Method for detecting data defects and computing device utilizing method
AssigneeHon Hai Precision Industry Co., Ltd.
InventorsTZU-CHEN LIN, TUNG-TSO TSAI, CHIN-PIN KUO
Life of this patent
Estimating the term…
Abstract
A method for detecting data defects and a computing device applying the method obtains a test image for analysis. A field to which the test image relates is determined. Based on the field, a target convolutional layer is determined from a convolutional neural network. The target convolutional layer is used to extract features of the test image. A target score of the test image and a score threshold corresponding to the field are determined. If the target score is less than the score threshold, it is determined that the test image reveals defects, thereby improving an accuracy of defect detection.
Claims20
A method for detecting data defects, the method comprising:
- obtaining a test image;
- determining a field to which the test image relates, and based on the field, determining a target convolutional layer from a convolutional neural network;
- using the target convolutional layer to extract features of the test image;
- determining a target score of the test image according to the features of the test image;
- determining a score threshold corresponding to the field;
- and
- determining that the test image is a defective image if the target score is less than the score threshold.
A computing device comprising a memory and a processor, the memory stores at least one computer-readable instruction, and the processor executes the at least one computer-readable instruction to implement a method for detecting data defects, the method comprising:
- obtaining a test image;
- determining a field to which the test image relates, and based on the field, determining a target convolutional layer from a convolutional neural network;
- using the target convolutional layer to extract features of the test image;
- determining a target score of the test image according to the features of the test image;
- determining a score threshold corresponding to the field;
- and
- determining that the test image is a defective image if the target score is less than the score threshold.
A non-transitory storage medium having at least one computer-readable instruction stored thereon, when the at least one computer-readable instruction is executed by a processor to implement a method for detecting data defects, the method comprising:
- obtaining a test image;
- determining a field to which the test image relates, and based on the field, determining a target convolutional layer from a convolutional neural network;
- using the target convolutional layer to extract features of the test image;
- determining a target score of the test image according to the features of the test image;
- determining a score threshold corresponding to the field;
- and
- determining that the test image is a defective image if the target score is less than the score threshold.
Dependencies are inferred from the claim text.