Inspection system for detecting foreign material and scratch at edge of semiconductor wafer and non-transitory computer-readable medium storing a program for same
The present disclosure proposes a system for detecting a foreign material adhering to or a scratch formed on a bevel at an edge of a semiconductor wafer in order to detect the foreign material or defect on the bevel without using a reference image and including a learning device ( 905 ) that outputs information on the foreign material adhering to or the scratch formed on the bevel as a learning result, in which the learning device performs learning in advance by using image data acquired by an image acquisition tool and the information on the foreign material or the scratch on the bevel included in the image data, and the foreign material or the scratch is detected by inputting the image data obtained by the image acquisition tool to the learning device (refer to FIG. 9 ).
1 . An inspection system for detecting a foreign material adhering to or a scratch formed on a bevel at an edge of a semiconductor wafer from image data obtained by an image acquisition tool, comprising:
a computer system including a processor and memory storing a program executed by the processor, the program causing the processor to:
perform learning in advance by using the image data acquired by the image acquisition tool and the information on the foreign material or the scratch on the bevel included in the image data, and output information on the foreign material adhering to or the scratch formed on the bevel as a learning result, and
detect the foreign material or the scratch based on the image data obtained by the image acquisition tool and the learning result,
wherein the computer system detects the foreign material or the scratch by using a learning model according to a manufacturing process based on a number of films of the semiconductor wafer.
2 . The inspection system according to claim 1 , wherein the image acquisition tool is communicably connected to the computer system, and
wherein the image acquisition tool includes:
an X-ray detector detecting X-rays emitted from a sample by irradiating the sample with a beam, and
an X-ray analyzer classifying elements contained in the sample based on an output of the X-ray detector.
3 . The inspection system according to claim 2 , wherein the image acquisition tool selectively executes analysis using an X-ray analyzer according to a type of the foreign material or the scratch detected by the processor.
4 . The inspection system according to claim 2 , wherein the computer system receives the image data from the image acquisition tool, receives information on elements from the X-ray analyzer, and executes a labeling process using the received information on elements on the received image data.
5 . The inspection system according to claim 1 , wherein the processor performs learning by using teacher data including manufacturing process information of the semiconductor wafer, and detects the foreign material or the scratch based on the manufacturing process information of a sample.
6 . A non-transitory computer-readable medium for storing a computer program for causing a computer to execute a process of detecting a foreign material adhering to or a scratch formed on a bevel at an edge of a semiconductor wafer from image data obtained by an image acquisition tool,
wherein the computer program executes:
a process of performing learning by using the image data acquired by the image acquisition tool and the information on the foreign material or the scratch on the bevel included in the image data, and outputting the information on the foreign material adhering to or the scratch formed on the bevel as a learning result; and
a process of detecting the foreign material or the scratch in another image data obtained by the image acquisition tool by using the learning result,
wherein the computer detects the foreign material or the scratch by using a learning model according to a manufacturing process based on a number of films of the semiconductor wafer.