Recognition settings
Contents
[
Hide
]
Aspose.OCR for .NET provides good recognition accuracy and performance by default. However, there will inevitably be cases where the default settings cannot provide reliable recognition results.
To configure Aspose.OCR recognition settings, pass an optional RecognitionSettings
structure to the recognition method.
Setting | Type | Default value | Description |
---|---|---|---|
all_image |
bool | false |
Force recognition of the entire image. Not used for receipt recognition. |
allowed_characters |
characters_allowed_type |
characters_allowed_type::ALL |
The predefined whitelist of characters Aspose.OCR engine will look for. |
alphabet |
string | All symbols | A custom list of characters to be recognized, provided as a case-sensitive string. Characters that do not match the provided list are ignored. |
auto_contrast |
bool | false |
Automatically increase the contrast of images before proceeding to recognition. |
auto_denoising |
bool | false |
Automatically remove noise from images before proceeding to recognition. |
correct_skew |
bool | true |
Automatically correct image tilt (deskew) before proceeding to recognition. |
detect_areas_mode |
detect_areas_mode_enum |
detect_areas_mode_enum::DOCUMENT |
Manually override the default document areas detection method. Not used for receipt recognition. |
filters |
custom_preprocessing_filters |
none | Preprocessing filters to be applied to the image. |
format |
export_format |
export_format::text |
The format of recognition results that are stored in memory (plain text, JSON or XML). |
ignoredCharacters |
string | none | A blacklist of characters that are ignored during recognition. |
language_alphabet |
language |
language::none |
Specify a language for recognition. |
lines_filtration |
bool | false |
Set to true to recognize text in tables.Set to false to improve performance by ignoring table structures and treating tables as plain text. |
preprocess_area |
rect* |
NULL |
Specify the image region to be affected by preprocessing filters. |
rectangles |
rect* |
NULL |
Areas of the image from which to extract text. |
rectangles_size |
size_t |
0 |
The number of recognition areas. |
save_format |
file_format |
file_format::txt |
The file format in which the recognition result is saved. |
skew |
double |
0 |
Manually rotate the image by the specified degree. Does not work if recognition areas are specified. |
threshold_value |
int |
0 |
Override the automatic binarization settings. |
upscale_small_font |
bool | false |
Improve small font recognition and detection of dense lines. |
Example
The following code example shows how to fine-tune recognition:
std::string image_path = "source.png";
const size_t len = 4096;
wchar_t buffer[len] = { 0 };
RecognitionSettings settings;
settings.language_alphabet = language::ukr;
settings.auto_contrast = true;
settings.upscale_small_font = true;
size_t res_len = aspose::ocr::page_settings(image_path.c_str(), buffer, len, settings);
std::wcout << buffer;