# US 12,183,147 B2 · Systems, methods and devices for monitoring betting activities

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

- Number: US 12,183,147 B2
- Document ID: US12183147B2
- Status: Granted
- Kind: B2
- Application number: 18/242,347
- Filed: 2023-09-05
- Published: 2023-12-28
- Granted: 2024-12-31
- Earliest claimed: 2015-05-29
- Assignees: Arb Labs Inc.
- Applicants: Arb Labs Inc.
- Inventors: Adrian Bulzacki; Vlad Cazan; Muhammad Talal Ibrahim
- Web page: https://patentgrep.com/patent/US12183147B2

## CPC

- G07F 17/3211: {Display means}
- A63F 3/00157: {Casino or betting games (horse races A63F3/00082)}
- G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/24323: {Tree-organised classifiers}
- G06F 18/25: Fusion techniques
- G06F 18/251: {of input or preprocessed data}
- G06F 18/253: {of extracted features}
- G06T 7/194: involving foreground-background segmentation
- G06T 7/50: Depth or shape recovery
- G06T 7/60: Analysis of geometric attributes
- G06V 10/141: Control of illumination
- 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 10/462: {Salient features, e.g. scale invariant feature transforms [SIFT]}
- G06V 10/50: by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V 10/56: relating to colour
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G07F 17/322: {Casino tables, e.g. tables having integrated screens, chip detection means}
- G07F 17/3227: {Configuring a gaming machine, e.g. downloading personal settings, selecting working parameters}
- G07F 17/3237: {about the players, e.g. profiling, responsible gaming, strategy/behavior of players, location of players}
- G07F 17/3239: {Tracking of individual players}
- G07F 17/3241: {Security aspects of a gaming system, e.g. detecting cheating, device integrity, surveillance (computer security G06F21/00)}
- G07F 17/3288: {Betting, e.g. on live events, bookmaking}
- A63F 2003/00164: {Casino tables}
- G06F 2218/00: Aspects of pattern recognition specially adapted for signal processing
- G06F 2218/12: Classification; Matching
- G06V 20/64: Three-dimensional [3D] objects
- G07F: COIN-FREED OR LIKE APPARATUS (coin sorting G07D3/00; coin testing G07D5/00; {handling coins or paper currencies apart from payment activated apparatus G07D; payment architectures, schemes or protocols G06Q20/00})
- A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A platform, device and process for capturing images of the surface of a gaming table and determining the quantity, identity, and arrangement of chips bet at a gaming table. Image data is captured corresponding to the one or more chips positioned in at least one betting area on a gaming surface of the respective gaming table and the data is processed to filter out the background, establish a two dimensional grid of points of interests and corresponding histograms for classifying the one or more chips through identifying a dominant classification of each row in the grid of points of interests.

## Claims

### Claim 1

A machine vision bet recognition device for visually capturing chip placement activities comprising:
a camera or sensor capturing image data corresponding to one or more chips positioned in at least one chip placement area captured across a plurality of channels including at least a depth information channel, a red channel, a green channel, and a blue channel; and a processor configured to:
process the captured image data by generating one or more representative histograms for each chip of the one or more chips for distinguishing different chip types, at least one of the one or more representative histograms generated from at least two channels of the plurality of channels including the depth information channel and at least one of the red channel, the green channel, and the blue channel;
for each chip of the one or more chips, assign a chip type to the chip by identifying a most similar corresponding reference histogram to the one or more representative histograms from a set of reference histograms; and
determine a total chip value or a change in the total chip value of the one or more chips in the at least one chip placement area based on the assigned chip types.

### Claim 2 (depends on 1)

The device of claim 1, wherein the total chip value or the change in the total chip value is used to determine a number of bets placed in the at least one chip placement area.

### Claim 3 (depends on 2)

The device of claim 2, wherein the number of bets placed in the at least one chip placement area is combined with a house edge factor to determine a theoretical win/loss rate.

### Claim 4 (depends on 1)

The device of claim 1, wherein the total chip value or the change in the total chip value is used to determine a number of gaming rounds participated in by a player corresponding to the at least one chip placement area.

### Claim 5 (depends on 4)

The device of claim 4, wherein the number of gaming rounds is combined with a house edge factor to determine a theoretical win/loss rate.

### Claim 6 (depends on 1)

The device of claim 1, wherein the total chip value or the change in the total chip value is associated with timestamps and used for pattern recognition.

### Claim 7 (depends on 6)

The device of claim 6, wherein the total chip value or the change in the total chip value and the timestamps are utilized for bet pattern tracking, and the timestamps used to estimate patterns of malicious behavior trends over a period of time.

### Claim 8 (depends on 6)

The device of claim 6, wherein the total chip value or the change in the total chip value and the timestamps are associated with a dealer user profile or a table profile and used to generate dealer or table metrics.

### Claim 9 (depends on 6)

The device of claim 6, wherein the total chip value and the timestamps are associated with a player user profile and used to generate player metrics.

### Claim 10 (depends on 9)

The device of claim 9, wherein the player metrics are processed for automatically provisioning player rewards or notifications informing a player corresponding to the player user profile that their betting was not efficient or sub-optimal based on computer analysis.

### Claim 11

A method for machine vision bet recognition by visually capturing chip placement activities comprising:
capturing, using a camera or sensor, image data corresponding to one or more chips positioned in at least one chip placement area captured across a plurality of channels including at least a depth information channel, a red channel, a green channel, and a blue channel;
processing the captured image data by generating one or more representative histograms for each chip of the one or more chips for distinguishing different chip types, at least one of the one or more representative histograms generated from at least two channels of the plurality of channels including the depth information channel and at least one of the red channel, the green channel, and the blue channel;
for each chip of the one or more chips, assigning a chip type to the chip by identifying a most similar corresponding reference histogram to the one or more representative histograms from a set of reference histograms; and
determining a total chip value or a change in the total chip value of the one or more chips in the at least chip placement area based on the assigned chip types.

### Claim 12 (depends on 11)

The method of claim 11, wherein the total chip value or the change in the total chip value is used to determine a number of bets placed in the at least one chip placement area.

### Claim 13 (depends on 12)

The method of claim 12, wherein the number of bets placed in the at least one chip placement area or a number of gaming rounds is combined with a house edge factor to determine a theoretical win/loss rate.

### Claim 14 (depends on 11)

The method of claim 11, wherein the total chip value or the change in the total chip value is used to determine a number of gaming rounds participated in by a player corresponding to the at least one chip placement area.

### Claim 15 (depends on 11)

The method of claim 11, further comprising:
calibrating the machine vision bet recognition by capturing a set of reference images for generating the set of reference histograms for the different chip types each identified using a plurality of images captured across a duration of time or in a plurality of gameplay or lighting settings.

### Claim 16 (depends on 15)

The method of claim 15, wherein the calibrating includes a machine-learning training phase that outputs the set of reference histograms from the set of reference images.

### Claim 17 (depends on 16)

The method of claim 16, wherein the machine-learning training phase includes training a machine learning classifier to distinguish between each chip type of the different chip types.

### Claim 18 (depends on 17)

The method of claim 17, wherein the captured image data is used to generate a waveform input that is processed through the trained machine learning classifier to determine a best match for identifying the most similar corresponding reference histogram.

### Claim 19 (depends on 18)

The method of claim 18, wherein the trained machine learning classifier is a neural network.

### Claim 20

A non-transitory computer readable medium storing machine interpretable instructions, which when executed by a processor, perform a machine vision bet recognition method, the method comprising:
capturing, using a camera or sensor, image data corresponding to one or more chips positioned in at least one chip placement area captured across a plurality of channels including at least a depth information channel, a red channel, a green channel, and a blue channel;
processing the captured image data by generating one or more representative histograms for each chip of the one or more chips for distinguishing different chip types, at least one of the one or more representative histograms generated from at least two channels of the plurality of channels including the depth information channel and at least one of the red channel, the green channel, and the blue channel;
for each chip of the one or more chips, assigning a chip type to the chip by identifying a most similar corresponding reference histogram to the one or more representative histograms from a set of reference histograms; and
determining a total chip value or a change in the total chip value of the one or more chips in the at least one chip placement area based on the assigned chip types.