Real - Time Text Reader

In most character recognition systems like Optical Character Recognition(OCR), the system may not work well in case of handwritten documents, documents with poor contrast, or when the text and the background are similar in darkness. In some circumstances, the presence of the aforementioned cases leads to poor character recognition. This paper presents a Real Time Text-Reader which works for scanned images and videos. Additionally, the system also extracts text from digital comic images. The system works in 5 phases which are acquirement of the image, pre-processing on image, segmentation, feature extraction, word extraction. It then tags the words into their respective parts of speech categories.