Page segmentation mode defines how your text will be searched for by Tesseract.
public enum TesseractPageSegmentationMode
Fully automatic page segmentation, but no OSD.
Automatic page segmentation, but no OSD, or OCR.
Automatic page segmentation with orientation and script detection (OSD).
Treat the image as a single word in a circle.
Orientation and script detection (OSD) only.
Treat the image as a single text line, bypassing hacks that are specific to Tesseract.
Assume a single uniform block of text.
Assume a single uniform block of vertically aligned text.
Treat the image as a single character.
Assume a single column of text of variable sizes.
Treat the image as a single text line.
Treat the image as a single word.
Find as much text as possible in no particular order.
Sparse text with orientation and script detection.