image-ocr
Extract text content from images using Tesseract OCR via Python
>_
Quick Installnpxskills add benchflow-ai/skillsbench--skill image-ocrInstructions
Loading…
Extract text content from images using Tesseract OCR via Python
npxskills add benchflow-ai/skillsbench--skill image-ocrLoading…
This skill enables accurate text extraction from image files (JPG, PNG, etc.) using Tesseract OCR via the pytesseract Python library. It is suitable for scanned documents, screenshots, photos of text, receipts, forms, and other visual content containing text.
The following Python libraries are required:
import pytesseract
from PIL import Image
import json
import os
All extracted content must be returned as valid JSON conforming to this schema:
{
"success": true,
"filename": "example.jpg",
"extracted_text": "Full raw text extracted from the image...",
"confidence": "high|medium|low",
"metadata": {
"language_detected": "en",
"text_regions": 3,
"has_tables": false,
"has_handwriting": false
},
"warnings": [
"Text partially obscured in bottom-right corner",
"Low contrast detected in header section"
]
}
success: Boolean indicating whether text extraction completedfilename: Original image filenameextracted_text: Complete text content in reading order (top-to-bottom, left-to-right)confidence: Overall OCR confidence level based on image quality and text claritymetadata.language_detected: ISO 639-1 language codemetadata.text_regions: Number of distinct text blocks identifiedmetadata.has_tables: Whether tabular data structures were detectedmetadata.has_handwriting: Whether handwritten text was detectedwarnings: Array of quality issues or potential errorsimport pytesseract
from PIL import Image
def extract_text_from_image(image_path):
"""Extract text from a single image using Tesseract OCR."""
img = Image.open(image_path)
text = pytesseract.image_to_string(img)
return text.strip()
import pytesseract
from PIL import Image
def extract_with_confidence(image_path):
"""Extract text with per-word confidence scores."""
img = Image.open(image_path)
# Get detailed OCR data including confidence
data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)
words = []
confidences = []
for i, word in enumerate(data['text']):
if word.strip(): # Skip empty strings
words.append(word)
confidences.append(data['conf'][i])
# Calculate average confidence
avg_confidence = sum(c for c in confidences if c > 0) / len([c for c in confidences if c > 0]) if confidences else 0
return {
'text': ' '.join(words),
'average_confidence': avg_confidence,
'word_count': len(words)
}
import pytesseract
from PIL import Image
import json
import os
def ocr_to_json(image_path):
"""Perform OCR and return results as JSON."""
filename = os.path.basename(image_path)
warnings = []
try:
img = Image.open(image_path)
# Get detailed OCR data
data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)
# Extract text preserving structure
text = pytesseract.image_to_string(img)
# Calculate confidence
confidences = [c for c in data['conf'] if c > 0]
avg_conf = sum(confidences) / len(confidences) if confidences else 0
# Determine confidence level
if avg_conf >= 80:
confidence = "high"
elif avg_conf >= 50:
confidence = "medium"
else:
confidence = "low"
warnings.append(f"Low OCR confidence: {avg_conf:.1f}%")
# Count text regions (blocks)
block_nums = set(data['block_num'])
text_regions = len([b for b in block_nums if b > 0])
result = {
"success": True,
"filename": filename,
"extracted_text": text.strip(),
"confidence": confidence,
"metadata": {
"language_detected": "en",
"text_regions": text_regions,
"has_tables": False,
"has_handwriting": False
},
"warnings": warnings
}
except Exception as e:
result = {
"success": False,
"filename": filename,
"extracted_text": "",
"confidence": "low",
"metadata": {
"language_detected": "unknown",
"text_regions": 0,
"has_tables": False,
"has_handwriting": False
},
"warnings": [f"OCR failed: {str(e)}"]
}
return result
# Usage
result = ocr_to_json("document.jpg")
print(json.dumps(result, indent=2))
import pytesseract
from PIL import Image
import json
import os
from pathlib import Path
def process_image_directory(directory_path, output_file):
"""Process all images in a directory and save results."""
image_extensions = {'.jpg', '.jpeg', '.png', '.webp'}
results = []
for file_path in sorted(Path(directory_path).iterdir()):
if file_path.suffix.lower() in image_extensions:
result = ocr_to_json(str(file_path))
results.append(result)
print(f"Processed: {file_path.name}")
# Save results
with open(output_file, 'w') as f:
json.dump(results, f, indent=2)
return results
# Specify language (default is English)
text = pytesseract.image_to_string(img, lang='eng')
# Multiple languages
text = pytesseract.image_to_string(img, lang='eng+fra+deu')
Use --psm to control how Tesseract segments the image:
# PSM 3: Fully automatic page segmentation (default)
text = pytesseract.image_to_string(img, config='--psm 3')
# PSM 4: Assume single column of text
text = pytesseract.image_to_string(img, config='--psm 4')
# PSM 6: Assume uniform block of text
text = pytesseract.image_to_string(img, config='--psm 6')
# PSM 11: Sparse text - find as much text as possible
text = pytesseract.image_to_string(img, config='--psm 11')
Common PSM values:
0: Orientation and script detection (OSD) only3: Fully automatic page segmentation (default)4: Single column of text of variable sizes6: Uniform block of text7: Single text line11: Sparse text13: Raw lineFor better OCR accuracy, preprocess images:
from PIL import Image, ImageFilter, ImageOps
def preprocess_image(image_path):
"""Preprocess image for better OCR results."""
img = Image.open(image_path)
# Convert to grayscale
img = img.convert('L')
# Increase contrast
img = ImageOps.autocontrast(img)
# Apply slight sharpening
img = img.filter(ImageFilter.SHARPEN)
return img
# Use preprocessed image for OCR
img = preprocess_image("document.jpg")
text = pytesseract.image_to_string(img)
For difficult images (low contrast, faded text, dark backgrounds), try multiple preprocessing approaches:
ImageOps.invert() for dark backgrounds with light textimg.point(lambda p: 255 if p > threshold else 0) with different threshold values (e.g., 100, 128)ImageFilter.SHARPEN to improve edge clarityFor challenging images, a single OCR pass may miss text. Use multiple passes with different configurations:
Try multiple PSM modes - Different page segmentation modes work better for different layouts (e.g., --psm 6 for blocks, --psm 4 for columns, --psm 11 for sparse text)
Try multiple preprocessing variants - Run OCR on several preprocessed versions of the same image
Combine results - Aggregate text from all passes to maximize extraction coverage
def multi_pass_ocr(image_path):
"""Run OCR with multiple strategies and combine results."""
img = Image.open(image_path)
gray = ImageOps.grayscale(img)
# Generate preprocessing variants
variants = [
ImageOps.autocontrast(gray),
ImageOps.invert(ImageOps.autocontrast(gray)),
gray.filter(ImageFilter.SHARPEN),
]
# PSM modes to try
psm_modes = ['--psm 6', '--psm 4', '--psm 11']
all_text = []
for variant in variants:
for psm in psm_modes:
try:
text = pytesseract.image_to_string(variant, config=psm)
if text.strip():
all_text.append(text)
except Exception:
pass
# Combine all extracted text
return "\n".join(all_text)
This approach improves extraction for receipts, faded documents, and images with varying quality.
Issue: Tesseract not found
# Verify Tesseract is installed
try:
pytesseract.get_tesseract_version()
except pytesseract.TesseractNotFoundError:
print("Tesseract is not installed or not in PATH")
Issue: Poor OCR quality
Issue: Empty or garbage output
Before returning results, verify:
json.loads() to validate)success, filename, extracted_text, confidence, metadata)
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.