Hardware realization of higher-order CMAC model for color calibration

Jar Shone Ker, Yau-Hwang Kuo, Bin-Da Liu

研究成果: Paper

10 引文 (Scopus)

摘要

The process of eliminating color errors from the gamut mismatch, resolution conversion, quantization and non-linearity between scanner and printer is usually recognized as an essential issue of color reproduction. To efficiently calibrate the non-linearity between scanning/printing devices, we present a linear systolic array architecture to realize the higher-order CMAC neural network model and propose an extended direct weight cell address mapping scheme for weight retrieving. This mapping scheme exhibits fast computation speed in generating weight cell addresses. Some experiments are performed to evaluate the approximation capability of the higher-order CMAC neural network models. It is shown that the CMAC model behaves well for those trained regions over the input space and exhibits smooth approximation for those untrained regions over the input space.

原文English
頁面1656-1661
頁數6
出版狀態Published - 1995 十二月 1
事件Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
持續時間: 1995 十一月 271995 十二月 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
城市Perth, Aust
期間95-11-2795-12-01

指紋

Calibration
Color
Hardware
Neural networks
Systolic arrays
Printing
Scanning
Experiments

All Science Journal Classification (ASJC) codes

  • Software

引用此文

Ker, J. S., Kuo, Y-H., & Liu, B-D. (1995). Hardware realization of higher-order CMAC model for color calibration. 1656-1661. 論文發表於 Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .
Ker, Jar Shone ; Kuo, Yau-Hwang ; Liu, Bin-Da. / Hardware realization of higher-order CMAC model for color calibration. 論文發表於 Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .6 p.
@conference{18b0318d0bd6497585a5de3c8dfccfba,
title = "Hardware realization of higher-order CMAC model for color calibration",
abstract = "The process of eliminating color errors from the gamut mismatch, resolution conversion, quantization and non-linearity between scanner and printer is usually recognized as an essential issue of color reproduction. To efficiently calibrate the non-linearity between scanning/printing devices, we present a linear systolic array architecture to realize the higher-order CMAC neural network model and propose an extended direct weight cell address mapping scheme for weight retrieving. This mapping scheme exhibits fast computation speed in generating weight cell addresses. Some experiments are performed to evaluate the approximation capability of the higher-order CMAC neural network models. It is shown that the CMAC model behaves well for those trained regions over the input space and exhibits smooth approximation for those untrained regions over the input space.",
author = "Ker, {Jar Shone} and Yau-Hwang Kuo and Bin-Da Liu",
year = "1995",
month = "12",
day = "1",
language = "English",
pages = "1656--1661",
note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

Ker, JS, Kuo, Y-H & Liu, B-D 1995, 'Hardware realization of higher-order CMAC model for color calibration', 論文發表於 Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95-11-27 - 95-12-01 頁 1656-1661.

Hardware realization of higher-order CMAC model for color calibration. / Ker, Jar Shone; Kuo, Yau-Hwang; Liu, Bin-Da.

1995. 1656-1661 論文發表於 Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .

研究成果: Paper

TY - CONF

T1 - Hardware realization of higher-order CMAC model for color calibration

AU - Ker, Jar Shone

AU - Kuo, Yau-Hwang

AU - Liu, Bin-Da

PY - 1995/12/1

Y1 - 1995/12/1

N2 - The process of eliminating color errors from the gamut mismatch, resolution conversion, quantization and non-linearity between scanner and printer is usually recognized as an essential issue of color reproduction. To efficiently calibrate the non-linearity between scanning/printing devices, we present a linear systolic array architecture to realize the higher-order CMAC neural network model and propose an extended direct weight cell address mapping scheme for weight retrieving. This mapping scheme exhibits fast computation speed in generating weight cell addresses. Some experiments are performed to evaluate the approximation capability of the higher-order CMAC neural network models. It is shown that the CMAC model behaves well for those trained regions over the input space and exhibits smooth approximation for those untrained regions over the input space.

AB - The process of eliminating color errors from the gamut mismatch, resolution conversion, quantization and non-linearity between scanner and printer is usually recognized as an essential issue of color reproduction. To efficiently calibrate the non-linearity between scanning/printing devices, we present a linear systolic array architecture to realize the higher-order CMAC neural network model and propose an extended direct weight cell address mapping scheme for weight retrieving. This mapping scheme exhibits fast computation speed in generating weight cell addresses. Some experiments are performed to evaluate the approximation capability of the higher-order CMAC neural network models. It is shown that the CMAC model behaves well for those trained regions over the input space and exhibits smooth approximation for those untrained regions over the input space.

UR - http://www.scopus.com/inward/record.url?scp=0029517705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029517705&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029517705

SP - 1656

EP - 1661

ER -

Ker JS, Kuo Y-H, Liu B-D. Hardware realization of higher-order CMAC model for color calibration. 1995. 論文發表於 Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, .