Image preprocessing

The accuracy and reliability of text recognition is highly dependent on the quality of the original image. Aspose.OCR for JavaScript via C++ offers a large number of fully automated and manual image processing filters that enhance an image before it is sent to the OCR engine.

Each preprocessing filter increases the image processing time. The approximate amount of additional time required for pre-processing (as a percentage of the minimum image processing pipeline) is listed in the Performance Impact column.

Filter	Action	Performance impact	Usage scenarios
Skew correction	Automatically straighten images aligned at a slight angle to the horizontal.	12%	Skewed images
Rotation	Manually rotate severely skewed images.	7.5%	Significantly rotated images
Noise removal	Automatically remove dirt, spots, scratches, glare, unwanted gradients, and other noise from photos and scans.	175% extra time 38% more memoryÂ ⁽¹⁾	Photos Old books Newspapers Postcards Documents with stains and dirt
Contrast correction	Automatically adjust the image contrast.	7.5%	Photos Old papers Text on a background
Binarization	Convert images to black and white automatically or manually adjust the criteria that determines whether a pixel is considered black or white.	0.9%Â ⁽²⁾	Used for text areas detection and most automatic image adjustments.

Notes

Automatic noise removal uses a powerful artificial intelligence algorithm that consumes significant computing resources and RAM. Use it with care, especially if end-users will work on entry-level desktops, Chromebooks and tablets.
Most OCR internal processing involves automatic conversion of images to back and white, thus the binarization settings do not have any significant effect on overall performance.

Applying multiple preprocessing filters

Multiple preprocessing filters can be applied to the same image to further improve the recognition quality. Note that each filter requires additional time and resources on the computer running the application. Do not add extra filters if you are satisfied with the recognition accuracy.

var settings = Module.WasmAsposeOCRRecognitionSettings();
settings.threshold_value = {THRESHOLD};
settings.correct_skew = true;
settings.skew = {ANGLE};
settings.auto_denoising = true;
settings.auto_contrast = true;

Approximate increase of processing time: 0%

Preparing content for recognition Recognition languages