Image OCR Extractor

What does Image OCR Extractor do?

Image OCR Extractor is an image text extraction API that converts any image — screenshot, invoice, receipt, form, or photo — into structured text using Tesseract OCR. Submit one image or a batch of up to 50 (PNG, JPG, WebP, TIFF, BMP), and receive extracted text plus a per-image confidence score. No API key, no GPU, no setup required.

This actor runs the full extract text from images pipeline automatically: download, preprocess, Tesseract recognition, and structured JSON output. When confidence is low, it retries with threshold preprocessing to improve accuracy — so you get the best result without any manual tuning.

---

Why use Image OCR Extractor?

1. Invoice and receipt digitization — Extract totals, line items, vendor names, and dates from receipt photos or scanned invoices to feed accounting workflows automatically.
2. Screenshot text extraction — Turn UI screenshots, error messages, and social media screenshots into searchable, indexable text in seconds.
3. Multilingual document processing — Support for 100+ languages including Japanese, Chinese, Korean, German, French, and Spanish, with combined-language mode for bilingual documents.
4. Form and survey digitization — Process handwritten or typed paper forms from scanned documents without manual data entry.
5. Batch data pipeline integration — OCR entire image archives and feed the output into LLMs, databases, or search indexes programmatically via the Apify API.

---

How to use Image OCR Extractor

1. Open the actor on Apify Store and click Try for free.
2. Paste one or more image URLs into the url or urls input field.
3. Select a language code (default: eng) and preprocessing mode (default: grayscale).
4. Click Start — results arrive in seconds.
5. Fetch structured JSON from the Apify dataset or connect via API for automation.

---

Input

Parameter	Type	Default	Description
url	string	—	Single image URL. Used when urls is empty.
urls	array	—	Batch list of image URLs (up to 50 per run).
language	string	eng	Tesseract language code: eng, deu, fra, spa, jpn, chi_sim, kor, or combined eng+deu.
preprocessing	string	grayscale	Image preprocessing: none, grayscale, or threshold (binarize).
pageSegMode	integer	3	Tesseract PSM: 3 = auto, 6 = block, 7 = line, 8 = word, 11 = sparse.
limit	integer	50	Max images to process per run (hard cap: 200).

Supported URL types: direct image links, Google Drive share links, and Dropbox share links are all automatically resolved — no manual conversion needed.

---

Output

Each processed image returns one JSON object:

{
  "index": 1,
  "url": "https://example.com/invoice.png",
  "ok": true,
  "text": "Invoice #2024-001\nBill To: Acme Corp\nTotal: $1,250.00",
  "word_count": 9,
  "confidence": 87.4,
  "auto_enhanced": false,
  "language": "eng",
  "error": null
}

auto_enhanced: true means low confidence was detected on the first pass and the actor automatically re-ran OCR with threshold preprocessing. error is populated only when the image could not be processed at all.

---

Data fields

Field	Type	Description
index	integer	Position in the input list (1-based)
url	string	Source image URL
ok	boolean	Whether OCR succeeded
text	string	Extracted text (newline-separated)
word_count	integer	Number of words extracted
confidence	float	Tesseract average confidence score (0–100)
auto_enhanced	boolean	Whether automatic threshold preprocessing was applied
language	string	Language code used
error	string or null	Error message if OCR failed

Confidence score guide:

Range	Meaning
85–100	High quality, likely accurate
60–84	Moderate — review critical fields
< 60	Low — actor automatically retries with threshold preprocessing

---

Cost estimation

Pay-Per-Event: $0.002 per image successfully OCR-processed. First 5 images per run are free.

Images per run	Charged images	Estimated cost
5 screenshots	0	Free
10 screenshots	5	$0.01
50 images (full batch)	45	$0.09
200 product photos	195	$0.39

---

FAQ

Does the OCR API support handwriting? Tesseract performs best on printed text. Handwriting recognition is possible but accuracy varies. Use preprocessing: threshold and pageSegMode: 6 for best results on handwritten forms.

Can I extract text from images with dark backgrounds or colored overlays? Yes. Use preprocessing: grayscale (the default) for colored or photographic backgrounds. For text printed on a white background, threshold gives sharper binarized results.

How accurate is image text extraction? For clean, high-resolution images with standard fonts, confidence scores typically land in the 85–95 range. Low-quality photos or stylized fonts may score lower, but the automatic enhancement retry improves results without manual effort.

Disclaimer: OCR accuracy depends on image quality, resolution, and font type. This actor is not intended for medical, legal, or financial document processing where 100% accuracy is required. Always verify extracted text for critical use cases.

---

Related actors

• PDF Text & Table Extractor — PDF version with table detection, password-protected PDFs, batch processing
• DOCX Text Extractor — Word document extraction, same URL/Drive/Dropbox pattern
• Excel & CSV Extractor — .xlsx/.xls/.csv to JSON, full row/column structure
• Web Page to Markdown Converter — HTML text extraction

Feedback

Leave a review on Apify Store