adjusting the exposure settings (e.g., exposure time, analog gain, etc.) of imaging device(s) and/or camera(s) utilized in machine vision systems. According to embodiments of the present disclosure, one or more images or frames of a stream of images captured by an imaging device of a machine vision system can be processed and analyzed to determine exposure settings that may be applied to capture subsequent images by the imaging device. For example, a frame of the stream of images can be partitioned into a plurality of zones, and the pixels of each zone can be non-uniformly sorted into a histogram to represent the distribution of pixels in each zone. The histogram values for each zone can be aggregated to determine an aggregated exposure value associated with the frame, which can be compared against a target exposure value in view of a response function associated with the imaging device to determine the exposure value for capturing subsequent frames in the stream of images.

Systems can be configured for detecting license plates and recognizing characters in license plates. In an example, a system can receive an image and identify one or more regions in the image that include a license plate. Character recognition can be performed in the one or more regions to determine contents of a candidate license plate. Location-specific information about a license plate format can be used together with the determined contents of the candidate license plate to determine if the recognized characters are valid.

An image processing apparatus counts at least one of the number of pixels having an identical color to a target pixel, the number of pixels having a similar color to the target pixel, and the number of pixels having a different color from the target pixel in a target window, and determines an attribute of the target pixel based on a result of the counting.

A date identification apparatus includes: an isolator that isolates, out of image data generated through capturing of an image of a medium to which a date is assigned using seven-segment characters, date area data to which the date is estimated to be assigned; a binarization converter that binarizes the date area data using a threshold based on luminance and hue; a labeler that subjects the binarized date area data to labeling to extract target area data that is identifiable as a numeral; a numeral identifier that performs a histogram on at least the target area data using a plurality of lines and identifies a numeral on a basis of a peak count in each of the lines; and a date data assigner that assigns date data based on the identified numeral to the image data.

The described aspects and implementations enable efficient detection and classification of objects with machine learning models that deploy a bird's-eye view representation and are trained using depth ground truth data. In one implementation, disclosed are system and techniques that include obtaining images, generating, using a first neural network (NN), feature vectors (FVs) and depth distributions pixels of images, wherein the first NN is trained using training images and a depth ground truth data for the training images. The techniques further include obtaining a feature tensor (FT) in view of the FVs and the depth distributions, and processing the obtained FTs, using a second NN, to identify one or more objects depicted in the images.

The present disclosure discloses a method and system for visual inspection of a target product. The method includes a) receiving an image associated with the target product; generating a plurality of region of interests (ROIs) associated with the image; identifying, based on the plurality of non-terminal ROIs, a first set of features and a second set of features associated with the image. The first set of features and the second set of features are indicative of one of a presence of defect within the image or an absence of defect within the image. The method also includes determining, based on the first set of features and the second set of features, a result of the visual inspection of the target product associated with the image. The result is a success result or a failure result.

Provided is a model training method, a data processing method and related apparatuses, relating to the technical fields of large model, image processing, and computer vision. The method includes: obtaining a historical process flow card set for spinning process; extracting a handwritten area from each historical process flow card; classifying the handwritten area to obtain a handwritten digit image block and a handwritten text image block; constructing a digit recognition model of different handwritten digit categories based on the handwritten digit image block, to extract a target digit from a newly-added process flow card; and constructing a text recognition model of different handwritten text categories based on the handwritten text image block, to extract a target text from the newly-added process flow card; wherein the target digit and the target text are used to construct a process flow database for the spinning process.

A method includes capturing a first image of the GUI at a first time, after the first time, providing the GUI with an input event to change a configuration of at least one of the plurality of graphical elements to include an expanded region and capturing a second image of the GUI at a second time after the input event. A background of the second image of the GUI changes from a background of the first image of the GUI to include one or more background text blocks and an expanded region text block. The method also includes obtaining, a difference image, determining whether the difference image includes the one or more background text blocks and the expanded region text block; and selecting a text block closest to a position of the at least one of the plurality of graphical elements as the expanded region text block.

Systems and methods are disclosed for presenting images of multiple, variant user interfaces along with corresponding metrics for concurrent comparison by a user. Client interfaces allow a client to interact with an underlying system and/or application. Examples of client interfaces include webpages that are presented to a client in a client/server system. Embodiments of the disclosed system and method allow user interface designers to directly compare images of variants of a user interface and corresponding metrics with images of one or more other variants on a display. In at least one embodiment, an image of a variant and corresponding metrics are designated as a control against which images of other variants and corresponding metrics are directly compared on the display.