Systems and methods for recognition of unreadable characters on printed circuit boards

Patent metadata

Field	Value
Publication number	US-2017372158-A1
Application number	US-201715612730-A
Country	US
Kind code	A1
Filing date	Jun 2, 2017
Priority date	Jun 2, 2016
Publication date	Dec 28, 2017
Grant date	—

Abstract

Systems and methods for recognition of unreadable characters on printed circuit boards. In some embodiments, a method for recognizing characters can be utilized for recognition of damaged characters on a printed circuit board. The method can include obtaining a digital image for each of a plurality of characters on the printed circuit board. The method can further include dividing each digital image into an array of regions. The method can further include generating a data structure from the arrays of the digital images. The data structure can include gradient features based on stroke shapes on small distances, structural features based on stroke trajectories on extended distances, and concavity features based on stroke relationships.

First claim

What is claimed is:

1 . A method for recognizing characters imprinted on a printed circuit board, the method comprising:
obtaining a digital image for each of a plurality of characters on the printed circuit board; dividing each digital image into an array of regions; and generating a data structure from the arrays of the digital images, the data structure including gradient features based on stroke shapes on small distances, structural features based on stroke trajectories on extended distances, and concavity features based on stroke relationships.

2 . The method of claim 1 further comprising obtaining another image of a character and performing a character recognition step based on the data structure.

3 . The method of claim 2 wherein the character recognition step is performed with a k-nearest neighbor classifier algorithm and a distance metric.

4 . The method of claim 3 wherein the distance metric includes a Euclidian Distance parameter.

5 . The method of claim 1 wherein the gradient features, the structural features, and the concavity features are obtained with a gradient, structural and concavity (GSC) algorithm.

6 . The method of claim 5 wherein the gradient features are obtained by two dimensional convolutions of each digital image with Sobel operators.

7 . The method of claim 5 wherein the structural features are obtained by adding zero padded borders to the array of each digital image, and seeking gradient patterns among array elements immediately surrounding each non-padded border array element.

8 . The method of claim 5 wherein the concavity features are obtained by generating a coarse pixel density of the array of each digital image, the coarse pixel density including a threshold applied to a count of all character pixels among the respective array.

9 . The method of claim 8 wherein the concavity features are further obtained by generating large-stroke information for the array of each digital image, the large-stroke information including a threshold applied to a histogram of pixels strokes in each of horizontal pixels and vertical pixels.

10 . The method of claim 9 wherein the concavity features are further obtained by generating upward, downward, left, right and hole information for the array of each digital image, the upward, downward, left, right and hole information including rays formed to hit the character pixels to thereby determine presence of additional character pixels or holes.

11 . The method of claim 1 wherein the data structure further includes a character class block representative of recognizable characters.

12 . The method of claim 11 wherein the recognizable characters include numeric characters 0 to 9.

13 . A method for recognizing characters imprinted on a printed circuit board, the method comprising:
obtaining a digital image of a character on the printed circuit board; and performing an optical character recognition process on the digital image using trained information that includes gradient features based on stroke shapes on small distances, structural features based on stroke trajectories on extended distances, and concavity features based on stroke relationships.

14 . A system for processing printed circuit boards, comprising:
a first production system configured to fabricate a plurality of printed circuit boards, each printed circuit board including a plurality of characters imprinted thereon to provide information about the printed circuit board; and a character recognition system configured to monitor at least some of the printed circuit boards, and including an imaging component configured to obtain a digital image of the characters on a selected printed circuit board, and a processor configured to perform an optical character recognition process on the digital image using trained information that includes gradient features based on stroke shapes on small distances, structural features based on stroke trajectories on extended distances, and concavity features based on stroke relationships.

15 . The system of claim 14 wherein the character recognition system further includes a storage component in communication with the processor and configured to store the trained information.

16 . The system of claim 14 wherein the processor is further configured to generate a data structure for the trained information.

17 . The system of claim 16 wherein the processor generates the data structure by obtaining a digital image for each of a plurality of characters on a selected printed circuit board, dividing each digital image into an array of regions, and generating the data structure from the arrays of the digital images, the data structure including the gradient features, the structural features, and the concavity features.

18 . The system of claim 14 further comprising a second production system configured to produce individual modules from each of at least some of the printed circuit boards fabricated by the first production system.

19 . The system of claim 18 wherein each printed circuit board is implemented as a packaging substrate panel having an array of modules joined together, such that the joined modules become the individual modules upon singulation by the second production system.

20 . The system of claim 18 wherein each individual module is configured to provide a wireless functionality.

Assignees

• Skyworks Solutions Inc

Inventors

• Nava Carlos Fabian

Classifications

• G06V30/18076

  by analysing connectivity, e.g. edge linking, connected component analysis or slices · CPC title

• G06V30/19173

  Classification techniques · CPC title

• G06F18/24147

  Distances to closest patterns, e.g. nearest neighbour classification · CPC title

• G06V30/224

  of printed characters having additional code marks or containing code marks · CPC title

• G06V30/10

  Character recognition · CPC title