计算机工程与应用2019，Vol.55Issue(2)：121-127,7.DOI:10.3778/j.issn.1002-8331.1709-0422
基于Sentence-Rank的图像句子标注
Image Sentence Annotation Based on Sentence-Rank Algorithm
摘要
Abstract
In the traditional image semantic sentence annotation, sentence templates are used to describe the content of image. However, it is hard to meet the logic of language using the traditional method. Aiming at this problem, this paper proposes to describe the image content by selecting an optimal sentence from the corpus , and design the Sentence-Rank algorithm with the N -gram algorithm to generate the annotated sentence. Firstly, the HSV-LBP-HOG fusion feature with the best performance is used for image classification, the image markings are obtained. Then, it uses the string matching algorithm to list all the sentences with the marked keywords from the corpus and sorts the obtained sentences by Sentence-Rank algorithm, and selects the highest rated sentence to describe the image. The experimental results show that the anno-tation sentence obtained by this method has lower perplexity, and solves the linguistic logic problem of sentences better.关键词
机器学习/自然语言处理/特征融合/Sentence-Rank/N -gramKey words
machine learning/natural language processing/feature fusion/Sentence-Rank/N -gram分类
信息技术与安全科学引用本文复制引用
徐守坤,徐坚,李宁,周佳,刘楚秋..基于Sentence-Rank的图像句子标注[J].计算机工程与应用,2019,55(2):121-127,7.基金项目
国家自然科学基金(No.71503260). （No.71503260）
