IJARCCE ISSN (Online) 2278-1021 ISSN (Print) 2319 5940 International Journal of Advanced Research in Computer and Communication Engineering ISO 3297:2007 Certified Vol. 6, Issue 5, May 2017 Copyright to IJARCCE DOI10.17148/IJARCCE.2017.6572 381 Preservation of Historical Documents using ICM and Filters Ashika Parvin 1 , Shajun Nisha 2 , Mohamed Sathik 3 M. Phil (Scholar), Computer Science, Sadakathullah Appa College, Tirunelveli, India 1 Prof & Head, PG Department of Computer Science, Sadakathullah Appa College, Tirunelveli, India 2 Principal, Sadakathullah Appa College, Tirunelveli, India 3 Abstract: Digital image enhancement technique is used for improving the visual qualities of the images. In this paper, contaminated Brahmi script is taken as an input and it is enhanced. There are numerous problems in preserving historical documents from degradation due to some bad storage conditions and poor contrast due to humidity. In this work, it is proposed to investigate the efficiency of logarithmic technique to enhance along with the performance of utilizing the Intersecting Cortical Model (ICM) network which is a simplified model of Pulse-Coupled Neural Network (PCNN) model and filters. Keywords: Digital Image Enhancement, PCNN, Filters, Brahmi script. I. INTRODUCTION Image processing is a common term that covers image segmentation, image registration, image fusion, image thinning, image enhancement, edge detection, feature extraction, image recognition, noise removal from image, classification of images, texture and fabric defects identification, and surveillance. Image Enhancement is the improvement of digital image quality, without knowledge about the source of degradation. Enhancement may be used to restore an image that has suffered some kind of deterioration due to the optics, electronics and environment. The manuscripts are the hand written documents and the techniques of writing manuscripts are called as “Paleography”. These scripts get damaged or erased due to the calamities of time and nature, the poor quality of paper, dirt, humidity or usage of poor quality inks.To enhance certain features of an image Logarithmic transformation method is used. It is used to brighten the intensities of an image More often, it is used to increase the contrast of lower intensity values. Pulse coupled neural network (PCNN) can remove contamination of scripts when used along with the application of filters. Pulse coupled neural network (PCNN) is a single-layer, two-dimensional algorithm is laterally connected network of integrate-and- fire neurons between the image pixels and network neurons. It is a good pre-processor in which neurons produces temporal series of pulse outputs and has the following advantages like global optimal approximation characteristic and favorable classification capability, rapid convergence of learning procedure, an optimal network to accomplish the mapping function in the feed-forward, no need to pre-train. The Intersecting Cortical Model (ICM), or ICM algorithm presented is a reduced set of equations of the Pulse-Coupled Neural Network (PCNN) model. Filtering is a technique for modifying or enhancing an image to emphasize certain features or remove other features which includes smoothing, sharpening, and edge enhancement. II. RELATED WORK Digital image processing is a broad subject and often involves procedures which can be mathematically complex, but central idea behind digital image processing is quite simple[1]. Generally image enhancement techniques are used to get detail that is obscured, or to highlight certain features of interest in image. In image enhancement process one or more attributes of image are modified. In spatial domain techniques [2], we directly deal with the image pixels. The pixel values are manipulated to achieve desired enhancement. These enhancement operations are performed in order to modify the image brightness, contrast or the distribution of the grey levels.. One such method of transformation used in this paper is log transformation maps [3] a narrow range of low input grey level values into a wider range of output values. Log functions are particularly useful when the input grey level values may have an extremely large range of values. This technique was used by[4]. By using this log transformation darker pixel values of the image are expanded by compressing the values in the higher levels. Compression of dynamic range values in an image by giving large variation in the pixel value is considered as the main characteristics of log transformation. Image enhancement using log transformation can only improve the quality of an image. But for betterment we combine it with pulse-coupled neural network (PCNN) model is used along with filters. In the late 1980s, Eckhorn et al. discovered that the midbrain in an oscillating way created binary images that could extract different features from the visual impression when they