.png){kind=icon}
.png){kind=icon}
Return
A multi-language writer identification method based on image mining and genetic algorithm techniques
.png){kind=icon}
PRE
AI
DOI：10.1007/s00500-018-3393-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Writing identification based on handwriting has many applications in the real world. Due to various forms of written letters in different languages, one of the major challenges in this context is offering an efficient method not being dependent on any specific language. In this paper, we have proposed a new approach based on image mining techniques for offline and text independent writer identification. In this method, each writers' prominent features are found from training samples, and then identification is done according to them. In the image mining part of the proposed approach, certain techniques including SVM classifier and genetic algorithms are employed. To evaluate this method and show its performance in different languages, CASIA for Chinese, IAM dataset for English and two datasets for Kannada and Persian language handwriting were examined. The experiment results demonstrate that the presented method has over 99% accuracy for these languages. Regarding the results in tested languages and the method details, it is highly likely that our method would have good results in other languages also.
Keywords:
Writer identification
Feature selection
Genetic algorithm
Support vector machine
Evolutionary strategy
Principal component analysis
K-nearest neighbor
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.