International Journal of Image Processing | |
K2 Algorithm-based Text Detection with An Adaptive Classifier Threshold | |
Hazrat Ali1  Sohail Asghar1  Khalid Iqbal1  Hong-Wei Hao1  Xu-Cheng Yin1  | |
[1] $$ | |
关键词: Bayesian Network; Adaptive Threshold; Bayesian Logistic Regression; Scene Image.; | |
DOI : | |
来源: Computer Science Journals | |
【 摘 要 】
In natural scene images, text detection is a challenging study area for dissimilar content-based image analysis tasks. In this paper, a Bayesian network scores are used to classify candidate character regions by computing posterior probabilities. The posterior probabilities are used to define an adaptive threshold to detect text in scene images with accuracy. Therefore, candidate character regions are extracted through maximally stable extremal region. K2 algorithm-based Bayesian network scores are learned by evaluating dependencies amongst features of a given candidate character region. Bayesian logistic regression classifier is trained to compute posterior probabilities to define an adaptive classifier threshold. The candidate character regions below from adaptive classifier threshold are discarded as non-character regions. Finally, text regions are detected with the use of effective text localization scheme based on geometric features. The entire system is evaluated on the ICDAR 2013 competition database. Experimental results produce competitive performance (precision, recall and harmonic mean) with the recently published algorithms.
【 授权许可】
Unknown
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201912040511272ZK.pdf | 775KB | download |