# US 2019/0244044 A1 · Systems and methods for recognizing symbols in images

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0244044 A1
- Document ID: US20190244044A1
- Status: Published application
- Kind: A1
- Application number: 16/391,083
- Filed: 2019-04-22
- Published: 2019-08-08
- Earliest claimed: 2016-04-08
- Assignees: Intelligent Security Systems Corporation
- Applicants: Intelligent Security Systems Corporation
- Inventors: Alexander BONCH-OSMOLOVSKY
- Web page: https://patentgrep.com/patent/US20190244044A1

## CPC

- G06V 30/224: of printed characters having additional code marks or containing code marks
- G06T 7/11: Region-based segmentation
- G06T 7/12: Edge-based segmentation
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A computer-implemented method comprises generating a description of a character symbol from a binarized image; comparing a template for the character symbol with the description of the character symbol based on a reference description, wherein the template comprises a grid of cells, a set of local features which may be present in the grid of cells, the reference description specifying which member of the set of local features should be present or absent in the grid of cells, and a threshold of an accepted deviation with the description of the character symbol; assigning a penalty value to the description of the character symbol via a cost function when a discrepancy exists based on the comparing; selecting the template as a match candidate for the character symbol when the penalty value is below the threshold; recognizing the character symbol based on the selecting.

## Claims

### Claim 1

A method comprising:
in response to pre-processing, by a server, an image inclusive of a symbol, comparing, by the server, a template for the symbol with a description of the symbol, wherein the template comprises a grid of cells, a set of local features which may be present in the grid of cells, a reference description specifying which member of the set of local features should be present or absent in the grid of cells, and a threshold of an accepted deviation with the description of the symbol;
in response to assigning, by the server, a penalty value to the description of the symbol via a cost function based on a discrepancy existing between the template and the description of the symbol, selecting, by the server, the template as a match candidate for the symbol based on the penalty value satisfying the threshold; and
recognizing, by the server, the symbol as the match candidate.

### Claim 2 (depends on 1)

The method of claim 1, wherein the symbol is a glyph.

### Claim 3 (depends on 2)

The method of claim 2, wherein the image shows a license plate, wherein the license plate includes the symbol.

### Claim 4 (depends on 1)

The method of claim 1, wherein the reference description comprises a mask table set that specifies a cell in which a presence or an absence of a respective local feature is meaningful for recognition.

### Claim 5 (depends on 1)

The method of claim 1, wherein the reference description comprises a pattern table set that indicates whether or not a given local feature should be present in a given cell of the symbol.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
rejecting, by the server, the template as the match candidate for the symbol based on the penalty value not satisfying the threshold.

### Claim 7 (depends on 1)

The method of claim 1, wherein the grid of cells is a first grid of cells, wherein the description of the symbol is based on:
segmenting, by the server, a bounding box into a second grid of cells, wherein the bounding box contains the symbol, wherein the first grid of cells corresponds to the second grid of cells, wherein the second grid of cells contains a plurality of pixels, each of the cells of the second grid of cells contains a set of pixels;
determining, by the server, for each of the pixels in the set of pixels of each of the cells of the second grid of cells, a presence or an absence of a local feature from the set of local features;
determining, by the server, for each of the cells of the second grid of cells, a presence or an absence of a local feature from the set of local features based on an application of a rule to an individual pixel included in that respective cell.

### Claim 8 (depends on 1)

The method of claim 1, wherein the grid of cells is a first grid of cells, wherein the description of the symbol includes a second grid of cells corresponding to the first grid of cells, wherein the template and the description of the symbol are compared based on:
for each of the local features of the reference description which mandates a presence or an absence of a specified local feature and for each of the cells in the second grid of cells, verifying, by the server, the presence or the absence in the description of the symbol.

### Claim 9 (depends on 1)

The method of claim 1, wherein the threshold is determined based on an appropriate presence or absence of a selected local feature in a selected cell of a bounding box, wherein the threshold corresponds to a number or percentage of cells meeting or not meeting a criterion.

### Claim 10 (depends on 1)

The method of claim 1, wherein for each local feature of the reference description and for each cell, where the description of the symbol mandates a presence or an absence of that local feature, a check for the presence or the absence of this respective feature in the description of the symbol is performed.

### Claim 11

A system comprising:
a server programmed to:
in response to pre-processing an image inclusive of a symbol, compare a template for the symbol with a description of the symbol, wherein the template comprises a grid of cells, a set of local features which may be present in the grid of cells, a reference description specifying which member of the set of local features should be present or absent in the grid of cells, and a threshold of an accepted deviation with the description of the symbol;
in response to assigning a penalty value to the description of the symbol via a cost function based on a discrepancy existing between the template and the description of the symbol, select the template as a match candidate for the symbol based on the penalty value satisfying the threshold;
recognize the symbol as the match candidate.

### Claim 12 (depends on 11)

The system of claim 11, wherein the symbol is a glyph.

### Claim 13 (depends on 12)

The system of claim 12, wherein the image shows a license plate, wherein the license plate includes the symbol.

### Claim 14 (depends on 11)

The system of claim 11, wherein the reference description comprises a mask table set that specifies a cell in which a presence or an absence of a respective local feature is meaningful for recognition.

### Claim 15 (depends on 11)

The system of claim 11, wherein the reference description comprises a pattern table set that indicates whether or not a given local feature should be present in a given cell of the symbol.

### Claim 16 (depends on 11)

The system of claim 11, wherein the server is programmed to reject the template as the match candidate for the symbol based on the penalty value not satisfying the threshold.

### Claim 17 (depends on 11)

The system of claim 11, wherein the grid of cells is a first grid of cells, wherein the description of the symbol is based on the server being programmed to:
segment a bounding box into a second grid of cells, wherein the bounding box contains the symbol, wherein the first grid of cells corresponds to the second grid of cells, wherein the second grid of cells contains a plurality of pixels, each of the cells of the second grid of cells contains a set of pixels;
determine for each of the pixels in the set of pixels of each of the cells of the second grid of cells, a presence or an absence of a local feature from the set of local features;
determine for each of the cells of the second grid of cells, a presence or an absence of a local feature from the set of local features based on an application of a rule to an individual pixel included in that respective cell.

### Claim 18 (depends on 11)

The system of claim 11, wherein the grid of cells is a first grid of cells, wherein the description of the symbol includes a second grid of cells corresponding to the first grid of cells, wherein the template and the description of the symbol are compared based on the server being programmed to:
for each of the local features of the reference description which mandates a presence or an absence of a specified local feature and for each of the cells in the second grid of cells, verify the presence or the absence in the description of the symbol.

### Claim 19 (depends on 11)

The system of claim 11, wherein the threshold is determined based on an appropriate presence or absence of a selected local feature in a selected cell of a bounding box, wherein the threshold corresponds to a number or percentage of cells meeting or not meeting a criterion.

### Claim 20 (depends on 11)

The system of claim 11, wherein for each local feature of the reference description and for each cell, where the description of the symbol mandates a presence or an absence of that local feature, a check for the presence or the absence of this respective feature in the description of the symbol is performed.
