Grading cosmetic appearance of a test object based on multi-region determination of cosmetic defects
A system and method for grading the cosmetic appearance of a test object based on multi-region determination of cosmetic defects are disclosed. The method may include grading a test object, such as, but not limited to, a computing device, for refurbishing and selling refurbished devices. In at least one embodiment, the method may include receiving, by a processing device, a plurality of images of surfaces of a test object. A region of interest in each of the plurality of images is identified and defects are identified. The cosmetic appearance of each region of interest is graded based on the identified defects and are stored. The system may include a housing with a translucent dome and a movable platform for receiving and positioning a computing device. The system may include a plurality of cameras and lights arranged to capture different views of the computing device.
1. A method, comprising:
receiving, by a processing device, a plurality of images of a test object, the plurality of images including a plurality of surfaces of the test object and captured with use of a reflection reduction lighting system that controls lighting to reduce reflections to enable defects to be identified rather than reflections on the plurality of surfaces of the test object,
wherein the reflection reduction lighting system includes at least one semi-transparent dome with at least one opening in the at least one semi-transparent dome for receiving the test object,
wherein the at least one semi-transparent dome is made of plastic and has a light transmission rate of 0.6% to 1.6%, and
wherein a shape of the at least one semi-transparent dome is selected to match a geometry of the test object;
selecting, by the processing device, a region of interest in each of the plurality of images, the region of interest comprising the test object having a background removed;
for the plurality of regions of interest as selected,
aligning each of the plurality of images with corresponding profile images, and
comparing, by the processing device, each region of interest with a respective corresponding profile image and identifying defects in each region of interest,
wherein the identifying defects in each region of interest comprises identifying brightness variations indicating an edge of a defect;
grading, by the processing device, a cosmetic appearance of each region of interest based on the identified defects; and
storing the grades of the cosmetic appearance for each region of interest.
2. The method of claim 1 , wherein the defects include scratches, cracks, discoloration, and combinations thereof.
3. The method of claim 1 , comprising determining one or more features of the defects of each region of interest as identified, wherein the one or more features comprise dimensions of a defect, area of a defect, contrast of a defect, depth of a defect, and combinations thereof.
4. The method of claim 3 , wherein grading the cosmetic appearance of each region of interest is based on a severity of the identified defects as determined from the one or more features of the identified defects.
5. The method of claim 1 , comprising outputting, by the processing device, the grades of the cosmetic appearance for each region of interest on a display.
6. The method of claim 1 , wherein grading the cosmetic appearance of each region of interest based on the identified defects comprises weighting a significance of a defect based on its location on the plurality of surfaces of the test object.
7. The method of claim 1 , wherein grading the cosmetic appearance of each region of interest based on the identified defects comprises weighting a significance of a defect based on a defect type, wherein the types of defects include scratches, cracks, and discoloration.
8. The method of claim 1 , comprising: aligning the plurality of images with corresponding profile images.
9. A method, comprising:
capturing an image of a first surface of a computing device with a first camera;
determining, by a processing device, a model and manufacturer of the computing device based on the image of the first surface of the computing device;
rotating the computing device to capture a second surface of the computing device that is opposite the first surface;
capturing an image of the second surface of the computing device with the first camera;
moving the computing device to a second location and capturing an image of a third surface using a second camera and capturing an image of a fourth surface using a third camera;
rotating the computing device to capture fifth and sixth surfaces that are opposite the third and fourth surfaces;
capturing an image of the fifth surface using the second camera and capturing an image of the sixth surface using the third camera;
selecting, by the processing device, a region of interest in each of the images, the region of interest comprising the computing device having a background removed;
for each region of interest as selected,
aligning the plurality of images with corresponding profile images;
comparing, by the processing device, each region of interest with a respective corresponding profile image and identifying defects in each region of interest,
wherein the identifying defects in each region of interest comprises identifying brightness variations indicating an edge of a defect;
grading, by the processing device, a cosmetic appearance of each region of interest based on the identified defects; and
storing the grades of the cosmetic appearance for each region of interest;
wherein the images are captured with use of a reflection reduction lighting system that controls lighting to reduce reflections to enable defects to be identified rather than reflections on the plurality of surfaces of the test object, wherein the reflection reduction lighting system includes at least one semi-transparent dome with at least one opening in the at least one semi-transparent dome for receiving the test object, wherein the at least one semi-transparent dome is made of plastic and has a light transmission rate of 0.6% to 1.6%, and wherein a shape of the at least one semi-transparent dome is selected to match a geometry of the test object.
10. The method of claim 9 , wherein the first surface is a rear surface of the computing device and the second surface is a front surface of the computing device, the second surface being a display of the computing device.
11. The method of claim 9 , wherein the third, fourth, fifth, and sixth surfaces are side surfaces of the computing device.
12. The method of claim 9 , wherein the defects include scratches, cracks, discoloration, and combinations thereof.
13. The method of claim 9 , comprising determining one or more features of the defects of each region of interest as identified, wherein the one or more features comprise dimensions of a defect, area of a defect, contrast of a defect, depth of a defect, and combinations thereof.
14. The method of claim 13 , wherein grading the cosmetic appearance of each region of interest is based on a severity of the identified defects as determined from the one or more features of the identified defects.
15. The method of claim 9 , comprising outputting, by the processing device, the grades of the cosmetic appearance for each region of interest on a display.
16. The method of claim 9 , wherein grading the cosmetic appearance of each region of interest based on the identified defects comprises weighting a significance of a defect based on its location on the plurality of surfaces of the computing device.
17. The method of claim 9 , wherein grading the cosmetic appearance of each region of interest based on the identified defects comprises weighting a significance of a defect based on a defect type, wherein the types of defects include scratches, cracks, and discoloration.