One embodiment provides a computer-implemented method that includes providing a dynamic list structure that stores one or more detected object bounding boxes. Temporal analysis is applied that updates the dynamic list structure with object validation to reduce temporal artifacts. A two-dimensional (2D) buffer is utilized to store a luminance reduction ratio of a whole video frame. The luminance reduction ratio is applied to each pixel in the whole video frame based on the 2D buffer. One or more spatial smoothing filters are applied to the 2D buffer to reduce a likelihood of one or more spatial artifacts occurring in a luminance reduced region.

The present disclosure provides a method and device for detecting an image category. The method includes: acquiring a sample data set including a plurality of sample images labeled with a category, the sample data set including a training data set and a verification data set; training a deep learning model using the training data set to obtain, according to different numbers of training rounds, at least two trained models; testing the at least two trained models using the verification data set to generate a verification test result; generating, based on the verification test result, a verification test index; determining, according to the verification test index, a target model from the at least two trained models; and predict a to-be-tested image of the target object using the target model to obtain the category of the to-be-tested image.

Systems and methods for automatically grading a user device are provided. Such systems and methods can include (1) a lighting element positioned at an angle relative to a platform, (2) an imaging device positioned at the angle relative to the platform such that light emitted from the lighting element and a field of view of the imaging device form a right angle where the light emitted from the lighting element and the field of view meet at a user device when the user device is positioned at a predetermined location on the platform, and (3) control circuitry that can activate the lighting element, instruct the imaging device to capture an image of a screen of the user device while the user device is at the predetermined location and is being illuminated by the first lighting element, and parse the image to determine whether the screen is damaged.

Provided are a light-emitting apparatus that can suppress manufacturing cost to a low level and perform light emission with high uniformity using a simple configuration, a calibration coefficient calculation method using the light-emitting apparatus, and a method for calibrating a captured image of an inspection target object. A plurality of light-emitting diodes arranged at equal intervals on the circumference of a virtual circle, and a milky white-colored emission window, which is provided on a top surface portion separated from the light-emitting diodes, has an outer edge that is smaller than the circumference on which the light-emitting diodes are arranged, and allows light of the light-emitting diodes to pass therethrough, are included. The diameter of the virtual circle on which the light-emitting diodes are arranged and a separation distance between the light-emitting diodes and the emission window are set to predetermined distances.

A method for detecting a display panel defect, including: collecting a panel image of a to-be-detected display panel, a plurality of first pixels of the display panel corresponding to a plurality of second pixels in the panel image; converting the panel image into a binary image; dilating each bright spot region in the binary image such that adjacent bright spot regions communicate with each other to form at least one closed communication region in the binary image; determining a region of interest mask image in the binary image in accordance with the at least one closed communication region; determining a region of interest in accordance with the region of interest mask image and the panel image; and performing feature identification on the region of interest to determine a defect of the display panel.

Some embodiments provide a method for calculating parasitic parameters for a pattern to be manufactured on an integrated circuit (IC) substrate. The method receives a definition of a wire structure as input. The method rasterizes the wire structure (e.g., produces pixel-based definition of the wire structure) to produce several images. Before rasterizing the wire structure, the method in some embodiments decomposes the wire structure into several components (e.g., several wires, wire segments or wire structure portions), which it then individually rasterizes. The method then uses the images as inputs to a neural network, which then calculates parasitic parameters associated with the wire structure. In some embodiments, the parasitic parameters include unwanted parasitic capacitance effects exerted on the wire structure. Conjunctively, or alternatively, these parameters include unwanted parasitic resistance and/or inductance effects on the wire structure.

A test support method includes a step of obtaining a pre-change image and a post-change image to be displayed on a monitoring and control system, a step of extracting, from the post-change image, multiple symbols that have changed from corresponding symbols in the pre-change image, a step of adding order information to the multiple symbols extracted, and a step of outputting a test image in which the order information is added to the multiple symbols.

What is disclosed are systems and methods for optical correction for correcting for non-uniformity in active matrix light emitting diode device (AMOLED) and other emissive displays, using iterative processing of images of calibration patterns including features of coarse and fine granularity to successively generate a high-resolution estimate of the panel pixel locations.

A method for detecting defects in appearance of a product from images thereof, applied in an electronic device, obtains positive sample images, negative sample images, and product sample images, divides the product sample images into input image blocks, and inputs the input image blocks into a pre-trained autoencoder to obtain reconstructed image blocks. The electronic device determines corresponding pixel points in the input image blocks, and corresponding pixel difference values, and generates feature connection regions of each input image block according to the positive sample images and the pixel difference values. The electronic device generates a first threshold, selects target regions from the feature connection regions and the first threshold, and generates a second threshold. The electronic device further determines a detection result of a product sample in the product sample image according to an area of the target area and the second threshold.

A system for manufacturing defect classification is presented. The system includes a first neural network receiving a first data as input and generating a first output, a second neural network receiving a second data as input and generating a second output, wherein first neural network and the second neural network are trained independently from each other, and a fusion neural network receiving the first output and the second output and generating a classification. The first data and the second data do not have to be aligned. Hence, the system and method of this disclosure allows various type of data that are collected during manufacturing to be used in defect classification.