Automatic Generation of Image Identifiers Based on Luminance and Parallel Processing
Recently, as the functionality of digital image acquisition devices is being improved, the commercial products with the high-performance functionality, such as smart phones and digital cameras, are being considered and utilized as an everyday commodity. As a result, it is natural that the volume of images which are collected from various paths or applications is also being enormously increased. According to this trend, the service platforms and applications, which support the functionalities necessary for image manipulation such as production, archiving and search, naturally demand the efficient management of enormous images either in independent or distributed systems. In such image management systems, an image identifier plays an important role in terms of identification of a particular image. Previous researches have been resolving problems either by applying complex methods that consume quite so much resources or by simple heuristic methods with the potential risk in terms of correspondence problem between identifiers and images. Therefore, the development of efficient and effective methods for the problem needs to be studied. In this paper, we propose a method to construct indexing of images utilizing the concept of the luminance area. The experimental evaluation of the proposed method illustrates that the proposed method satisfies the requirements for the image identification while reducing the processing cost.
KeywordsImage identifier Luminance Parallel processing
This research was supported by The Leading Human Resource Training Program of Regional Neo industry through the National Research Foundation of Korea(NRF) funded by the Ministry of Science and ICT (No. NRF-2016H1D5A1909989).
- 1.Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, online: https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/mobile-white-paper-c11-520862.html
- 2.Photo and Video Sharing Grow Online, online: http://www.pewinternet.org/2013/10/28/photo-and-video-sharing-grow-online
- 9.Hadoop 2.6 hdfs, online: https://hadoop.apache.org/docs/r2.6.0/hadoop-project-dist/hadoop-hdfs/HdfsUserGuide.html
- 10.Apache Hadoop, online: https://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#Prerequisites
- 11.HIPI: Hadoop Image Processing Interface, online: http://hipi.cs.virginia.edu
- 12.Widipedia, OpenCV, online: https://en.wikipedia.org/wiki/OpenCV
- 13.Class HipiImageBundle, online: http://hipi.cs.virginia.edu/javadoc/org/hipi/imagebundle/HipiImageBundle.html
- 14.Tool/hibImport, online: http://hipi.cs.virginia.edu/examples/hibImport.html
- 15.Class Culler, online: http://hipi.cs.virginia.edu/javadoc/org/hipi/mapreduce/Culler.html
- 16.Digital differential analyzer (graphics algorithm), online: https://en.wikipedia.org/wiki/Digital_differential_analyzer_(graphics_algorithm)
- 17.Relative luminance, online: https://en.wikipedia.org/wiki/Relative_luminance
- 18.Reinhard, E., Stark, M., Shirley, P., Ferwerda, J.: Photographic tone reproduction for digital images. ACM Trans. Graphics (TOG) 21, 267–276 (2002)Google Scholar