A Comparative Study of the Complexities of Neural Network Based Focal-Plane Image Compression Schemes (スマート信号処理とその画像・音声処理への応用論文小特集)
スポンサーリンク
概要
- 論文の詳細を見る
Block coding of images can be implemented efficiently by neural networks. Kohonen self-organizing maps (SOMs) have been previously proposed for the implementation of full-search vector quantizers, and multilayer perceptrons (MLPs) have been proposed for the implementation of linear-transform-based vector quantizers. In this article, we introduce a complexity function that estimates how many CMOS transistors the proposed solutions will require, if they are implemented with analog hardware that is typical of focal-plane solutions for modern digital cameras. We also propose the use of non-linear MLPs with Gaussian, hyperbolic tangent, or polynomial Kernel functions, to implement new complexity-constrained vector quantizers. The complexity function is applied to several SOMs and MLPs (linear and non-linear). Numerical simulation results show that MLPs achieve complexity reduction factors around 15 with respect to the SOMs, while not losing more than 1.5 dB in reconstruction quality or 0.04 bpp in the minimal bit rate.
- 社団法人電子情報通信学会の論文
- 2005-11-01
著者
-
Mitra Sanjit
Department Of Electrical And Computer Engineering University Of California
-
Gomes Jose
Departamento De Farmacologia Insituto De Biociencias De Botucatu
-
Gomes Jose
Department Of Electrical Engineering Federal University Of Rio De Janeiro
-
MITRA Sanjit
Department of Electrical and Computer Engineering, University of California
関連論文
- Studies on Anti-Allergic Constituents in the Leaves and Stems of Anchietia salutaris var. martiana (Violaceae)
- A Statistical Model-Based V/UV Decision under Background Noise Environments(Speech and Hearing)
- A Comparative Study of the Complexities of Neural Network Based Focal-Plane Image Compression Schemes (スマート信号処理とその画像・音声処理への応用論文小特集)
- Multiband Vector Quantization Based on Inner Product for Wideband Speech Coding(Speech and Hearing)