Semiconductor inspection apparatus
Patent Information
- Application Number
- TW115201106
- Authority / Receiving Office
- TW · TW
- Patent Type
- Utility models
- Current Assignee / Owner
- Filing Date
- 2026-02-03
- Publication Date
- 2026-09-21
- Estimated Expiration
- 2036-02-02
Smart Images

Figure TWG2TB001912682_001 
Figure TWG2TB001912682_002 
Figure TWG2TB001912682_003
Abstract
Claims
1. A semiconductor testing device comprising: a testing stage; a robotic arm for gripping an object to be tested; a light source for emitting illumination light to the testing stage; an image acquisition device for capturing a test image of the object to be tested relative to the testing stage; and a control device electrically connected to the testing stage, the robotic arm, the light source, and the image acquisition device, and having an artificial intelligence defect detection module and an automatic optical inspection module, wherein the control device controls the robotic arm to place the object to be tested on the testing stage, and then uses the detection results of the artificial intelligence defect detection module and the automatic optical inspection module to distinguish a complex background and at least one defect of the object to be tested, thereby finding the location of the at least one defect in the complex background.
2. The semiconductor inspection equipment as described in claim 1, wherein the control device uses the automatic optical inspection module to analyze the inspection image to determine whether the inspection image has a complex background on the surface, and then decides whether to activate the artificial intelligence defect detection module based on the judgment result.
3. The semiconductor inspection apparatus as claimed in claim 2, wherein when the control device determines that the inspection image has the complex background on the surface, it activates the artificial intelligence defect detection module to exclude the complex background from the inspection image and find the location of the at least one defect.
4. The semiconductor inspection device as described in claim 3, wherein the control device automatically shuts down the automatic optical inspection module and switches to the artificial intelligence defect inspection module when the number of one of the inspection images with the complex background of the surface exceeds a predetermined threshold.
5. The semiconductor inspection device as claimed in claim 2, wherein when the control device determines that the inspection image does not have the complex background of the surface, it does not activate the artificial intelligence defect detection module, and continues to use the automatic optical inspection module to find the location of the at least one defect in the inspection image.
6. The semiconductor inspection device as claimed in claim 5, wherein the control device automatically shuts down the automatic optical inspection module and switches to the artificial intelligence defect detection module when the number of defects and / or the total area of a defect exceeds a predetermined defect standard.
7. The semiconductor testing apparatus as claimed in claim 1, wherein when the control device identifies the at least one defect, it uses a defect filtering module to determine whether the at least one defect is a false positive.
8. The semiconductor inspection apparatus as claimed in claim 1, wherein the control device drives the automatic optical inspection module to analyze the inspection image according to a first defect predetermined rule to find the at least one defect that conforms to a first defect size.
9. The semiconductor inspection apparatus as claimed in claim 8, wherein the control device further drives the artificial intelligence defect detection module to analyze the inspection image according to a second defect predetermined rule different from the first defect predetermined rule to find the at least one defect that meets a second defect size; the second defect size is larger than the first defect size.
10. The semiconductor inspection apparatus as claimed in claim 9, wherein the control device simultaneously or alternately uses the automatic optical inspection module and the artificial intelligence defect detection module to analyze the inspection image to identify the at least one defect of different sizes.
