An image forming apparatus includes circuitry. The circuitry generates a binary image having area gradation or a scaled image having area gradation from an image read by a scanner. The circuitry outputs classification of the binary image or the scaled image according to a neural network model learned in advance.

An image augmentation device is provided, which includes a memory and a processor. The processor is configured for performing following operations: extracting a first object contour from a first image mask, wherein the first object contour corresponds to a first label; superimposing the first object contour to a superimposed region in a second image mask according to an augmentation parameter to generate a third image mask, wherein the augmentation parameter includes a contour scaling parameter, a contour moving distance, a contour rotation angle and a range which can be superimposed, and the third image mask includes the first object contour and a second object contour in the second image mask; and generating a sample image which corresponds to according to the first object contour and the second object contour in the third image mask by a generative adversarial network model for performing machine learning.

A system and method provide for determining regions of interest within an image based on viewer interaction with the image. At least one image associated with a location is provided for display in a viewport, and pose data related to user interaction with the at least one image is identified. Weights are assigned to portions of the at least one image based on the pose data, the weights indicating at least a period of time the portion of the at least one image is generally at a center of the viewport. Based on the assigned weights, image regions of interest of the at least one image are determined.

An analysis method of lane stripe images, an image analysis device and a non-transitory computer readable medium thereof are provided to perform steps of: setting a reference point as a center to recognize the lane stripe image in a plurality of default directions; defining a plurality of preset sections onto the lane stripe image and determining a characteristic value of the lane stripe image in each of the preset sections whenever the lane stripe image is recognized in one of the default directions; determining a first feature parameter according to the characteristic values of the lane stripe image in the preset sections when the lane stripe image is recognized in at least one of the default directions; and determining an actual lane parameter of the lane stripe image according to at least the first feature parameter.

Provided are an image processing method, a device, and a storage medium, the method comprising: performing human face detection on a first image, and obtaining position information for each human face in the first image, then determining whether the first image conforms to a multi-person composition rule on the basis of the position information of each human face in the first image; and cropping the first image based on the position information of each face in the first image to obtain a processed image, in response to the first image not complying with the multi-person composition rule.

Embodiments of the present application provide a browser-based frame extraction method. The method includes: monitoring a target operation of a user on a target page of a browser; obtaining a local video file associated with the target operation; and extracting a plurality of target frames from the local video file using a WebAssembly video parser in the browser. This disclosure enables a browser to independently complete operations such as frame extraction on videos in various encoding formats so as to reduce server load.

An image processing apparatus includes an image division unit, an image processing unit, and an integration unit. The image division unit divides a palm print image into a plurality of divisional images. The image processing unit determines a valid region in each of the plurality of divisional images by using a fingerprint model, performs image processing that extracts core lines in each valid region, and generates respective processed divisional images corresponding to the divisional images. The integration unit generates an entire processed image corresponding to an entire of the palm print image by integrating the processed divisional images.

A device may capture a plurality of preview frames of a document, and for each preview frame of the plurality of preview frames, process the preview frame to identify an object in the preview frame. Processing the preview frame may include converting the preview frame into a grayscale image, generating a blurred image based on the grayscale image, detecting a plurality of edges in the blurred image, defining at least one bounding rectangle based on the plurality of edges, and determining an outline of the object based on the at least one bounding rectangle. The device may determine whether a value of an image parameter, associated with the one or more preview frames, satisfies a threshold, and provide feedback to a user of the device, or automatically capture an image of the document, based on determining whether the value of the image parameter satisfies the threshold.

A display defect detection system and a detection method thereof are disclosed. A display defect detection system includes a preprocessing circuit receiving a capture image of a test pattern, displayed by a display panel, as a panel image including diagonal Mura and preprocessing the panel image to output a preprocessing image and a Mura detection circuit calculating a final feature value of the diagonal Mura by multiplying a first feature value, in which a luminance difference of the diagonal Mura is reflected, by a second feature value in which a shape ratio of the diagonal Mura is reflected, on the basis of an edge map of the preprocessing image, and detecting a display position of the diagonal Mura on the basis of the final feature value of the diagonal Mura.

A computer accesses a plurality of image frames. The computer identifies, within the plurality of image frames, a plurality of vehicle front vehicle back detections. The computer pairs at least a subset of the plurality of vehicle back detections with vehicle front detections. A given vehicle back detection is paired with a given vehicle front detection based on camera angle relative to a predefined axis. The computer assigns, using each of a plurality of pools, a score to each vehicle front detection—vehicle back detection pair, each non-paired vehicle front detection, and each non-paired vehicle back detection. Each pool comprises a data structure representing a scoring mechanism and a set of detections. The computer assigns each detection to a pool that assigned a highest score to that detection. Upon determining that a given pool comprises at least n detections: the computer labels the given pool as representing a specific vehicle.