Method and apparatus for locating dot text in an image

A non-transitory computer readable storage medium that provides instructions, which when executed by a processor, cause said processor to perform operations comprising:

• extracting a first set of a plurality of dots from an image;
• determining whether a first region of interest including the first set of dots satisfies selection criteria, wherein the first region of interest is oriented based on a first and a second axis resulting from a principal component analysis of the first set of dots;
• responsive to determining that the first region of interest satisfies the selection criteria, outputting the first region of interest as a location of dot text in the image;
• and
• responsive to determining that the first region of interest does not satisfy the selection criteria, performing the following:
• (a) removing an outlier dot from the first set of dots to obtain a second set of dots,
• (b) determining whether a second region of interest including the second set of dots satisfies the selection criteria, wherein the second region of interest is oriented based on a third and fourth axis resulting from a principal component analysis of the second set of dots,
• (c) responsive to determining that the second region of interest satisfies the selection criteria, outputting the second region of interest as a location of the dot text in the image, and
• (d) responsive to determining that the second region of interest does not satisfy the selection criteria, repeating (a) and (b) until a resulting region of interest is determined to satisfy the selection criteria, wherein in the repeated (a) and (b) the first set of dots is updated to include the second set of dots after removal of the outlier dot.

A system for locating dot text in an image comprising:

• one or more processors;
• and
• a non-transitory computer readable storage medium that stores code which when executed by the one or more processors, causes the system to:
• extract a first set of a plurality of dots from an image,
• determine whether a first region of interest including the first set of dots satisfies selection criteria, wherein the first region of interest is oriented based on a first and a second axis resulting from a principal component analysis of the first set of dots,
• responsive to determining that the first region of interest satisfies the selection criteria, output the first region of interest as a location of the dot text in the image, and
• responsive to determining that the first region of interest does not satisfy the selection criteria, perform the following:
• (a) remove an outlier dot from the first set of dots to obtain a second set of dots,
• (b) determine whether a second region of interest including the second set of dots satisfies the selection criteria, wherein the second region of interest is oriented based on a third and fourth axis resulting from a principal component analysis of the second set of dots,
• (c) responsive to determining that the second region of interest satisfies the selection criteria, output the second region of interest as a location of the dot text in the image, and
• (d) responsive to determining that the second region of interest does not satisfy the selection criteria, repeat (a) and (b) until a resulting region of interest is determined to satisfy the selection criteria, wherein in the repeated (a) and (b) the first set of dots is updated to include the second set of dots after removal of the outlier dot.