Chapter 10. Developing Segmentation Algorithms for Text Recognition

In the previous chapters, we learned about a wide range of image processing techniques such as thresholding, contours descriptors, and mathematical morphology. In this chapter, we will discuss common problems that you may face while dealing with scanned documents, such as identifying where the text is or adjusting its rotation. We will also learn how to combine techniques presented in the previous chapters to solve those problems. By the end of this chapter, we will have segmented regions of text that can be sent to an optical character recognition (OCR) library.

By the end of this chapter, you should be able to answer the following questions:

• What kind of OCR applications exists?
• What are the common problems while writing an OCR application?
• How do I identify regions of documents?
• How do I deal with problems like skewing and other elements in the middle of the text?
• How do I use Tesseract OCR to identify my text?