Region of interest location and selective image compression

Patent metadata

Field	Value
Publication number	US-10699091-B2
Application number	US-201715716226-A
Country	US
Kind code	B2
Filing date	Sep 26, 2017
Priority date	May 29, 2015
Publication date	Jun 30, 2020
Grant date	Jun 30, 2020

Abstract

Systems and methods of operation for an image processor system to process images to locate two-dimensional regions which are likely to contain machine-readable symbol data or text. Such regions of interest (ROIs) may be preserved at full resolution, whilst the contents of non-ROIs are averaged into a single pixel value. Transition densities in an image may be converted into a numeric value. Such transition densities may be indicative of the presence of data of interest, such as textual data and/or machine-readable symbol data. The pixels values for the pixels in the ROIs may be sent to a decoder unchanged (i.e., full resolution), which absolves the decoder from having to perform any ROI location computations. Modified or altered images may be compressed to much smaller size files while maintaining lossless ROIs, which allows for transmission of such images to processor-based devices over a data communications channel in real time.

First claim

The invention claimed is:

1. A method of operation for an image processor system, the method comprising:
receiving, by at least one processor, a binarized image file comprising a plurality of binarized pixels, each of the binarized pixels having a binarized pixel value;
for each of the binarized pixels,
assigning, by the at least one processor, a pattern value dependent on a pattern of the binarized pixel values in a region of binarized pixels that includes the binarized pixel; and
determining, by the at least one processor, a direction value based at least in part on the assigned pattern value;

generating, by the at least one processor, a vector image file that comprises the direction values determined for each of the plurality of binarized pixels of the binarized image file;
dividing, by the at least one processor, the vector image file into a plurality of blocks, each of the plurality of blocks having a size of N×M, pixels, wherein N and M are integers; and
for each block,
generating, by the at least one processor, a histogram of the direction values in the block; and
analyzing, by the at least one processor, the generated histogram to distinguish between the block having a one dimensional machine-readable symbol, a two dimensional machine-readable symbol, or text.

2. The method of claim 1 wherein assigning a pattern value comprises assigning a pattern value dependent on a pattern of the binarized pixel values in a 3×3 region of binarized pixels that includes the binarized pixel as the center pixel of the region.

3. The method of claim 1 wherein determining a direction value comprises utilizing the assigned pattern value as an index into a lookup table of pattern values and corresponding direction values.

4. The method of claim 1 wherein determining a direction value comprises determining a direction value, and the directions represented by the direction values are separated from one another by a fixed angle, and each of the directional values comprises an integer multiple of the fixed angle.

5. The method of claim 4 wherein the directions represented by the direction values are separated from one another by 22.5 degrees.

6. The method of claim 1 wherein analyzing the generated histogram comprises determining a centroid of the histogram which corresponds to at least one directional value for the block.

7. The method of claim 1 wherein analyzing the generated histogram comprises analyzing the generated histogram for a statistical mode of the histogram.

8. The method of claim 1 wherein dividing the vector image file into a plurality of blocks comprises dividing the vector image file into a plurality of blocks each having a size of N×M pixels, where N and M are each equal to 16.

9. The method of claim 1 wherein analyzing the generated histogram comprises applying vector amplitude normalization factors to the histogram.

10. The method of claim 1 wherein analyzing the generated histogram comprises determining that that the block comprises a one-dimensional machine-readable symbol, and further determining an angular direction of the one-dimensional machine-readable symbol.

11. The method of claim 1 wherein analyzing the generated histogram comprises determining that the block includes multiple directional values, and the method further comprises determining whether the block includes a two-dimensional machine-readable symbol or text by comparing a binarization score of the block to a determined two-dimensional binarization threshold value.

12. An image processor system, comprising:
at least one processor;
at least one nontransitory processor-readable storage medium operatively coupled to the at least one processor which stores a binarized image file comprising a plurality of binarized pixels, each of the binarized pixels having a binarized pixel value, the at least one nontransitory processor-readable medium further storing at least one of data or instructions which, when executed by the at least one processor, cause the at least one processor to:
for each of the binarized pixels,
assign a pattern value dependent on a pattern of the binarized pixel values in a region of binarized pixels that includes the binarized pixel; and
determine a direction value based at least in part on the assigned pattern value;

generate a vector image file that comprises the direction values determined for each of the plurality of binarized pixels of the binarized image file;
divide the vector image file into a plurality of blocks, each of the plurality of blocks having a size of N×M, pixels, wherein N and M are integers; and
for each block,
generate a histogram of the direction values in the block; and
analyze the generated histogram to distinguish between the block having a one dimensional machine-readable symbol, a two dimensional machine-readable symbol, or text.

13. The method of claim 1 , further comprising identifying a valid one dimensional machine-readable symbol or two dimensional machine-readable symbol before initiating decoding thereof by a decode engine.

14. The image processor system of claim 12 wherein the region comprises a 3×3 region of binarized pixels that includes the binarized pixel as the center pixel of the region.

15. The image processor system of claim 12 wherein the at least one processor utilizes the assigned pattern value as an index into a lookup table of pattern values and corresponding direction values.

16. The image processor system of claim 12 wherein the at least one processor divides the vector image file into a plurality of blocks each having a size of N×M pixels, wherein N and M are each equal to 16.

17. The image processor system of claim 12 wherein the at least one processor applies vector amplitude normalization factors to the histogram.

18. The image processor system of claim 12 wherein the at least one processor determines whether the block includes multiple directional values, and further compares a binarization score of the block to a determined two-dimensional binarization threshold value to determine whether the block includes a two-dimensional machine-readable symbol or text.

19. The image processor system of claim 12 wherein the one-dimensional machine-readable symbol is a barcode.

20. An image processor system comprising:
at least one processor;
at least one nontransitory processor-readable storage medium operatively coupled to the at least one processor which stores a binarized image file comprising a plurality of binarized pixels, each of the binarized pixels having a binarized pixel value, the at least one nontransitory processor-readable medium further storing at least one of data or instructions which, when executed by the at least one processor, cause the at least one processor to:
for each of the binarized pixels,
assign a pattern value dependent on a pattern of the binarized pixel values in a region of binarized pixels that includes the binarized pixel; and
determine a direction value based at least in part on the assigned pattern value:

generate a vector image file that comprises the direction values determined for each of the plurality of binarized pixels of the binarized image file;
divide the vector image file into a plurality of blocks, each of the plurality of blocks having a size of N×M, pixels, wherein N and M are integers; and
for each block,
generate a histogram of the direction values in the block; and
analyze the generated histogram to determine whether the block comprises a one dimensional machine-readable symbol, a two dim

Assignees

• Datalogic Usa Inc

Inventors

• Gagliano Jeffrey A

Classifications

• G06K7/1495 Primary

  the method including an image compression step · CPC title

• G06V10/25 Primary

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06K7/10732

  Light sources · CPC title

• G06K7/1417

  2D bar codes · CPC title

• G06K7/1413

  1D bar codes · CPC title