Skew correction

When a page is fed to a flatbed scanner (mechanically or manually) or photographed with a smartphone, it is nearly impossible to achieve perfect alignment. As a result, a slight skew (tilt) inevitably occurs in scanned images or photographs.

Skew angle detection and image straightening is critical to the OCR process as it directly affects the reliability and efficiency of segmentation and text extraction. Aspose.OCR offers automated processing algorithms to correct image tilt (deskew) before proceeding to recognition.

Detecting skew angles

To find out skew angles for all images in a batch, use CalculateSkew method. It returns a list of SkewOutput objects, one per image, with the following properties:

Property Type Description
Angle double Skew angle in degrees.
ImageIndex int Sequence number of the image on the page. When working with single-page images, this value is always 0.
Page int Page number. When working with single-page images, this value is always 0.
Source String The full path or URL of the source file. If the file is provided as a BufferedImage object, an array of pixels, or a Base64 string, this value will be empty.
AsposeOcr recognitionEngine = new AsposeOcr();
// Add PDF documents to OcrInput object
OcrInput input = new OcrInput(InputType.PDF);
input.Add("source.pdf");
// Detect skew angles
ArrayList<SkewOutput> angles = recognitionEngine.CalculateSkew(input);
angles.forEach((angle) -> {
	System.out.println("File: " + angle.Source + " | Page: " + angle.Page + " | Image: "+ angle.ImageIndex + " | Angle: " + angle.Angle +"°");
});

Skewed image

> File: "C:\source.pdf" | Page: 0 | Image: 0 | Angle: 5.9°

Automatic skew correction

To automatically straighten skewed image before recognition, run the image through AutoSkew preprocessing filter.

AsposeOCR api = new AsposeOCR();
// Apply automatic skew correction
PreprocessingFilter filters = new PreprocessingFilter();
filters.add(PreprocessingFilter.AutoSkew());
// Prepare batch
OcrInput images = new OcrInput(InputType.SingleImage, filters);
images.add("image.png");
// Save processed images to the folder
ImageProcessing.Save(images, "C:\\images");
Skewed image Deskewed image

Manual skew correction

In some cases, automatic skew correction may incorrectly determine the angle of the image. This can happen to significantly rotated images (more than 20% inclination) or poor quality photos with significant perspective distortions.

To deal with such situations, you can rotate the image by the specified degree using Rotate preprocessing filter. The rotation angle is passed in degrees:

  • Negative angle (-360 to 0): rotate counterclockwise;
  • Positive angle (0 to 360): rotate clockwise.
AsposeOCR api = new AsposeOCR();
// Apply manual rotation
PreprocessingFilter filters = new PreprocessingFilter();
filters.add(PreprocessingFilter.Rotate(-90));
// Prepare batch
OcrInput images = new OcrInput(InputType.SingleImage, filters);
images.add("image.png");
// Save processed images to the folder
ImageProcessing.Save(images, "C:\\images");

Image regions preprocessing

Automatic skew correction and manual rotation filters can be applied to specific regions of an image. For example, you can straighten an illustration on a page while leaving the rest of the content unchanged.

To apply a filter to an area, specify its top left corner along with width and height as Rectangle object. If the region is omitted, the filter is applied to the entire image.

Rectangle rectangle = new Rectangle(5, 161, 340, 340);
PreprocessingFilter filters = new PreprocessingFilter();
filters.add(PreprocessingFilter.Rotate(90, rectangle));

Usage scenarios

  • Automatic skew correction is recommended in almost all cases, except for perfectly straight scans.
  • Manual rotation is recommended for:
    • photos of low quality;
    • images with a significant angle of inclination.