Expand description
Page layout analysis and text ordering for OCR
Re-exports§
pub use crate::utils::OcrError;pub use crate::utils::Result;pub use analyzer::*;pub use classifier::*;pub use column_detector::*;pub use detection_cnn::*;pub use detector::*;pub use form_extractor::*;pub use line_detector::*;pub use text_ordering::*;pub use union_find_ccl::*;
Modules§
- analyzer
- Layout analysis operations
- classifier
- Region classifier for document layout analysis
- column_
detector - Column detection for multi-column document layout analysis
- detection_
cnn - Lightweight detection CNN for text region heatmaps
- detector
- Region detection operations
- form_
extractor - Form field extraction
- line_
detector - Line detection for text layout analysis
- text_
ordering - Text ordering for proper reading sequence
- union_
find_ ccl - Union-Find (Disjoint Set) based Connected Component Labeling
Structs§
- Text
Line Features - Features extracted from a text line
Enums§
- Baseline
Estimate - Baseline estimate for a text line
Functions§
- estimate_
ascender_ descender - Estimate ascender and descender heights
- estimate_
baseline - Estimate baseline for a text line using bottom pixel analysis
- estimate_
cap_ height - Estimate cap height (height of uppercase letters)
- estimate_
x_ height - Estimate x-height for a text line
- extract_
text_ line_ features - Extract all text line features