Performance analysis of platform independent image transcoders

Today many "Internet ready" devices available on the market are Web-enabled. These devices often have a low bandwidth, high latency access to the Internet that causes a bottleneck of data communication. Moreover, a number of client devices have very limited computing power and hardware/software resources to handle some of the content-rich information that a user might want to access from the network. A content transcoder is a possible solution to solve the problem caused by the deficiencies of such devices. To extend the concept further we believe a transportable content transcoder will provide more flexibility than the current static proxy solution. However, the current Internet environment is heterogeneous, and implementing such a transcoder with native programming language is not applicable. To overcome this issue, a transportable transcoder needs to be implemented using platform independence language, such as Java. Inevitably, there will be tradeoffs when using such a language in terms of performance. In this paper, we present our findings on the performance of a Java image transcoder by comparing one written in native code (C). In addition, we investigate means to optimise the performance of our Java transcoder From our results we evaluate the viability of this concept.

[1]  John R. Smith,et al.  Transcoding Internet content for heterogeneous client devices , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[2]  Helen J. Wang,et al.  ICEBERG: an Internet core network architecture for integrated communications , 2000, IEEE Wirel. Commun..

[3]  Aruna Seneviratne,et al.  The use of software agents as proxies , 2000, Proceedings ISCC 2000. Fifth IEEE Symposium on Computers and Communications.

[4]  John R. Smith,et al.  Content-based transcoding of images in the Internet , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[5]  John Wawrzynek,et al.  JPEG Quality Transcoding Using Neural Networks Trained with a Perceptual Error Measure , 1999, Neural Computation.

[6]  Ming-Ting Sun,et al.  Motion Vector Refinement for High-Performance Transcoding , 1999, IEEE Trans. Multim..

[7]  Steven McCanne,et al.  An active service framework and its application to real-time multimedia transcoding , 1998, SIGCOMM '98.

[8]  Eric A. Brewer,et al.  Adapting to network and client variability via on-demand dynamic distillation , 1996, ASPLOS VII.