---
key: mechanic/phone-camera--family-objects
type: mechanic
id: phone-camera--family-objects
lang: en
title: 'Objects, signs and relationships'
summary: >-
The camera recognizes supported object classes. Seeing AI has a dedicated
currency mode; it does not identify every object or material.
updatedAt: '2026-10-22'
status: active
url: 'https://gamemechanics.pro/en/knowledge/mechanic/phone-camera--family-objects/'
jsonUrl: >-
https://gamemechanics.pro/api/v1/knowledge/en/mechanic/phone-camera--family-objects.json
markdownUrl: >-
https://gamemechanics.pro/content/knowledge/en/mechanic/phone-camera--family-objects.md
aliases: []
tags:
- Phone camera interactions
- Mechanics catalog
sourceIds:
- source-c571f972753e630a
- source-334fc4874b474465
- source-5cd7e7e00e5de5a7
sources:
- id: source-c571f972753e630a
title: MediaPipe Object Detector
url: >-
https://developers.google.com/edge/mediapipe/solutions/vision/object_detector
verifiedAt: null
- id: source-334fc4874b474465
title: ARCore Augmented Images
url: 'https://developers.google.com/ar/develop/augmented-images'
verifiedAt: null
- id: source-5cd7e7e00e5de5a7
title: Seeing AI
url: 'https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4'
verifiedAt: null
relations: []
placements:
- catalogId: phone-camera
id: family-objects
title: Phone camera interactions
url: 'https://gamemechanics.pro/en/mechanics/phone-camera/#family-objects'
categoryIds:
- section-1
supersededBy: []
attributes:
preview:
updatedAt: '2026-10-22'
title: 'Objects, signs and relationships'
description: >-
The camera recognizes supported object classes. Seeing AI has a dedicated
currency mode; it does not identify every object or material.
image:
src: images/mechanics/input-seeing-ai-3.webp
width: 720
height: 1280
crop:
x: 90
'y': 280
width: 540
height: 940
game: Seeing AI
sourceUrl: 'https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4'
originalUrl: >-
https://is1-ssl.mzstatic.com/image/thumb/PurpleSource221/v4/ee/e4/23/eee42313-d4c2-2728-6052-cda58984e9e4/dc602422-f4bb-4b6a-a7cb-e8a578e7b5d0_iPhone8_Currency-en.jpg/720x1560bb.jpg
credit: Microsoft Corporation
rights: >-
Imagery © Microsoft Corporation. Developer-distributed screenshot or
frame; all rights reserved. Excluded from MIT and CC BY 4.0.
caption: 'Seeing AI: a dedicated currency recognition mode'
alt: 'Seeing AI: a dedicated currency recognition mode'
markers:
- x: 50
'y': 55
label: A banknote is in view in Currency mode
tips:
- Limit supported classes and allow confirmation of uncertain results.
examples:
- title: Seeing AI
url: 'https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4'
endsAt: null
provenance: >-
Original editorial design catalog consolidated from project discussions on
2026-10-20. Complete discussion item lists and contextual limitations are
preserved; linked primary sources support specific techniques, not the entire
classification. English translation was prepared with machine assistance and
editorial review.
license: CC-BY-4.0
codeLicense: MIT
attribution: gamemechanics.pro contributors
catalogKey: catalog/phone-camera
---
# Objects, signs and relationships
id: phone-camera--family-objects
type: mechanic
key: mechanic/phone-camera--family-objects
lang: en
status: active
url: https://gamemechanics.pro/en/knowledge/mechanic/phone-camera--family-objects/
The camera recognizes supported object classes. Seeing AI has a dedicated currency mode; it does not identify every object or material.
## At a glance
[Seeing AI](https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4) · Imagery © Microsoft Corporation. Developer-distributed screenshot or frame; all rights reserved. Excluded from MIT and CC BY 4.0.
1. A banknote is in view in Currency mode
- Limit supported classes and allow confirmation of uncertain results.
- [Seeing AI](https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4)
## How it works
Real things become input to the rules. The finished detector recognizes its classes. Recognizing a specific toy, material or condition usually requires a separate model and testing on real scenes.
## Variants
### Variants and applications
- Item category. Action: Show an object of the desired class; the game accepts it as an answer. Application: Scavenger hunt, dictionary, resource search. Technologies: Recognition or machine learning model.
- Specific instance. Action: Show a pre-registered item or its visual label. Application: Personal artifact, level key, collectible toy. Technologies: Recognition or machine learning model; Own algorithm.
- Counting objects. Action: Display a specified number of visible items of one or more classes. Application: Arithmetic, order picking, visual inventory. Technologies: Recognition or machine learning model.
- Geometric shape. Action: Find a circle, triangle, symmetrical or elongated object. Application: Teaching geometry, collecting parts, visual classification. Technologies: Image analysis.
- Material or texture. Action: Show a surface from a limited trained set. Application: Texture catalog, artistic search, conditional crafting resources. Technologies: Recognition or machine learning model; Own algorithm.
- Visual condition. Action: Translate a familiar object between distinguishable states. Application: Open box as a switch, model assembly, checking a task step. Technologies: Recognition or machine learning model; Own algorithm.
- Spatial relationship in the frame. Action: Place one object above, inside a contour or next to another. Application: Visual recipes, teaching prepositions, compositional riddles. Technologies: Image analysis; Recognition or machine learning model.
- Comparison with a sample. Action: Find a thing or image similar to the standard according to the selected criterion. Application: Matching a pair, searching for differences, visual memory. Technologies: Image analysis; Recognition or machine learning model.
## Context and limits
Games, learning, creativity and interactive applications. Author's systematization of game rules based on proven technical capabilities. Examples are application ideas and not statements of released products.
## Connected materials
## Sources and provenance
Original editorial design catalog consolidated from project discussions on 2026-10-20. Complete discussion item lists and contextual limitations are preserved; linked primary sources support specific techniques, not the entire classification. English translation was prepared with machine assistance and editorial review.
- [MediaPipe Object Detector](https://developers.google.com/edge/mediapipe/solutions/vision/object_detector) (id: source-c571f972753e630a)
- [ARCore Augmented Images](https://developers.google.com/ar/develop/augmented-images) (id: source-334fc4874b474465)
- [Seeing AI](https://apps.apple.com/us/app/seeing-ai/id999062298?uo=4) (id: source-5cd7e7e00e5de5a7)
CC-BY-4.0 · gamemechanics.pro contributors