Automated focusing of a microscope of an optical inspection system

1. A system, comprising:

a memory that stores computer executable components; and

a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:

an analyzer component that:

partitions sample images into a grid pattern comprising equally sized sub-images, wherein each sample image of the sample images is acquired at different focal positions along an optical axis of a microscope;

for each grid location of the grid pattern:

analyzes corresponding sub-images at the grid location of the sample images,

identifies whether any sub-image of the corresponding sub-images has a maximized variance of a gradient derivative,

in response to identification of a sub-image of the corresponding sub-images that has the maximized variance of the gradient derivative, denotes a sample image comprising the identified sub-image as having the maximized variance of the gradient derivative for the grid location;

a selection component that selects an image, from the sample images, that comprises a highest quantity of grid locations denoted as having the maximized variance of the gradient derivative; and

a focus component that, based on a focal position corresponding to the image selected, focuses the microscope to the focal position.

2. The system of claim 1 , wherein the gradient derivative is selected from a group consisting of a Laplacian derivative, a Sobel derivative, and a Scharr derivative.

3. The system of claim 1 , wherein the selection component selects the image further based on a ranking value assigned to the one or more sub-images identified as having the maximized variance of the gradient derivative in the image.

4. The system of claim 1 , further comprising a pixel mask component that masks one or more pixel locations of the sample images.

5. The system of claim 1 , further comprising an equalizer component that sets one or more image attributes of the sample images to one or more constant settings, wherein the one or more image attributes are selected from a group consisting of image contrast, image grayscale, image luminance, image brightness, image hue, and image saturation.

6. The system of claim 1 , further comprising a filter component that filters the respective sample images to reduce image noise captured in the respective sample images.

7. The system of claim 1 , wherein the sample images comprise reflected-light pattern images.

8. The system of claim 1 , wherein the microscope comprises an optical microscope.

9. The system of claim 1 , wherein the sample images comprise images of an electronic device selected from a group consisting of a semiconductor integrated circuit, a semiconductor integrated circuit package, a semiconductor integrated circuit assembly, a semiconductor integrated circuit wafer, and a semiconductor integrated circuit die.

10. A computer-implemented method, comprising:

in response to acquiring sample images at different focal positions along an optical axis of a microscope:

partitioning, by a system operatively coupled to a processor, the sample images into a grid pattern comprising equally sized sub-images,

for each grid location of the grid pattern:

analyzing, by the system, corresponding sub-images at the grid location of the sample images,

identifying, by the system, whether any sub-image of the corresponding sub-images has a maximized variance of a gradient derivative

in response to identification of a sub-image of the corresponding sub-images that has the maximized variance of the gradient derivative, denoting, by the system, a sample image comprising the identified sub-image as having the maximized variance of the gradient derivative for the grid location;

selecting, by the system, an image from the sample images that comprises a highest quantity of grid locations denoted as having the maximized variance of the gradient derivative; and

based on a focal position corresponding to the image selected, focusing, by the system, the microscope to the focal position.

11. The computer-implemented method of claim 10 , wherein the gradient derivative is selected from a group consisting of a Laplacian derivative, a Sobel derivative, and a Scharr derivative.

12. The computer-implemented method of claim 10 , wherein the selecting comprises selecting, by the system, the image from the sample images, further based on a ranking value assigned to the one or more sub-images identified as having the maximized variance of the gradient derivative in the image.

13. The computer-implemented method of claim 10 , further comprising masking, by the system, one or more pixel locations of the sample images.

14. The computer-implemented method of claim 10 , further comprising setting, by the system, one or more image attributes of the sample images to one or more constant settings, wherein the one or more image attributes are selected from a group consisting of image contrast, image grayscale, image luminance, image brightness, image hue, and image saturation.

15. The computer-implemented method of claim 10 , further comprising filtering, by the system, the sample images to reduce image noise captured in the sample images.

16. The computer-implemented method of claim 10 , wherein the sample images comprise reflected-light pattern images of an electronic device selected from a group consisting of a semiconductor integrated circuit, a semiconductor integrated circuit package, a semiconductor integrated circuit assembly, a semiconductor integrated circuit wafer, and a semiconductor integrated circuit die.

17. A computer program product facilitating a microscope focusing process, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

partition, by the processor, sample images into a grid pattern comprising equally sized sub-images, wherein each sample image of the sample images is acquired at different focal positions along an optical axis of the microscope;

for each grid location of the grid pattern:

analyze, by the processor, corresponding sub-images at the grid location of the sample images

identify, by the processor, whether any sub-image of the corresponding sub-images has a maximized variance of a gradient derivative

in response to identification of a sub-image of the corresponding sub-images that has the maximized variance of the gradient derivative, denote, by the processor, a sample image comprising the identified sub-image as having the maximized variance of the gradient derivative for the grid location;

select, by the processor, an image from the sample images that comprises a highest quantity of grid locations denoted as having the maximized variance of the gradient derivative; and

based on a focal position corresponding to the image selected, focus, by the processor, a microscope to the focal position.

18. The computer program product of claim 17 , wherein the gradient derivative is selected from a group consisting of a Laplacian derivative, a Sobel derivative, and a Scharr derivative.

19. The computer program product of claim 17 , wherein the processor selects the image from the sample images further based on a ranking value assigned to the one or more sub-images identified as having the maximized variance of the gradient derivative in the image.

20. The computer program product of claim 17 , wherein the sample images comprise reflected-light pattern images of an electronic device selected from a group consisting of a semiconductor integrated circuit, a semiconductor integrated circuit package, a semiconductor integrated circuit assembly, a semiconductor integrated circuit wafer, and a semiconductor integrated circuit die.