文章基本信息

标题：Features Ranking Method to Determine Significant Features for Handwriting Images – Systematic Literature Review
本地全文：下载
作者：Nurul Farah Atiqah Mohd Tahir ; Intan Ermahani A. Jalil ; Mohd Sanusi Azmi 等
期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2020
卷号：12
期号：2
页码：43-59
出版社：International Center for Scientific Research and Studies
摘要：Features ranking is a very essential step in determining significant features for handwriting image. Its goal is to increase the classification performance by reducing the computational cost. In the context of handwriting recognition, the extraction of image features can lead to the problem of high dimensionality of data. This has become the handwriting recognition problem whereby the variation of generated features are contributing to the factor of irrelevant or redundant features while maybe even correlated to each other that burden the classification process. As a result, this will be contributing to the lower identification performance accuracy due to the increase of computational complexity. This paper used a Systematic Literature Review (SLR) to compile the features ranking based technique to overcome the drawbacks above. SLR is a literature review that collects and critically analyze multiple studies to answer the research question. Five research questions were drawn for this purpose. Information such as techniques, collection of datasets and methods’ performances were extracted from 52 articles. This information was analyzed to identify the strengths and weaknesses of the techniques and the affecting elements to the performance of features ranking. The SLR has also found out that some of the studies were using feature selection method in handwriting recognition. The efficiency of some feature selection method has exceeded other approaches, even though it is only at a reasonable level. Therefore, more studies are needed to overcome the drawbacks of the handwriting recognition by using features ranking.
关键词：feature extraction;features ranking;feature selection;handwriting recognition