Open AccessNoise Reduction Technique In Scanned Document Using Cuckoo Optimization Algorithm
Author(s) -
Prof. S. S. Thakare,
Prof. Dr. S. N. Kale
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1069.0886s19
Subject(s) - noise (video) , computer science , noise reduction , artificial intelligence , pixel , preprocessor , pattern recognition (psychology) , image processing , computer vision , digitization , segmentation , median filter , algorithm , image (mathematics)
While scanning, digitization and transmission, scanned documents can be contaminated with noise. Noise can be categorized by identifying its characteristics. Noise observed for similar pattern scanned document is the source for selecting appropriate noise removal techniques. Any image processing method can have few phases like (i) Pre-processing, (ii) Segmentation, (iii) Recognition and (iv) Post processing. This pre-processing stage is an essential stage, which primarily deals with noise removal. This paper involves the use of the Cuckoo Optimization Algorithm (COA) to remove noise in preprocessing. COA has shown its superior capabilities in fast convergence and better optimal global performance. It finds the most likely pixel value to restore noisy pixels.