Artificial intelligence identified measuring method for a semiconductor image

1. An artificial intelligence identified measuring method for a semiconductor image, comprising the steps of:

providing an original image of a semiconductor;

identifying a type and/or a category of the original image by artificial intelligence;

introducing a predetermined dimension measuring mode corresponding to the identified type and/or the identified category to scan the original image to generate a measurement signal of the original image; and

extracting a designated object from the original image to generate a specific physical parameter of the original image after operation based on a measurement signal of the designated object and the measurement signal of the original image.

2. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 1 , wherein the original image of a semiconductor is photoshoot and provided by a scanning electron microscope (SEM), a tunneling electron microscope (TEM), an atomic force microscope (AFM), a focused ion beam (FIB) or a X-ray diffractometer (X-ray).

3. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 1 , wherein the designated object is a designated structure, a designated height, a designated distance, a designated 50% height, a minimum part, a maximum part, a bottommost part or a topmost part of the original image.

4. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 1 , wherein the specific physical parameter is selected from one of a group consisted of a thickness, a width, an average thickness, an average width, a standard deviation of a thickness, a standard deviation of a width, a root mean square of a thickness, and a root mean square of a width of a specific layer of the semiconductor, or combinations thereof, and/or the specific physical parameter is selected from one of a group consisted of a length, a width, a height, a gap, an angle and an arc length of a designated object of the semiconductor, or combination thereof.

5. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 1 , wherein the operation of the measurement signal is proceed by intensity difference operation, integral difference operation or differential difference operation.

6. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 1 , wherein the step of identifying a type and/or a category of the original image by artificial intelligence is proceed by a neural network module.

7. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 6 , wherein the neural network module is a Convolutional Neural Network (CNN) module or a Recurrent Neural Network (RNN) module.

8. An artificial intelligence identified measuring method for a semiconductor image, comprising the steps of:

providing an original image of a semiconductor;

optimizing the original image to generate an optimized image;

identifying a type and/or a category of the optimized image by artificial intelligence;

introducing a predetermined dimension measuring mode corresponding to the identified type and/or the identified category to scan the optimized image to generate a measurement signal of the optimized image; and

extracting a designated object from the optimized image to generate a specific physical parameter after operation based on a measurement signal of the designated object and the measurement signal of the optimized image.

9. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the original image of a semiconductor is photoshoot and provided by a scanning electron microscope (SEM), a tunneling electron microscope (TEM), an atomic force microscope (AFM), a focused ion beam (FIB) or a X-ray diffractometer (X-ray).

10. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the step of optimizing the original image to generate an optimized image is to optimized the brightness, and/or the contrast, and/or the sharpness, and/or the color saturation, and/or the gamma correction, and/or the gray scales, and/or the hue, and/or the color difference, and/or the color temperature, and/or the focus, and/or the resolution, and/or the noise, and/or the edge planarization of the original image.

11. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the designated object is a designated structure, a designated height, a designated distance, a designated 50% height, a minimum part, a maximum part, a bottommost part or a topmost part of the optimized image.

12. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the specific physical parameter is selected from one of a group consisted of a thickness, a width, an average thickness, an average width, a standard deviation of a thickness, a standard deviation of a width, a root mean square of a thickness, and a root mean square of a width of a specific layer of the semiconductor, or combinations thereof, and/or the specific physical parameter is selected from one of a group consisted of a length, a width, a height, a gap, an angle and an arc length of a designated object of the semiconductor, or combination thereof.

13. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the operation of the measurement signal is proceed by intensity difference operation, integral difference operation or differential difference operation.

14. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 8 , wherein the step of identifying a type and/or a category of the original image by artificial intelligence is proceed by a neural network module.

15. The artificial intelligence identified measuring method for a semiconductor image as claimed in claim 14 , wherein the neural network module is a Convolutional Neural Network (CNN) module or a Recurrent Neural Network (RNN) module.