Input data and information sources
Line cameras can also capture workers. Inspection images and defect data reveal design and manufacturing progress and can be trade secrets.
Visual and acoustic quality inspection
Also known as: AI-based visual inspection
Cameras or microphones capture components and products on the production line; a model checks defects, completeness and correct variants.
Understand the use case
What defines this use case?
The model learns from recordings labelled by specialists as good or defective, then checks each item at line speed. BMW states that it uses this in its plants, including driving sound analysis at Dingolfing; Audi has trialled sheet-metal crack detection.
This page describes a typical system design. Actual data flows and permissions depend on your implementation.
- System design
- Analysis and processing
- Ability to act
- Action permissions depend on integration
- Fields of use
- automotive industry
- Also known as
- automated visual inspection, machine vision inspection, visual inspection
How it works, step by step
System design and data flows
Input data
Cameras, microphones or other sensors record each item on the line.
Some stations analyse image and audio together. Line cameras can also capture workers.
Processing
A model compares the recording with patterns learned from labelled examples.
The model compares a product's visual or acoustic signals with learned or specified quality characteristics. This produces a classification or flagged anomalies. Whether a product is rejected is determined by subsequent inspection or equipment control, according to its rules.
Results
The result is “acceptable” or identifies defects, missing parts or an incorrect variant.
The result describes the defined model task. A match, category or forecast acquires its professional significance only in conjunction with the underlying data and intended use.
Use and impact
Defective parts are reinspected, reworked or rejected; others go to assembly or customers.
Integration determines whether the result is simply displayed, adopted after approval or written directly into a business application. These variants differ in their data flows and permissions.
Explore the system design: Select a component to see its task, incoming and outgoing data, and role in the use case. The guided walkthrough explains each phase. Then use Yes, Uncertain and No to represent your specific system variant.
5 review first12 clarify7 baseline threats
- Present
- Depends on your system
- Absent
- Review first
- To clarify
How to use the model
The diagram shows the typical architecture. Select a component to see what happens there and adapt its features to your system. Enable “Analysis guidance” to see which threats need reviewing for this architecture. The page's checklist continues to describe the typical case.
Changes from the typical case
None yet. Each change will appear here.
Where most threats arise
- 4 clarify
- 3 review first
- 3 clarify
- 3 clarify
In this system design: 5 to review first, 12 to clarify, 7 baseline threats.
Architecture as a list
External access: Depends on your system
To clarify
Input: Part of every AI system
To clarify
Baseline for every AI system
AI model: Part of every AI system
Review first
- Model Drift & Degradation Review priority
Provider service: Depends on your system
To clarify
Training and feedback: Present
Review first
Result: Part of every AI system
Baseline for every AI system
Business application or equipment: Depends on your system
To clarify
person: Part of every AI system
Review first
- Overreliance Review priority
Unapproved AI services: Depends on your system
To clarify
Supply chain and technical foundations: 5 baseline threats applying to every AI system
Baseline for every AI system
How it differs from similar use cases
Monitors machine and equipment condition rather than manufactured parts
Intelligent video analytics in public spaces
Analyses camera images of events in public spaces
AI-assisted medical image analysis
Analyses patients' X-rays, CT or MRI images
Data and information
Processing and operating environment
Alongside in-house development, suppliers offer systems with pretrained models.
Storage and further use
Models learn from the organisation's own components; Audi developed its system itself. Staff reinspection findings can feed back as new training examples.
Results and data sharing
Depending on integration, it blocks an item in manufacturing control or only flags it for reinspection. A system controlling a diverter or gripper to reject defective parts directly acts on the line.
Using a provider does not automatically determine where processing takes place. Storage location, subcontractors, deletion periods and use for training must be checked for the specific deployment.
Assess risks and determine measures
From understanding the system to analysing risks
- Define the system boundary
Record data, participants, interfaces and permissions. Resolve uncertain characteristics in the model.
- Investigate threats
Relate review candidates to actual data flows: what could happen, and who would be affected?
- Assess risk
Assess impacts and likelihood in the deployment context. The number of review candidates is not a risk score.
- Provide evidence of measures
Select appropriate controls, assign responsibilities and define effectiveness checks. Document residual risks and approvals.
Key threats in the application context
- 3 particularly important
- 2 typical
- 12 depending on the system
- 7 additional threats for every AI system
A total of 24 threats from the threat catalogue may be relevant to this use case.
Priority review points
A new variant, supplier or lighting changes recordings without model retraining. The inspection then passes defects or rejects good parts.
Targeted Poisoning / Label Poisoning
Someone with training data access deliberately labels certain defect images as acceptable. The model then passes that defect, sending parts unnoticed into assembly or to customers.
Relying on the camera to find every defect can lead to dropping manual sampling. Defect types the model has never seen remain undetected.
2 further review candidates in the typical design
Other relevant threats
Your own training or operational feedback can introduce manipulated data into training datasets.
Listed because of this characteristic
- Learns from your own data
Training data or an adopted base model can introduce hidden triggers for misbehaviour.
Listed because of this characteristic
- Learns from your own data
Up to 12 further threats may apply, depending on your system design. Nine threats need to be reviewed for every AI system. Two of these are particularly important here and are therefore listed above.
System features and open questions
Each Yes adds further threats to your checklist, up to 12 in total. If you cannot yet answer a question, include its threats in your review.
- Added by this Yes
How your system is built
- Processes confidential data3 threats
- Processes personal data2 threats
- Controls physical processes2 threats
- Processes text, images and speech together2 threats
- Changes data or triggers processes1 threat
How you operate the system
- Available to people outside the organisation5 threats
- Accepts queries directly through an interface4 threats
- Accessible over a network3 threats
- Incurs costs with each query1 threat
- Passes content to services outside your environment1 threat
- Shares computing resources with other customers or applications1 threat
- Used alongside unapproved AI services1 threat
How your system is built
Can the system change things itself, such as storing data, sending messages, initiating transactions or granting permissions?
Depending on integration, it blocks an item in manufacturing control or only flags it for reinspection.
If yes, add
Does the system process information about identifiable people, including in inputs, outputs or logs?
Line cameras can also capture workers.
If yes, add
Does the system process confidential information such as trade secrets, health or financial data?
Inspection images and defect data reveal design and manufacturing progress and can be trade secrets.
If yes, add
Does the system directly move or control something physical, such as motors, valves, vehicles or temperatures?
A system controlling a diverter or gripper to reject defective parts directly acts on the line.
If yes, add
Does the system process several input types together, such as text with images or speech?
Some stations analyse image and audio together.
If yes, add
How you operate the system
These questions arise for almost every AI system.
Can people or programs query the model directly, for example through an interface?
If yes, add
Is the system accessible over a network or dependent on network services?
If yes, add
Do you pay per query or unit of computing time, so costs increase with use?
If yes, add
Can content leave your environment, for example to a cloud provider, web search or email?
If yes, add
Does the system share servers or computing resources with other customers or applications?
If yes, add
Can people outside your organisation use the system, including without login?
If yes, add
Do staff also use AI services for this task that your organisation has not approved?
If yes, add
Controls and implementation
Measures for the priority review areas are expanded. Each linked measure explains how to implement it.
Review priorityModel Drift & Degradation3 measures
Review priorityTargeted Poisoning / Label Poisoning3 measures
Review priorityOverreliance3 measures
Training Data Poisoning2 measures
Backdoor ML Model2 measures
Controls for the remaining threats are available on their pages in the threat catalogue.
AI Act provisions
Applies to every AI system
Art. 4: AI literacy
Applies if staff or appointed representatives operate or use AI systems.
Applies since 2 February 2025.
Obligations and details for Art. 4: AI literacy
- Who bears the obligations
- Provider, Deployer, Product manufacturer, Provider of a general-purpose AI model
Detailed obligations
Generally does not apply
Art. 6 para. 1, Annex I Section A: Safety component of an assessed product
An end-of-line inspection that only reports defects is generally not a machine safety component. This may differ if it intervenes in machine control.
Obligations and details for Art. 6 para. 1, Annex I Section A: Safety component of an assessed product
- The general condition is
- Applies if the system is itself a product or a safety component of a product requiring third-party assessment under Annex I legislation, such as machinery, lifts, medical devices or toys.
- Exception
- Systems improving only operation, performance or comfort without a safety role are not safety components under Article 6(1a)–(1c).
- Who bears the obligations
- Provider, Deployer, Product manufacturer
Detailed obligations
Classify your system with the quick checker All obligations in the obligations compass
Cross-cutting threats
Review these threats for every AI system, whatever its purpose.
Atypical system features
View 17 further questions
If any of these features does apply to your system, add the listed threats.
Does the system generate its own text, such as answers, drafts or summaries?
If yes, add
Does the system generate or edit images, sounds, voices or videos?
If yes, add
Does the system create new content from open-ended requests that people read, see or hear directly? Translation, reading aloud and transcription do not count.
If yes, add
Can users give the system natural language tasks that it then performs?
The inspection system analyses recordings and does not accept natural language instructions.
If yes, add
Does the system search its own collection of documents or records for relevant content?
If yes, add
Does the system formulate answers from retrieved documents?
If yes, add
Does the system use a knowledge graph storing concepts and their relationships?
If yes, add
Does the system remember content from earlier conversations or tasks and reuse it later?
If yes, add
Does the system call other programs, interfaces or search services itself, even if only to read?
If yes, add
Does the system determine its next steps itself based on earlier results?
If yes, add
Does the system delegate tasks to other AI agents or incorporate their results?
If yes, add
Is the system connected to tools or data sources through the Model Context Protocol (MCP)?
If yes, add
Does the system process content outsiders may have written or altered, such as emails, uploads or websites?
Recordings come from the organisation's own line cameras and microphones.
If yes, add
Do documents from several customers, departments or permission groups share one search store?
If yes, add
Does the system generate code, scripts or database queries for further use?
If yes, add
Does the system execute programs, scripts or commands itself?
If yes, add
Is the system intended to maximise a specified metric, such as revenue, utilisation or clicks?
If yes, add
Sources
- Report of a deployment
BMW Group, AIQX: Artificial intelligence in quality inspection, 27 November 2023 According to the deployer
BMW describes AIQX at its plants, including sound inspection at Dingolfing.
- Report of a deployment
automobil-produktion.de, Pressed parts: Audi uses machine learning to hunt cracks, 15 October 2018
The report describes a pilot at Ingolstadt's press shop.
- Statistics
Federal Statistical Office, Enterprises using AI technologies, 2025
Among AI-using companies, 17 per cent use image recognition.
- Other source
Plattform Lernende Systeme, AI map
The AI map treats quality control as a distinct application field.
Related use cases
Also in the field of Manufacturing, retail and logistics
- Predictive maintenanceThe system detects impending machine or equipment failure from sensor and operational data so maintenance can be planned in time.
- Sales and demand forecastingRetailers use a model to predict how much of each item each store will sell, then turn those forecasts into suggested orders or completed orders.
Updated: 30 September 2026. Review checklist rules version 0.3.2, threat catalogue version 2026.10.24.2. How these pages are structured