Fields captured by our OCR engine specialized in nutritional information

The Koncile OCR solution Capture the essential information on nutritional values, facilitating the work of nutritionists, food manufacturers and health professionals. It allows digitize and structure The nutritional data onwards image files or PDFs.

You can not only extract automatically thanks to intelligent document processing, key information such as calories, macronutrients, allergens, ingredients and energy values, but also analyze and verify them by confronting them with databases Or specific criteria.

	Name	Type	Example	Guideline
	Validité	Text	Oui	Vérifie que le RIB est bien constitué des éléments suivants : - Code banque (5 chiffres) - Code guichet (5 chiffres) - Numéro de compte (11 caractères alphanumériques) - Clé RIB (2 chiffres) Si les RIB est bien constitué de ces éléments, choisis la valeur "Oui". Sinon choisis la valeur "Non".

Calories (kcal)

tableau Number 250 Identify the units “kcal” or “kJ”. Verify that it is a value per 100g or per serving.

Proteins (g)

tableau Number 30

Carbohydrates (g)

tableau Number 50

ingredients

tableau Text wheat flour, sugar, skim milk, eggs, sunflower oil, salt Look for the section that contains “Ingredients.” Separate ingredients by “,” and structure them in the form of a list. Remove any brackets or annotations that could alter the analysis (e.g.: “natural flavor (vanilla)” → “natural flavor, vanilla”).

Allergens

tableau Text gluten, milk, eggs Detect the section containing the allergens (often introduced by “Contains” or “May contain”). Convert allergens into a JSON list to facilitate automatic search. Standardize terms to avoid typographical variations (e.g., “egg” → “egg”).

Add any extraction field

See full template

Edit AI instructions

An OCR Solution Built for Nutritional Data Capture

Automatically extract key nutritional information

Calories, macronutrients, allergens, ingredients, energy values, and more directly from food labels.

From Nutritional Labels to a Structured Database

Simplify nutritional data management by converting food packaging into structured, machine-readable information.

Multi-Format Processing

Easily process and standardize nutritional information from various formats, including images and PDFs.

Nutritional Data Parsing via API

Build a complete, searchable nutritional database integrated into your application and accessible via API to automate food composition analysis.

Beyond OCR: Validation and verification of extracted fields

Is the nutritional information accurate? Are the calorie counts correct? Are allergens clearly listed? Do the ingredients comply with regulations? Optimize your food data management with intelligent OCR.

The OCR API to automate the management of nutritional values

‍

status

string

Document status, which can be DONE, DUPLICATE, or IN PROGRESS.

document_id

integar

Unique number assigned to each invoice

general_fields

objects

General fields that appear only once in each extracted document. Returned in the format: {field name: extracted value}

line_fields

objects

Repeated fields extracted in bulk for each line or table. Returned in the format: {field name: extracted value}

status

string

Statut du document qui peut être DONE, DUPLICATE, IN PROGRESS.

document_id

integer

Numéro unique attribué pour chaque document

general_fields

objects

Champs généraux apparaissant une seule fois dans chaque document extrait. Retour au format : {nom du champ: valeur extraite}

line_fields

objects

Champs répétés extraits en bloc pour chaque ligne ou chaque tableau. Retour au format : {nom du champ: valeur extraite}

Full Documentation

I claim my API key

Request

curl api.koncile.ai/tasks/{task_id}/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY"

response = requests.get(f"{api_url}/tasks/{task_id}/",
headers={"accept": "application/json", "Authorization":{"Bearer{api_key}"})

Response

{
"status": DONE | DUPLICATE | IN PROGRESS | FAILED,
"document_id": ID,
"document_name": "name",
"status_message": "",
	"General_fields":
		{
		"Date" : {"value": "05/08/2022", "confidence_score": 0.99},
		"Price" : {"value": "$23", "confidence_score": 0.98}
		}
	,
	"Line_fields":
		{
		"Date" : [{"value": "05/08", "confidence_score": 0.97}, {"value" : "05/08", "confidence_score": 0.98}, ],
		"Price" : [{"value": "$23", "confidence_score": 0.98}, {"value": "$12", "confidence_score": 0.97}],
		}
}

Any question?

How does OCR extract nutritional information?

OCR analyzes nutritional value using computer vision algorithms to detect and read characters. With natural language understanding (NLP), OCR can identify critical information. This process ensures accurate extraction of structured and unstructured data from the document.

‍

Can I extract specific information from a nutritional value?

Yes, you can extract specific information about nutritional value, such as calories, fats, sugars, ingredients, or allergens. OCR can be set up to extract this data based on the sections or formats you are dealing with.

‍

In what format should I upload nutrition facts for OCR analysis?

You can upload your nutrition facts in PDF, PNG, or JPEG format. These formats are compatible with our OCR technology, allowing accurate extraction of the information contained in the document. Consult the documenting for more details on accepted formats and the upload process.

‍

Can OCR process nutritional value if it is printed or handwritten?

Yes, OCR is capable of processing printed or handwritten nutritional values. If the document is handwritten, OCR uses advanced techniques to recognize handwritten characters and convert them into digital text, while ensuring the accuracy of the extracted data.

‍

How does Koncile integrate with my existing tools and software?

Koncile is accessible via an API, with complete documentation available here. Additionally, you can import your documents directly into the application and download the extracted data in XLSX, XLS, CSV, or JSON formats for seamless integration into your workflows.

I need further assistance.

Check our API documentation, contact us at contact@koncile.ai. You can also create a demo account or book a demonstration with our team.

What are Koncile's prices?

Koncile offers 3 plans, including enterprise options for handling large volumes of data. You can check our pricing on the dedicated page in our documentation.

What types of documents can be processed by OCR?

An OCR software, especially an advanced solution like Koncile, can process a wide variety of documents. You can start from our library with all our document templates. Some of the most popular templates include OCR for invoices, OCR for identity documents, and OCR for bank statements. Here's a list of documents that can be processed by OCR:

Common professional documents:

Invoices: Supplier invoices, customer invoices, regardless of format (paper, PDF, image) or layout.
Purchase Orders: Extraction of product details, quantities, prices, etc.
Delivery Notes: Verification of received goods, tracking of deliveries.
Contracts: Extraction of key clauses, due dates, and stakeholders.
HR Documents: Summaries, cover letters, hiring forms, performance evaluations.
Legal Documents: Leases, non-disclosure agreements, various legal documents.
Financial Documents: Bank statements, transfer orders, financial reports.
Marketing Documents: Contact forms, survey responses, coupons.
Logistics Documents: Bills of lading, transport contracts, road or sea transport invoices.

Handwritten documents:

Handwritten forms: Questionnaires, surveys, etc.
Handwritten notes: Notes taken during meetings, annotations on documents.
Medical prescriptions: Koncile is particularly effective in this area.
Handwritten tables
Handwritten lists

Other types of documents:

Digitized documents: Scanned paper archives (books, newspapers, historical documents).
Photos of documents: Taken with a smartphone or camera.
Screenshots: Containing text.
PDF files: “Image” PDFs (scans) and native PDFs (generated by software).
Technical documents: Product sheets, manuals.
Multilingual documents: From any country and written in any language.

What are general fields and repeated fields?

In each extraction template, you will find:

General fields: These are pieces of information that appear only once in each document (e.g., the invoice number or the invoice date).
Repeated fields: These are pieces of information that appear multiple times in a document, such as item descriptions or prices in each line of a quote. Use repeated fields for extracting tables and charts from your documents.

Reliable and customizable AI OCR software for all your nutritional values

The OCR that detects key nutritional data

Fields captured by our OCR engine specialized in nutritional information

Why choose Koncile OCR for your nutritional values ?

Tailor the extraction to your needs

Set up Koncile in just one day

Connect Koncile to your tools

Experience next-generation data extraction

An OCR Solution Built for Nutritional Data Capture

Automatically extract key nutritional information

From Nutritional Labels to a Structured Database

Multi-Format Processing

Nutritional Data Parsing via API

Beyond OCR: Validation and verification of extracted fields

The OCR API to automate the management of nutritional values

An AI OCR designed for security

No training on your data

Fully encrypted software

Secure storage of extracted data

RGPD compliant

Discover all the documents you can automate

How does OCR extract nutritional information?

Can I extract specific information from a nutritional value?

In what format should I upload nutrition facts for OCR analysis?

Can OCR process nutritional value if it is printed or handwritten?

How does Koncile integrate with my existing tools and software?

I need further assistance.

What are Koncile's prices?

What types of documents can be processed by OCR?

What are general fields and repeated fields?