Method and apparatus for automatic measurement of pad geometry and inspection thereof

1. A machine vision method of inspecting a semiconductor interconnection pad, the method comprising:

acquiring an image of the pad, the pad having a multiple zone pattern;

automatically deriving a multiple zone geometric description of the multiple zone pattern using the image, wherein the step of automatically deriving comprises:

extracting a plurality of features from the image;

generating a plurality of hypothetical geometric descriptions using the features; and

selecting the multiple zone geometric description from the plurality of hypothetical geometric descriptions, including:

validating at least one of the plurality of hypothetical descriptions using an area-based contrast evaluation to provide validated hypothetical descriptions; and

selecting at least one validated hypothetical description using a maximum number of zones to provide a multiple zone geometric description; and

using the multiple zone geometric description in a machine vision inspection of the pad.

2. The method of claim 1 wherein the step of generating a plurality of hypothetical geometric descriptions using the features comprises an acceptance test using a contrast value of the features.

3. The method of claim 1 wherein the step of generating a plurality of hypothetical geometric descriptions using the features comprises an acceptance test using a grey level range of the features.

4. The method of claim 1 wherein the features include at least one of a side feature, an edge feature, a noise feature, a surface defect feature, a feature not associated with boundaries of the multiple zone pattern, a corner boundary of the multiple zone pattern and a side boundary of the multiple zone pattern.

5. The method of claim 1 further comprising the step of comparing at least one of the features to at least one adjacent feature to determine whether the at least one feature is compatible with the at least one adjacent feature.

6. A method for inspecting a semiconductor interconnection pad using a machine vision system, the method comprising:

acquiring an image of the pad, the pad having a multiple zone pattern;

automatically deriving a multiple zone geometric description of the multiple zone pattern using the image, wherein the step of automatically deriving comprises:

extracting at least one zone boundary from a plurality of zone boundaries identified on the image of the multiple zone pattern;

extracting a plurality of features from the at least one zone boundary identified on the image;

generating a plurality of hypothetical geometric descriptions using the features; and

selecting the multiple zone geometric description from the plurality of hypothetical geometric descriptions, including:

validating at least one of the plurality of hypothetical descriptions using an area-based contrast evaluation to provide validated hypothetical descriptions; and

selecting at least one validated hypothetical description to provide a multiple zone geometric description; and

using the multiple zone geometric description in a machine vision inspection of the pad.

7. The method of claim 6 wherein the step of generating a plurality of hypothetical descriptions using the features comprises an acceptance test using a contrast value of the features.

8. The method of claim 6 wherein the step of generating a plurality of hypothetical descriptions using the features comprises an acceptance test using a grey level range of the features.

9. The method of claim 6 wherein the features include at least one of a side feature, an edge feature, a noise feature, a surface defect feature, a feature not associated with boundaries of the multiple zone pattern, a corner boundary of the multiple zone pattern and a side boundary of the multiple zone pattern.

10. An apparatus for inspecting a semiconductor interconnection pad comprising:

means for acquiring an image of the pad, the pad having a multiple zone pattern;

means for automatically deriving a multiple zone geometric description of the multiple zone pattern using the image, wherein the means for automatically deriving comprises:

means for extracting a plurality of features from the image;

means for generating a plurality of hypothetical geometric descriptions using the features; and

means for selecting the multiple zone geometric description from the plurality of hypothetical geometric descriptions, including:

means for validating at least one of the plurality of hypothetical descriptions using an area-based contrast evaluation to provide validated hypothetical descriptions; and

means for selecting at least one validated hypothetical description using a maximum number of zones to provide a multiple zone geometric description; and

means for using the multiple zone geometric description in a machine vision inspection of the pad.

11. The apparatus of claim 10 wherein the means for generating a plurality of hypothetical geometric descriptions using the features comprises an acceptance test using a contrast value of the features.

12. The apparatus of claim 10 wherein the means for generating a plurality of hypothetical geometric descriptions using the features comprises an acceptance test using a grey level range of the features.

13. The apparatus of claim 10 wherein the features include at least one of a side feature, an edge feature, a noise feature, a surface defect feature, a feature not associated with boundaries of the multiple zone pattern, a corner boundary of the multiple zone pattern and a side boundary of the multiple zone pattern.

14. The apparatus of claim 10 further comprising means for comparing at least one feature to at least one adjacent feature to determine whether the at least one feature is compatible with the at least one adjacent feature.