Abstract: Embodiments of this application provide a defect detection method and apparatus. The method includes: obtaining an image for inspection; performing anomaly detection on the image for inspection to obtain an anomaly region image corresponding to the image for inspection; and performing defect classification on the anomaly region image to obtain defect detection information of the image for inspection. The defect detection method of the embodiments of this application is divided into two steps of anomaly detection and defect classification. Anomaly detection is performed on the image for inspection first, and then defect classification needs to be performed only on an anomaly region, reducing the workload of defect classification, thereby improving the efficiency of defect detection.

Abstract: Embodiments of this application provide a measurement method and a measurement apparatus. The measurement method includes: acquiring a first image and a second image of a target object, where the first image is acquired by a camera located on a non-backlight side of the target object, and the second image is acquired by a camera located on a backlight side of target object; and measuring the target object for size information according to the first image and the second image. The technical solution of this application can improve accuracy and precision of inspection while improving production efficiency.

Abstract: The present application provides a method and system for defect detection. The method includes: acquiring a two-dimensional (2D) picture of an object to be detected; inputting the acquired 2D picture to a trained defect segmentation model to obtain a segmented 2D defect mask, where the defect segmentation model is trained based on a multi-level feature extraction instance segmentation network with intersection over union (IoU) thresholds being increased level by level, and the 2D defect mask includes information about a defect type, a defect size, and a defect location of a segmented defect region; and determining the segmented 2D defect mask based on a predefined defect rule to output a defect detection result.

Abstract: A correction method for a depth image of a battery includes obtaining the depth image of the battery. The depth image includes two adjacent surfaces of a shell assembly of the battery and an intersecting line between the two adjacent surfaces. The method further includes extracting the intersecting line from the depth image, determining planes in the depth image in which the two adjacent surfaces are located, and obtaining a datum plane based on the intersecting line and the planes in which the two adjacent surfaces are located. The datum plane is parallel to the intersecting line, and included angles between the datum plane and the planes in which the two adjacent surfaces are located are equal to each other. The method also includes projecting and mapping points in the depth image to the datum plane, to obtain depth information of points in a corrected depth image.

Abstract: Embodiments of this application provide a measurement method and a measurement apparatus. The measurement method includes: acquiring a first image and a second image of a target object, where the first image is acquired by a camera located on a non-backlight side of the target object, and the second image is acquired by a camera located on a backlight side of target object; and measuring the target object for size information according to the first image and the second image. The technical solution of this application can improve accuracy and precision of inspection while improving production efficiency.

Abstract: Embodiments of this application provide a defect detection method and apparatus. The method includes: obtaining an image for inspection; performing anomaly detection on the image for inspection to obtain an anomaly region image corresponding to the image for inspection; and performing defect classification on the anomaly region image to obtain defect detection information of the image for inspection. The defect detection method of the embodiments of this application is divided into two steps of anomaly detection and defect classification. Anomaly detection is performed on the image for inspection first, and then defect classification needs to be performed only on an anomaly region, reducing the workload of defect classification, thereby improving the efficiency of defect detection.

Abstract: An image recognition method may include: acquiring a target image, where the target image may include a weld bead region; performing initial segmentation on the target image, to obtain a first recognition result, where the first recognition result may include first recognition information for the weld bead region in the target image; performing feature extraction on the target image, to obtain a region representation; obtaining a context representation based on the first recognition result and the region representation, where the context representation may be used for representing a correlation between each pixel and remaining pixels in the target image; and obtaining a second recognition result based on the context representation, where the second recognition result may include second recognition information for the weld bead region in the target image.

Abstract: Provided are a method and system for anomaly detection. The method includes: acquiring a picture of an object to be detected; inputting the acquired picture to each of a trained teacher network and a student network distilled from the teacher network, to obtain a feature map output by the teacher network and a feature map output by the student network, where the teacher network is trained by constructing a defective sample to learn feature distribution of normal samples from a pre-trained expert network; and determining a greatest anomalous pixel in a difference map between the feature map output by the teacher network and the feature map output by the student network as an anomaly value of the acquired picture, to output an anomaly detection result.

Abstract: A method for training a cell defect detection model includes training a defect classification model that includes an output layer using a plurality of first sample images so that a defect classification model obtained through training is capable of predicting a plurality of first-preset-category defects of a cell, inputting a second sample image to a defect classification model with at least an output layer removed to obtain a sample feature vector of the second sample image, inputting the sample feature vector of the second sample image to a backbone model to obtain a predicted defect classification result of the second sample image, and adjusting, based on a second-preset-category defect and the predicted defect classification result of the second sample image, parameters of the backbone model and the defect classification model with at least the output layer removed.

Abstract: The present application provides a method and system for defect detection. The method includes: acquiring a two-dimensional (2D) picture of an object to be detected; inputting the acquired 2D picture to a trained defect segmentation model to obtain a segmented 2D defect mask, where the defect segmentation model is trained based on a multi-level feature extraction instance segmentation network with intersection over union (IoU) thresholds being increased level by level, and the 2D defect mask includes information about a defect type, a defect size, and a defect location of a segmented defect region; and determining the segmented 2D defect mask based on a predefined defect rule to output a defect detection result.

Abstract: An image recognition method may include: acquiring a target image, where the target image may include a weld bead region; performing initial segmentation on the target image, to obtain a first recognition result, where the first recognition result may include first recognition information for the weld bead region in the target image; performing feature extraction on the target image, to obtain a region representation; obtaining a context representation based on the first recognition result and the region representation, where the context representation may be used for representing a correlation between each pixel and remaining pixels in the target image; and obtaining a second recognition result based on the context representation, where the second recognition result may include second recognition information for the weld bead region in the target image.