文章基本信息

标题：Development of Adaptive Thresholding Technique for Classification of Synthetic Aperture Radar Images
本地全文：下载
作者：Debabrata Samanta ; Dr. Goutam Sanyal
期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2011
卷号：2
期号：4Ver1
出版社：Ayushmaan Technologies
摘要：The main purpose of this paper is to extract objects from Images and recognizing text characters. Our approach uses Morphological operation for text localization, and, Support Vector Machine for character recognition, along with some preprocessing and post processing steps. This algorithm is tested with natural Images as well as Images taken from ICDAR 2003 Robust Reading Competition dataset. The proposed work is evaluated using ICDAR 2003 competition metrics specification and the performance is compared with the existing methods developed in the previous three years.
关键词：Morphological Dilation; Support Vector Machines; Median;Filter; Laplacian of Gaussian Edge detector; Connected;Components;y.