Spark is an open-source big data processing framework which is one of the emerging platforms. Spark can be employed to process large datasets in distributed environment. Spark has a programming model which is similar to MapReduce that expands itself with a property of data sharing abstraction called resilient distributed datasets. This paper illustrates how an Apache Spark framework is most effectively used as an incisive solution for addressing the big data image-processing problem of generating mosaics with the broad range of libraries inbuilt in it. In this paper, we evaluated the performance of Apache Spark using image-processing technique and compared its performance with Scalding. The results imply that for larger datasets Spark runs 17× times faster than Scalding.
CITATION STYLE
Neralla, S. R. G. (2019). Generation of photographic mosaic using apache spark and scalding for image processing. In Lecture Notes in Electrical Engineering (Vol. 476, pp. 233–248). Springer Verlag. https://doi.org/10.1007/978-981-10-8234-4_21
Mendeley helps you to discover research relevant for your work.