> For the complete documentation index, see [llms.txt](https://docs.saas.haut.ai/haut.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.saas.haut.ai/haut.ai/haut.ai-features/algorithms/face-metrics-2-0/quality-algorithm.md).

# Quality Algorithm

How Haut.AI measures image quality, why it affects the accuracy of analysis, and how to tell whether an image is good enough to analyze.

## FAQ

### How do we measure image quality? What is image quality?

Image quality is assessed by evaluating various factors that affect the clarity, visibility, and usefulness of an image, particularly for tasks like skin analysis. Key aspects include:

* **Lighting conditions**: Proper illumination ensures that the subject is well-lit, avoiding shadows or overly bright areas that can distort details.
* **Face visibility**: Ensuring the face is clearly visible, fully framed, and not obscured by objects or partial angles.
* **Image resolution**: High resolution allows for capturing fine details, which is critical for accurate analysis.
* **Noise levels**: Reducing digital noise (random speckles or grain) helps maintain the image's clarity and sharpness.

***

### How does image quality influence skin analysis quality?

Image quality directly affects the accuracy and reliability of skin analysis. Poor-quality images can result in flawed or incorrect results. Here are some key examples:

* **Face visibility**: If the face is not fully visible or is obscured, the analysis cannot be performed, as critical areas of the skin may not be detected.
* **Lighting conditions**: Insufficient lighting or shadows can cause important skin features (like blemishes or texture) to be either overexposed or lost in darkness, leading to inaccurate analysis.
* **Image resolution**: Low-resolution images can blur details, making it difficult to assess skin texture, pores, or fine lines accurately.
* **Noise**: High noise levels can distort the image, reducing the effectiveness of machine learning models trained on clean data and leading to incorrect assessments.

Good image quality ensures the skin analysis is precise and trustworthy, minimizing errors and improving user experience.

***

### How do we understand if an image is of good quality?

We use a custom algorithm that evaluates image quality based on specific criteria tailored to our needs, such as lighting, resolution, and face visibility. This algorithm helps ensure that only high-quality images are accepted for skin analysis. It is designed to filter out photos that do not meet the required standards, allowing for more accurate and reliable results.

**Why not turn off the quality algorithm?**

Turning off the quality algorithm is highly discouraged, as it serves as a safeguard for ensuring reliable results. Disabling it could lead to several issues:

* **Bad quality images**: Without the algorithm, low-resolution, poorly lit, or noisy images might be used.
* **Wrong skin analysis results**: Poor image quality can lead to inaccurate assessments, undermining the trustworthiness of the analysis.
* **Bad user experience**: Users may receive inconsistent or incorrect feedback, damaging their confidence in the system.
* **Lack of traceability**: The quality algorithm also provides feedback on why an image was rejected or failed, which helps identify problems and improve the user experience.

Keeping the quality algorithm active ensures that only images suitable for accurate skin analysis are processed, maintaining both performance and user satisfaction.

***

{% hint style="warning" %}
Not a Haut.AI client yet?
{% endhint %}

<a href="https://haut.ai/book-a-demo?utm_source=referral&#x26;utm_medium=saas_docs&#x26;utm_campaign=Docs_SaaS_HautAI" class="button primary" data-icon="user-vneck">Book a demo</a> <a href="https://haut.ai/product/ai-skin-analysis?utm_source=referral&#x26;utm_medium=saas_docs&#x26;utm_campaign=Docs_SaaS_HautAI" class="button secondary" data-icon="external-link">Platform overview on haut.ai</a>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.saas.haut.ai/haut.ai/haut.ai-features/algorithms/face-metrics-2-0/quality-algorithm.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.