Macro inspection systems, apparatus and methods
The disclosed technology relates to an inspection apparatus that includes a stage configured to retain a specimen for inspection, an imaging device having a field of view encompassing at least a portion of the stage to view a specimen retained on the stage, and a plurality of lights disposed on a moveable platform. The inspection apparatus can further include a control module coupled to the imaging device, each of the lights and the moveable platform. The control module is configured to perform operations including: receiving image data from the imaging device, where the image data indicates an illumination landscape of light incident on the specimen; and automatically modifying, based on the image data, an elevation of the moveable platform or an intensity of one or more of the lights to adjust the illumination landscape. Methods and machine-readable media are also contemplated.
1. A method, comprising:
generating, by a computing system, a training data set for training a prediction model to generate an illumination profile for a specimen positioned on a stage of an inspection apparatus, the training data comprising image data and non-image data of a plurality of training specimens;
training, by the computing system, the prediction model to generate illumination profiles for the plurality of training specimens, each illumination profile comprising one or more of an indication of lighting positions for a plurality of lights illuminating a corresponding specimen, an intensity level of each of the plurality of lights, a color of each of the plurality of lights, or distance information between each of the plurality of lights and the stage; and
applying, by the computing system, the prediction model to an image of the specimen to create the illumination profile for the specimen.
2. The method of claim 1 , wherein applying, by the computing system, the prediction model to the image of the specimen to create the illumination profile for the specimen comprises:
inputting context data, the image of the specimen, and non-image specimen data into the prediction model generate the illumination profile to be applied to illuminate the specimen.
3. The method of claim 1 , wherein the training data set further comprises:
for each image in the image data, information describing an activation, an intensity, a color, and a position of lights used to illuminate a respective specimen.
4. The method of claim 1 , wherein the training data set further comprises:
for each image in the image data, a distance between a specimen stage holding a respective specimen and a lens capturing the image of the respective specimen.
5. The method of claim 1 , wherein creating the illumination profile for the specimen comprises:
determining which lights of an inspection system to activate for illuminating the specimen.
6. The method of claim 5 , wherein creating the illumination profile for the specimen further comprises:
determining at which intensity to set each light of the inspection system for illuminating the specimen.
7. The method of claim 5 , wherein creating the illumination profile for the specimen further comprises:
determining a color at which to set each light of the inspection system for illuminating the specimen.
8. The method of claim 5 , wherein creating the illumination profile for the specimen further comprises:
determining a positioning to set each light of the inspection system for illuminating the specimen.
9. A system comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:
generating a training data set for training a prediction model to generate an illumination profile for a specimen positioned on a stage of an inspection apparatus, the training data comprising image data and non-image data of a plurality of training specimens;
training the prediction model to generate illumination profiles for the plurality of training specimens, each illumination profile comprising one or more of an indication of lighting positions for a plurality of lights illuminating a corresponding specimen, an intensity level of each of the plurality of lights, a color of each of the plurality of lights, or distance information between each of the plurality of lights and the stage; and
applying the prediction model to an image of the specimen to create the illumination profile for the specimen.
10. The system of claim 9 , wherein applying the prediction model to the image of the specimen to create the illumination profile for the specimen comprises:
inputting context data, the image of the specimen, and non-image specimen data into the prediction model generate the illumination profile to be applied to illuminate the specimen.
11. The system of claim 9 , wherein the training data set further comprises:
for each image in the image data, information describing an activation, an intensity, a color, and a position of lights used to illuminate a respective specimen.
12. The system of claim 9 , wherein the training data set further comprises:
for each image in the image data, a distance between a specimen stage holding a respective specimen and a lens capturing the image of the respective specimen.
13. The system of claim 9 , wherein creating the illumination profile for the specimen comprises:
determining which lights of an inspection system to activate for illuminating the specimen.
14. The system of claim 13 , wherein creating the illumination profile for the specimen further comprises:
determining at which intensity to set each light of the inspection system for illuminating the specimen.
15. The system of claim 13 , wherein creating the illumination profile for the specimen further comprises:
determining a color at which to set each light of the inspection system for illuminating the specimen.
16. The system of claim 13 , wherein creating the illumination profile for the specimen further comprises:
determining a positioning to set each light of the inspection system for illuminating the specimen.
17. A non-transitory computer readable medium having one or more sequences of instructions, which, when executed by a processor, causes a computing system to perform operations comprising:
generating, by the computing system, a training data set for training a prediction model to generate an illumination profile for a specimen positioned on a stage of an inspection apparatus, the training data comprising image data and non-image data of a plurality of training specimens;
training, by the computing system, the prediction model to generate illumination profiles for the plurality of training specimens, each illumination profile comprising one or more of an indication of lighting positions for a plurality of lights illuminating a corresponding specimen, an intensity level of each of the plurality of lights, a color of each of the plurality of lights, or distance information between each of the plurality of lights and the stage; and
applying, by the computing system, the prediction model to an image of the specimen to create the illumination profile for the specimen.
18. The non-transitory computer readable medium of claim 17 , wherein applying, by the computing system, the prediction model to the image of the specimen to create the illumination profile for the specimen comprises:
inputting context data, the image of the specimen, and non-image specimen data into the prediction model generate the illumination profile to be applied to illuminate the specimen.
19. The non-transitory computer readable medium of claim 17 , wherein the training data set further comprises:
for each image in the image data, information describing an activation, an intensity, a color, and a position of lights used to illuminate a respective specimen.
20. The non-transitory computer readable medium of claim 17 , wherein the training data set further comprises:
for each image in the image data, a distance between a specimen stage holding a respective specimen and a lens capturing the image of the respective specimen.