US 11,308,605 B2Granted

Image processing for printed circuit board component detection

AssigneeUniversity of Florida Research Foundation, Inc.

InventorsNavid Asadi-Zanjani, Mark M. Tehranipoor, Mukhil Azhagan Mallaiyan Sathiaseelan

Life of this patent

Estimating the term…

Loading patent…

Abstract

There is a need for more effective and efficient printed circuit board (PCB) design. This need can be addressed by, for example, solutions for performing automated PCB component estimation. In one example, a method includes identifying a PCB image of a PCB; performing chromaticity-based background subtraction on the PCB image to generate a background-subtracted PCB image; performing morphological noise removal on the background-subtracted PCB image to generate a noise-removed PCB image; and performing object localization on the noise-removed PCB image to identify one or more PCB component estimations within the noise-removed PCB image.

Claims20

Dependent claims

A computer-implemented method for performing printed circuit board (PCB) component estimation, the computer-implemented method comprising:

performing chromaticity-based background subtraction via one or more processors executing on a PCB design computing entity on a PCB image of the PCB to generate a background-subtracted PCB image, wherein the chromaticity-based background subtraction comprises:
for each particular pixel in the PCB image,
determining a normalized chromatic intensity measure for the particular pixel,
determining whether the normalized chromatic intensity measure satisfies a chromatic intensity threshold,
responsive to determining the normalized chromatic intensity measure satisfies the chromatic intensity threshold, generating a modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a background pixel, and
responsive to determining the normalized chromatic intensity measure fails to satisfy the chromatic intensity threshold, generating the modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a foreground pixel;
performing morphological noise removal on the background-subtracted PCB image via the one or more processors executing on the PCB design computing entity to generate a noise-removed PCB image, wherein the morphological noise removal comprises performing a sequence of at least one of one or more morphological erosions or one or more morphological dilations on the background-subtracted PCB image;
performing object localization on the noise-removed PCB image via the one or more processors executing on the PCB design computing entity to identify one or more PCB component estimations within the noise-removed PCB image, wherein the object localization comprises performing segmentation on the noise-removed PCB image to detect contiguous pixel segments within the noise-removed PCB image to identify the one or more PCB component estimations;
generating a bill of materials for the PCB by the one or more processors executing on the PCB design computing entity using the one or more PCB component estimations;
and
refining, using the one or more processors, one or more PCB manufacturing processes based at least in part on the bill of materials.

8 more elements

An apparatus for performing printed circuit board (PCB) component estimation, the apparatus comprising at least one processor and at least one memory including program code, the at least one memory and the program code configured to, with the at least one processor, cause the apparatus to at least:

perform chromaticity-based background subtraction on a PCB image of the PCB to generate a background-subtracted PCB image, wherein the chromaticity-based background subtraction comprises:
for each particular pixel in the PCB image,
determining a normalized chromatic intensity measure for the particular pixel,
determining whether the normalized chromatic intensity measure satisfies a chromatic intensity threshold,
responsive to determining the normalized chromatic intensity measure satisfies the chromatic intensity threshold, generating a modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a background pixel, and
responsive to determining the normalized chromatic intensity measure fails to satisfy the chromatic intensity threshold, generating the modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a foreground pixel;
perform morphological noise removal on the background-subtracted PCB image to generate a noise-removed PCB image, wherein the morphological noise removal comprises performing a sequence of at least one of one or more morphological erosions or one or more morphological dilations on the background-subtracted PCB image;
perform object localization on the noise-removed PCB image to identify one or more PCB component estimations within the noise-removed PCB image, wherein the object localization comprises performing segmentation on the noise-removed PCB image to detect contiguous pixel segments within the noise-removed PCB image to identify the one or more PCB component estimations;
generate a bill of materials for the PCB using the one or more PCB component estimations;
and
refine one or more PCB manufacturing processes based at least in part on the bill of materials.

8 more elements

A non-transitory computer storage medium comprising instructions for performing printed circuit board (PCB) component estimating, the instructions being configured to cause one or more processors to at least perform operations configured to:

perform chromaticity-based background subtraction on a PCB image of the PCB to generate a background-subtracted PCB image, wherein the chromaticity-based background subtraction comprises:
for each particular pixel in the PCB image,
determining a normalized chromatic intensity measure for the particular pixel,
determining whether the normalized chromatic intensity measure satisfies a chromatic intensity threshold,
responsive to determining the normalized chromatic intensity measure satisfies the chromatic intensity threshold, generating a modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a background pixel, and
responsive to determining the normalized chromatic intensity measure fails to satisfy the chromatic intensity threshold, generating the modified pixel for the particular pixel within the background-subtracted PCB image that indicates that the particular pixel is a foreground pixel;
perform morphological noise removal on the background-subtracted PCB image to generate a noise-removed PCB image, wherein the morphological noise removal comprises performing a sequence of at least one of one or more morphological erosions or one or more morphological dilations on the background-subtracted PCB image;
perform object localization on the noise-removed PCB image to identify one or more PCB component estimations within the noise-removed PCB image, wherein the object localization comprises performing segmentation on the noise-removed PCB image to detect contiguous pixel segments within the noise-removed PCB image to identify the one or more PCB component estimations;
generate a bill of materials for the PCB using the one or more PCB component estimations;
and
refine one or more PCB manufacturing processes based at least in part on the bill of materials.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/149,097Filed 14 Jan 2021 · us provisional application
Priority: 14 Feb 2020
Published: US 2021/0256683 A119 Aug 2021
Granted: 19 Apr 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification13 codes

G06T 7/0004
Inspection of images, e.g. flaw detection: industrial image inspection
G06T 7/10
Image analysis: segmentation; Edge detection
G06T 7/11
Segmentation; Edge detection: region-based segmentation
G06T 7/136
Segmentation; Edge detection: involving thresholding

Family

Application62/976,752Us provisional application · filed 14 Feb 2020
US 2021/0256683 A1Pre-grant publication · published 19 Aug 2021
US 11,308,605 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key