image-ocr
Extract text content from images using Tesseract OCR via Python
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- image-ocr
- description
- Extract text content from images using Tesseract OCR via Python
03 SKILL.md 正文
Mandatory Structured Receipt Field Extraction and Delivery
-
Preserve field evidence before selecting values
For every date and amount candidate, retain the original text, field label, source region, recognition source, and acceptance or correction reason in working records separate from the prescribed output schema. Give each field an explicit state: candidate, unresolved, or confirmed. Confirm a value only after its own evidence establishes the field identity and complete reading. A first non-empty candidate is not automatically confirmed; format validity, frequency, page confidence, keyword rank, and line position alone are insufficient. Compare competing readings of the same field and retain unresolved conflicts. End extraction for an image only when both fields are evidence-confirmed, or save its unresolved fields for local review.
-
Select the final payable amount by its meaning
Identify the final payable field before selecting its number. Distinguish it from item prices, subtotals, sales totals, tax amounts, payments received, change, and identifiers; use the amount after applicable taxes, discounts, and rounding. Do not automatically exclude an amount because it includes GST. Select the complete number bound to that field, not simply the last number or latest line. For a next-line fallback, verify the label-to-number association and rule out an intervening field. An unverified association remains unresolved even if it yields a plausible amount.
-
Parse numbers and dates conservatively and completely
Preserve the complete original number and its punctuation. Correct confusable characters or separators only within the confirmed field region, retaining the original reading and the evidence for the correction. Decimal placement or missing digits must be supported by that field: a decimal elsewhere on the page or the token's length is not evidence. Date order and any character correction likewise require date-field context. Never repair an invalid month by modulo, digit truncation, or merely making the date valid. A required interpretation without supporting evidence must stay unresolved and enter local review, not silently become an accepted value.
-
Review uncertain fields locally
After the first pass, build a review queue from missing, conflicting, ambiguous, or weak-fallback-dependent fields, including non-empty guesses and unsupported digit or date repairs. Decide review eligibility from the candidate's extraction path and evidence, not merely from suspicious label keywords or whether the output is populated. For each queued field, actually recognize a crop containing its label and complete value, or directly inspect that region in the original image when needed. Use field semantics, applicable arithmetic relationships, and date context to record an evidence-backed decision or keep the field unresolved. An empty suspicious-keyword scan does not clear this queue. Clear evidence needs no extra voting; parser edits or full-batch reruns alone do not count as local review.
-
Keep confirmed results stable
Protect evidence-confirmed fields, not the first candidates returned by OCR. Keep unconfirmed fields open to stronger same-field evidence; a first-found assignment must not block a later justified correction. Retries for other fields preserve confirmed values. Correct a confirmed value only with stronger same-field evidence and a recorded reason. After changing shared parsing logic, review affected records against their saved evidence and update only justified changes.
-
Save incrementally and reserve delivery budget
Save each image's first-pass candidates, evidence, field states, and unresolved items as soon as that image is processed, before moving to the next image or refining it. Writing one evidence file only after the entire batch finishes is not an incremental checkpoint. Save each local-review decision before proceeding. Retry only fields needing new evidence and apply incremental updates. Reserve execution, writing, and verification budget. Materialize the final workbook from saved records without starting another full-batch OCR pass. A checkpoint alone is not delivery of the required file.
-
Confirm completion from the actual deliverable
Execute modified scripts and update the target file. Before invoking finish, audit the saved field records: each accepted value must have a confirmation reason grounded in its own source evidence, and each review-required field must have an actual review decision. Report the confirmed and unresolved field counts; being non-null is not an acceptance test. Reopen the workbook and compare each delivered field with its corresponding confirmed record, in addition to checking input coverage, schema, format, and ordering. File existence, legal formats, row counts, and printed values alone are insufficient. Resolve outstanding fields where evidence permits; otherwise write the prescribed missing value and disclose them without claiming complete extraction. Values in logs or memory are not delivered until written and verified in the actual file.
Image OCR Skill
Purpose
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.
When to Use
- Extracting text from scanned documents or photos
- Reading text from screenshots or image captures
- Processing batch image files that contain textual information
- Converting visual documents to machine-readable text
- Extracting structured data from forms, receipts, or tables in images
Required Libraries
The following Python libraries are required:
import pytesseract
from PIL import Image
import json
import os
Input Requirements
- File formats: JPG, JPEG, PNG, WEBP
- Image quality: Minimum 300 DPI recommended for printed text; clear and legible text
- File size: Under 5MB per image (resize if necessary)
- Text language: Specify if non-English to improve accuracy
Output Schema
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"
]
}
Field Descriptions
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 errors
Code Examples
Basic OCR Extraction
import 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()
OCR with Confidence Data
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)
}
Full OCR with JSON Output
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))
Batch Processing Multiple Images
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
Tesseract Configuration Options
Language Selection
# 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')
Page Segmentation Modes (PSM)
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 line
Image Preprocessing
For 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)
Advanced Preprocessing Strategies
For difficult images (low contrast, faded text, dark backgrounds), try multiple preprocessing approaches:
- Grayscale + Autocontrast - Basic enhancement for most images
- Inverted - Use
ImageOps.invert()for dark backgrounds with light text - Scaling - Upscale small images (e.g., 2x) before OCR to improve character recognition
- Thresholding - Convert to binary using
img.point(lambda p: 255 if p > threshold else 0)with different threshold values (e.g., 100, 128) - Sharpening - Apply
ImageFilter.SHARPENto improve edge clarity
Multi-Pass OCR Strategy
For 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 6for blocks,--psm 4for columns,--psm 11for 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.
Error Handling
Common Issues and Solutions
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
- Preprocess image (grayscale, contrast, sharpen)
- Use appropriate PSM mode for the document type
- Ensure image resolution is sufficient (300+ DPI)
Issue: Empty or garbage output
- Check if image contains actual text
- Try different PSM modes
- Verify image is not corrupted
Quality Self-Check
Before returning results, verify:
- [ ] Output is valid JSON (use
json.loads()to validate) - [ ] All required fields are present (
success,filename,extracted_text,confidence,metadata) - [ ] Text preserves logical reading order
- [ ] Confidence level reflects actual OCR quality
- [ ] Warnings array includes all detected issues
- [ ] Special characters are properly escaped in JSON
Limitations
- Tesseract works best with printed text; handwriting recognition is limited
- Accuracy decreases with decorative fonts, artistic text, or extreme stylization
- Mathematical equations and special notation may not extract accurately
- Redacted or watermarked text cannot be recovered
- Severe image degradation (blur, noise, low resolution) reduces accuracy
- Complex multi-column layouts may require custom PSM configuration
Version History
- 1.0.0 (2026-01-13): Initial release with Tesseract/pytesseract OCR
04 同仓库更多 Skills
video-frame-extraction
Extract frames from video files and save them as images using OpenCV
openai-vision
Analyze images and multi-frame sequences using OpenAI GPT vision models
image-ocr
Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms
video-frame-extraction
Extract frames from video files and save them as images using OpenCV
openai-vision
Analyze images and multi-frame sequences using OpenAI GPT vision models
image-ocr
Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms