Pretrained computer vision classifier

Identify check number clarity with one API call.

A pretrained check number clarity classifier that sorts an image into one of 8 categories — what the clarity level of the check number is. Use the check number clarity API immediately, no training required, then adapt it to your own data when you need more.

Use this classifier Try with your image

Pretrained · Nyckel-trained 8 labels out of the box Image input

nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke

Blurred 0.92

Clear 0.05

Try the check number clarity classifier

Drop in a photo and get the prediction back. No signup, no setup.

What this check number clarity classifier recognizes

A sample of the 8 labels this pretrained classifier chooses between.

Blurred

Clear

Faded

Illegible

Partially Visible

Slightly Clear

Totally Clear

Very Clear

Need a label that isn't here? Clone the classifier into your Nyckel console and edit the label set to fit your data.

Call the check number clarity API

Get your own copy of this classifier behind your own endpoint — callable from any HTTP client:

API quick start

curl -X POST "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"data": "https://example.com/photo.jpg"}'

import requests

response = requests.post(
    "https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke",
    headers={"Authorization": "Bearer YOUR_ACCESS_TOKEN"},
    json={"data": "https://example.com/photo.jpg"},
)
print(response.json())

const response = await fetch("https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_ACCESS_TOKEN",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ data: "https://example.com/photo.jpg" }),
});
console.log(await response.json());

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, 'https://www.nyckel.com/v1/functions/YOUR_FUNCTION_ID/invoke');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, '{"data": "https://example.com/photo.jpg"}');

$headers = array();
$headers[] = 'Authorization: Bearer YOUR_ACCESS_TOKEN';
$headers[] = 'Content-Type: application/json';
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
curl_close($ch);
echo $result;

Create free account to get your live API key Clone this function to get a live API key

How to invoke a function →

Example response

{
  "labelName": "Blurred",
  "labelId": "label_...",
  "confidence": 0.92
}

API documentation Authentication Pricing Get your endpoint

Under the hood

Model type

Nyckel-trained

Trained on a Nyckel-curated dataset covering 8 check number clarity categories, served on Nyckel's own infrastructure — your image stays on Nyckel.

Input

Image

Send an image URL or file to the invoke endpoint; the response is a label with a confidence score.

Make it yours

Adaptable

Clone it, then correct predictions and add your own samples in the console — Nyckel retrains automatically, turning this into a custom model tuned to your data.

More than a demo: this page is one of thousands of pretrained functions on Nyckel, an ML classification platform. You can invoke classifiers by API, review predictions, correct labels, collect samples from production traffic, and promote any pretrained function to a private custom model — without changing your integration.

Where teams use check number clarity classification

Invoice Verification

This function can be employed by accounting departments to automatically verify the clarity of invoice images scanned or emailed for processing. By ensuring that the numbers are clear, organizations can reduce errors in payments and enhance their auditing processes.

Receipt Validation

Retailers can use this functionality to check the clarity of scanned receipts during returns or exchanges. By accurately identifying if the transaction details are legible, it can streamline the customer service processes and improve customer satisfaction.

Document Compliance

Law firms can implement the clarity checking function on client documents to ensure that all crucial numeric details are discernible. This can help avoid legal complications that arise from misinterpreted data, reinforcing the firm’s commitment to accuracy.

Medical Billing Accuracy

Healthcare providers can use this identifier to assess the clarity of numeric information on billing statements and insurance forms. By ensuring that numbers are clear, the chances of billing errors can decrease, thus lowering the rate of claim denials and disputes.

Academic Record Processing

Educational institutions can integrate this function to check the clarity of scanned student transcripts and report cards. Ensuring the legibility of grades and other numeric data can facilitate smoother enrollment processes and enhance record-keeping accuracy.

Financial Report Review

Companies can apply this function for internal auditing to verify that numeric data within scanned financial reports is clear and readable. By identifying unclear figures, businesses can maintain more accurate financial records and minimize risks associated with data misinterpretation.

E-commerce Transaction Confirmation

Online retailers can utilize this function to validate the clarity of transaction confirmation documents or digital receipts sent to customers. By ensuring that all numbers are legible, the retailer can build trust with customers and reduce inquiries related to transaction details.

Common questions

What's the difference between a zero-shot and a Nyckel-trained classifier?

A zero-shot classifier uses a large foundation model's general knowledge to pick between your labels — no task-specific training, so new or edited labels work immediately. A Nyckel-trained classifier has been trained on labeled examples and runs on Nyckel's own infrastructure, which typically makes it faster, cheaper per call, and more accurate on data that resembles its training set. The "Under the hood" section on this page shows which kind this classifier is, and any classifier can be adapted into a trained one by adding your own examples.

How do I know whether this will work for my application?

Honestly: we can't know in advance — it depends on your data stream and how closely it resembles what this classifier has seen. The reliable way to find out is to measure it on your own data: start invoking the classifier with real traffic, or upload and annotate a set of images in the console — make sure they look like your production data, not idealized examples. Nyckel's evaluation metrics then show you exactly how it performs on that data before you rely on it.

What happens when it makes a mistake?

No classifier is perfect, so Nyckel is built around the correction loop: invokes can be captured for review, you confirm or correct predictions in the console, and corrections become training data. Over time the model adapts to your data distribution — accuracy on your traffic improves with use rather than staying fixed.

Do I need training data to get started?

No. This check number clarity classifier works out of the box — clone it into your console and you'll have your own API endpoint in under a minute. Training data only enters the picture when you want to adapt it: your corrected predictions and uploaded samples improve the model, and you can also edit the label set to match your needs.

What does it cost to try?

Trying the classifier on this page is free with no signup. Cloning it requires a free account, and the free tier covers your first API calls each month — see nyckel.com/pricing for current limits and paid tiers.

Ready to classify check number clarity at scale?

Add this pretrained classifier to your Nyckel console — you'll get a live API endpoint in under a minute, and a path to a custom model when you need one.

Use this classifier Read the docs