mirror of
https://github.com/immich-app/immich
synced 2025-11-14 17:36:12 +00:00
feat: ocr (#18836)
* feat: add OCR functionality and related configurations * chore: update labeler configuration for machine learning files * feat(i18n): enhance OCR model descriptions and add orientation classification and unwarping features * chore: update Dockerfile to include ccache for improved build performance * feat(ocr): enhance OCR model configuration with orientation classification and unwarping options, update PaddleOCR integration, and improve response structure * refactor(ocr): remove OCR_CLEANUP job from enum and type definitions * refactor(ocr): remove obsolete OCR entity and migration files, and update asset job status and schema to accommodate new OCR table structure * refactor(ocr): update OCR schema and response structure to use individual coordinates instead of bounding box, and adjust related service and repository files * feat: enhance OCR configuration and functionality - Updated OCR settings to include minimum detection box score, minimum detection score, and minimum recognition score. - Refactored PaddleOCRecognizer to utilize new scoring parameters. - Introduced new database tables for asset OCR data and search functionality. - Modified related services and repositories to support the new OCR features. - Updated translations for improved clarity in settings UI. * sql changes * use rapidocr * change dto * update web * update lock * update api * store positions as normalized floats * match column order in db * update admin ui settings descriptions fix max resolution key set min threshold to 0.1 fix bind * apply config correctly, adjust defaults * unnecessary model type * unnecessary sources * fix(ocr): switch RapidOCR lang type from LangDet to LangRec * fix(ocr): expose lang_type (LangRec.CH) and font_path on OcrOptions for RapidOCR * fix(ocr): make OCR text search case- and accent-insensitive using ILIKE + unaccent * fix(ocr): add OCR search fields * fix: Add OCR database migration and update ML prediction logic. * trigrams are already case insensitive * add tests * format * update migrations * wrong uuid function * linting * maybe fix medium tests * formatting * fix weblate check * openapi * sql * minor fixes * maybe fix medium tests part 2 * passing medium tests * format web * readd sql * format dart * disabled in e2e * chore: translation ordering --------- Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com> Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
This commit is contained in:
parent
c666dc6c67
commit
02b29046b3
90 changed files with 3610 additions and 1722 deletions
|
|
@ -18,6 +18,7 @@ class SystemConfigMachineLearningDto {
|
|||
required this.duplicateDetection,
|
||||
required this.enabled,
|
||||
required this.facialRecognition,
|
||||
required this.ocr,
|
||||
this.urls = const [],
|
||||
});
|
||||
|
||||
|
|
@ -31,6 +32,8 @@ class SystemConfigMachineLearningDto {
|
|||
|
||||
FacialRecognitionConfig facialRecognition;
|
||||
|
||||
OcrConfig ocr;
|
||||
|
||||
List<String> urls;
|
||||
|
||||
@override
|
||||
|
|
@ -40,6 +43,7 @@ class SystemConfigMachineLearningDto {
|
|||
other.duplicateDetection == duplicateDetection &&
|
||||
other.enabled == enabled &&
|
||||
other.facialRecognition == facialRecognition &&
|
||||
other.ocr == ocr &&
|
||||
_deepEquality.equals(other.urls, urls);
|
||||
|
||||
@override
|
||||
|
|
@ -50,10 +54,11 @@ class SystemConfigMachineLearningDto {
|
|||
(duplicateDetection.hashCode) +
|
||||
(enabled.hashCode) +
|
||||
(facialRecognition.hashCode) +
|
||||
(ocr.hashCode) +
|
||||
(urls.hashCode);
|
||||
|
||||
@override
|
||||
String toString() => 'SystemConfigMachineLearningDto[availabilityChecks=$availabilityChecks, clip=$clip, duplicateDetection=$duplicateDetection, enabled=$enabled, facialRecognition=$facialRecognition, urls=$urls]';
|
||||
String toString() => 'SystemConfigMachineLearningDto[availabilityChecks=$availabilityChecks, clip=$clip, duplicateDetection=$duplicateDetection, enabled=$enabled, facialRecognition=$facialRecognition, ocr=$ocr, urls=$urls]';
|
||||
|
||||
Map<String, dynamic> toJson() {
|
||||
final json = <String, dynamic>{};
|
||||
|
|
@ -62,6 +67,7 @@ class SystemConfigMachineLearningDto {
|
|||
json[r'duplicateDetection'] = this.duplicateDetection;
|
||||
json[r'enabled'] = this.enabled;
|
||||
json[r'facialRecognition'] = this.facialRecognition;
|
||||
json[r'ocr'] = this.ocr;
|
||||
json[r'urls'] = this.urls;
|
||||
return json;
|
||||
}
|
||||
|
|
@ -80,6 +86,7 @@ class SystemConfigMachineLearningDto {
|
|||
duplicateDetection: DuplicateDetectionConfig.fromJson(json[r'duplicateDetection'])!,
|
||||
enabled: mapValueOfType<bool>(json, r'enabled')!,
|
||||
facialRecognition: FacialRecognitionConfig.fromJson(json[r'facialRecognition'])!,
|
||||
ocr: OcrConfig.fromJson(json[r'ocr'])!,
|
||||
urls: json[r'urls'] is Iterable
|
||||
? (json[r'urls'] as Iterable).cast<String>().toList(growable: false)
|
||||
: const [],
|
||||
|
|
@ -135,6 +142,7 @@ class SystemConfigMachineLearningDto {
|
|||
'duplicateDetection',
|
||||
'enabled',
|
||||
'facialRecognition',
|
||||
'ocr',
|
||||
'urls',
|
||||
};
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue