期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2017
卷号：8
期号：4
页码：25
DOI：10.5121/sipij.2017.8403
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：In this digital world, artificial intelligence has provided solutions to many problems, likewise to encounterproblems related to digital images and operations related to the extensive set of images. We should learnhow to analyze an image, and for that, we need feature extraction of the content of that image. Imagedescription methods involve natural language processing and concepts of computer vision. The purpose ofthis work is to provide an efficient and accurate image description of an unknown image by using deeplearning methods. We propose a novel generative robust model that trains a Deep Neural Network to learnabout image features after extracting information about the content of images, for that we used the novelcombination of CNN and LSTM. We trained our model on MSCOCO dataset, which provides set ofannotations for a particular image, and after the model is fully automated, we tested it by providing rawimages. And also several experiments are performed to check efficiency and robustness of the system, forthat we have calculated BLEU Score.
关键词：Image Annotation; Feature Extraction; LSTM; Deep Learning; NLP.
Loading...
