• PARAMITA MAJI

Image enhancement is one of the challenging issues in low level image processing. Camera captured and scanned document images can suffer from some form of degradation. Degraded, noisy scanned documents can appear due to improper paper feeding into the scanner. Camera captured images also may be degraded due to lighting intensity of the environment, blur, imperfect focus, shadow, uneven illumination, use of the flash light while capturing the image and distorted by a non-planar document shape. So, the document images are often hard to read, have low contrast, became faded, washed out, crumpled and are corrupted by various artifacts, as a result it substantially deteriorate the performance of document processing systems. An improved algorithm has been proposed for document image analysis and enhancement to enhance the quality and improve the readability of degraded document images. The main idea of this paper is to enhance the quality of document images and extracts the text components. Here, pre-processing performed on the document images, is composed of several steps and the steps are represented through a Graphical User Interface (GUI). At first dataset are collected, converted into grayscale, then splitted into two halves vertically and then both halves binarized individually. An adaptive binarization has been developed here. Splitted portions merged after filtering is applied on each half, then skew-corrected and segmented into separate characters and saved into a folder. Here, Skew has been corrected based on their entropy calculation of Horizontal Projection Profile (HPP). Experimental results show that this method performs well on bad or uneven illumination document images.

Adaptive Thresholding, Character Segmentation, Horizontal Projection profile, Camera Captured Document Images, Scanned Document Images, Image Enhancement, Skew Detection & Skew Correction

"Document Image Analysis and Enhancement for OCR Applications ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.187-194, May-2019, Available :http://www.jetir.org/papers/JETIR1905F27.pdf

"Document Image Analysis and Enhancement for OCR Applications ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp187-194, May-2019, Available at : http://www.jetir.org/papers/JETIR1905F27.pdf