Digital Image Processing

B. Gangamma ¹, K. Srikanta Murthy ², Arun Vikas Singh ³

Affiliations
1 Department of ISE, PESIT, Bangalore, Karnataka, IN
2 Department of CSE, PESSE, Bangalore, Karnataka, IN
3 Department of ECE, PESIT, Bangalore, Karnataka, IN

Abstract

Historical documents play vital role in understanding our past. As these documents carry valuable information, preservation of such documents in proper format and state is a major challenge for us. Digitization is the one of the better method to preserve these documents for longer duration. Image processing techniques can be utilized to preprocess the image to enhance the images which are degraded in nature. One of the image processing techniques, preprocessing is the vital step in enhancing the degraded noisy images. In this paper a combination of bilateral filter along with set theory operations are used to enhance the historical document image. The bilateral filter is non linear filter which smoothes the image without smoothing the edges. The proposed method eliminates noise, uneven background and enhances the contrast of the script image. The result of the proposed method is compared with Mean, and Gaussian filter and are better than these methods. Performance of the proposed method is measured using Peak Signal Noise Ratio.

Keywords

Bilateral Filter, Contrast Enhancement, Denoising, Degraded Document, Historical, Spatial Domain.

Full Text

     

Arun Vikas Singh ¹, K. Srikanta Murthy ², B. Gangamma ³

Affiliations
1 Department of ECE, PESIT, Bangalore, Karnataka, IN
2 Department of CSE, PESSE, Bangalore, Karnataka, IN
3 Department of ISE, PESIT, Bangalore, Karnataka, IN

Abstract

Digital image compression has received significant attention of researchers in the last few decades. Recently, there has been many compression algorithm based on wavelets. Image compression using wavelet based algorithms lead to high compression ratios in comparison to other compression techniques. Inherently, wavelets have a limitation in their ability to capture the edge related information in a given image. It has been well demonstrated by researchers that traditional wavelets are not very effective in dealing with multidimensional signals with distributed discontinuities. In this paper, a novel image compression algorithm based on a combination of Discrete Shearlet Transform (DST) and Set Partitioning In Hierarchical Trees (SPIHT) has been proposed. It has been demonstrated that the performance of the proposed technique is superior to the existing techniques in terms of Peak Signal to Noise Ratio (PSNR) and Computation Time (CT).

Keywords

Image Compression, Discrete Wavelet Transform (DWT), Discrete Shearlet Transform (DST), Sub Band Image Decomposition, Embedded Zero-Tree Wavelet (EZW) and Set Partitioning in Hierarchical Trees (SPIHT).

Full Text