To read text or numbers of an image, you will need OCR software
Optical Character Recognition, or OCR, is a technology to convert different types of documents, such as scanned paper documents, PDF files or images captured by a digital camera into text so that they are editable and searchable.
There are both free & commercial toolkits. Try any of these -
Free:
InstantOCR - web based OCR http://www.instantocr.com/
SimpleOCR - 9.3MB application. SDK/Command Line versions are commercially available http://www.simpleocr.com/Scanning/Document_Imaging/Software/OCR_Software/ocr_freeware.asp
OCR Terminal beta - web based OCR http://www.ocrterminal.com/ converts TIFF, JPEG, GIF, BMP formats to .doc, .txt, .rtf, .xml formats; PDF to Word
Free, Under development:
GOCR - open-source http://jocr.sourceforge.net/
Tesseract - open source OCR engine http://code.google.com/p/tesseract-ocr/
Commercial OCR Toolkits:
ABBYY FineReader http://www.abbyy.com/sdk/
OmniPage - http://www.nuance.com/omnipage/capturesdk/
If you need an API, try SimpleOCR or ABBYY FineReader or OmniPage
Source: http://mvark.blogspot.com/2009/02/free-ocr-tools.html