Multimedia data is expanding exponentially. The speedup growth of technology combined with storage capabilities and reasonable capacity has resulted in an explosion in multimedia availability and applications. Most data is available in the form of images and videos. Today a large amount of image data is produced through digital cameras, mobile phones and other sources. Processing this large set of images involves very complex and frequent operations in a large database that lead to challenges to improve query time and data storage capacity. Many image processing algorithms and computer vision are applicable to extensive data tasks. Mostly to run image processing algorithms on large data sets that are currently limited to the computing power of a single computer system. In order to handle such a huge data, cloud computing is used but storing data on cloud need security. Encrypting a complete image is a time consuming task to overcome the problem selective encryption is proposed based on MapReduce, Fuzzy K-Means Clustering and Data Encryption Standard(DES). The proposed scheme performs the feature extraction using MapReduce parallel speeding up the process ten times faster if ten Hadoop cluster nodes are involved. On the extracted features Fuzzy KMeans clustering is applied to segment the image and identify the region of interest(ROI). DES is applied on ROI to secure the image.
Published In:IJCAT Journal Volume 6, Issue 4
Date of Publication : April 2019
Pages : 21-26
Figures :02
Tables :--
Sayyada Fahmeeda Sultana : Department of Computer Science & Engineering,
PDA College of Engineering, Gulbarga, India.
Dr. Shubhangi D C : Department of Computer Science, VTU PG Center,
Gulbarga, India.
A MapReduce based image Segmentation scheme is proposed that uses Fuzzy K-Means clustering to segment image into foreground and background. MapReduce perform feature extraction by first reading numerical equivalent of image as text input, then splits the input into blocks using Mapper process, the reducer process counts the number of different pixels values and return the sum of different pixels in each block with block number. This Reducer generated output gets as input to Fuzzy K-Means clustering and which gives two clusters, these are the foreground and background blocks of image. Then DES encryption algorithm is applied on foreground image. The proposed scheme is faster then executed on local machine with the utilization of parallel processes through the use of Hadoop cluster.
[1]. White, B., Yeh, T., Lin, J., & Davis, L. (2010, July). Web-scale computer vision using mapreduce for multimedia data mining. In Proceedings of the Tenth International Workshop on Multimedia Data Mining (p. 9). ACM. [2]. Pereira, R., Azambuja, M., Breitman, K., & Endler, M. (2010, July). An architecture for distributed high performance video processing in the cloud. In 2010 IEEE 3rd international conference on cloud computing (pp. 482-489). IEEE.
[3]. Hawick, K. A., Coddington, P. D., & James, H. A. (2003). Distributed frameworks and parallel algorithms for processing large-scale geographic data. Parallel Computing, 29(10), 1297-1333.
[4]. Amazon.com Inc. Amazon elastic compute cloud (amazon ec2), October 2012 [5]. Lv, Z., Hu, Y., Zhong, H., Wu, J., Li, B., & Zhao, H. (2010, October). Parallel k-means clustering of remote sensing images based on mapreduce. In International Conference on Web Information Systems and Mining (pp. 162-170). Springer, Berlin, Heidelberg. [6]. Kumar, S., & Srivastava, S. (2014). Image encryption using simplified data encryption standard (S-DES). International Journal of Computer Applications, 104(2). [7]. Sabarad, A. K., Kankudti, M. H., Meena, S. M., & Husain, M. (2015, February). Color and Texture Feature Extraction using Apache Hadoop Framework. In 2015 International Conference on Computing Communication Control and Automation (pp. 585-588). IEEE. [8]. Kong, Z., Li, T., Luo, J., & Xu, S. (2019). Automatic Tissue Image Segmentation Based on Image Processing and Deep Learning. Journal of healthcare engineering, 2019. [9]. Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I. (2010). Spark: Cluster computing with working sets. HotCloud, 10(10-10), 95. [10]. Sardar, T. H., & Ansari, Z. (2018). An analysis of mapreduce efficiency in document clustering using parallel k-means algorithm. Future Computing and Informatics Journal, 3(2), 200-209.
[11]. Sardar, T. H., & Ansari, Z. (2018). Partition based clustering of large datasets using MapReduce framework: An analysis of recent themes and directions. Future Computing and Informatics Journal. [12]. Coppersmith, D. (1994). The Data Encryption Standard (DES) and its strength against attacks. IBM journal of research and development, 38(3), 243-250. [13]. Hartigan, J. A., & Wong, M. A. (1979). Algorithm AS 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), 28(1), 100-108. [14]. Dean, J., & Ghemawat, S. (2008). MapReduce: simplified data processing on large clusters. Communications of the ACM, 51(1), 107-113. [15]. Amazon, E. C. (2015). Amazon web services. Available in: http://aws. amazon. com/es/ec2/(November 2012). [16]. Joshi, S. B. (2012, April). Apache hadoop performance-tuning methodologies and best practices. In Proceedings of the 3rd acm/spec international conference on performance engineering (pp. 241-242). ACM. [17]. Koitzsch, K. (2017). Standard Toolkits for Hadoop and Analytics. In Pro Hadoop Data Analytics (pp. 43-62). Apress, Berkeley, CA.
