International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 129 | Views: 267 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Computer Science & Engineering | India | Volume 5 Issue 11, November 2016 | Popularity: 6.7 / 10


     

Generating Captions for News Domain using Randomization Technique

Kalyani Zinjurde, Ena Jain


Abstract: Many of the search engines deployed on the web retrieve images without analyzing their content, simply by matching their user queries against their collocated textual information. This limits the applicability of search engines, a great deal of work has focused on the development of generating descriptive words for an image automatically. Images are automatically captioned in two stagesContent selection and surface realization. Content selection suggests s for the image using image annotation model. whereas, surface realization technique uses extractive and ive methods to generate caption. the approach is to analyze the performance of captioned images using phrases rather than words. Randomization improves the generation process.


Keywords: Image annotation Process, Text annotation Process, content selection, stemming process, stop word removal, surface realization, caption formation


Edition: Volume 5 Issue 11, November 2016


Pages: 798 - 804




Text copied to Clipboard!
Kalyani Zinjurde, Ena Jain, "Generating Captions for News Domain using Randomization Technique", International Journal of Science and Research (IJSR), Volume 5 Issue 11, November 2016, pp. 798-804, https://www.ijsr.net/getabstract.php?paperid=ART20162915