TY - GEN
T1 - Low intensity rgb texture enhancement based on near infrared image using perceptual information
AU - Lee, Jaelin
AU - Park, Younghyeon
AU - Jeon, Byeungwoo
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12
Y1 - 2018/12
N2 - The texture information in the near-infrared (NIR) image is known to be effective in improving the visibility of visible-range image, thus, texture enhancement using NIR images has been investigated for the low contrast area. Since image contrast enhancement ultimately targets for human, many methods have been developed considering the Human Visual System (HVS)'s responses to luminance. In a low brightness region, the Just-Noticeable-Difference (JND), which statistically reflects sensitivity characteristics of human eye, is high, thus noise is relatively hard to notice. However, after the contrast enhancement, the noise is well recognized because the JND value decreases. In this paper, JND with respect to the background brightness is computed to properly address the characteristic of the image. We propose an image contrast enhancement method that adds texture components of NIR images to RGB image with using JND value obtained from RGB images as weights.
AB - The texture information in the near-infrared (NIR) image is known to be effective in improving the visibility of visible-range image, thus, texture enhancement using NIR images has been investigated for the low contrast area. Since image contrast enhancement ultimately targets for human, many methods have been developed considering the Human Visual System (HVS)'s responses to luminance. In a low brightness region, the Just-Noticeable-Difference (JND), which statistically reflects sensitivity characteristics of human eye, is high, thus noise is relatively hard to notice. However, after the contrast enhancement, the noise is well recognized because the JND value decreases. In this paper, JND with respect to the background brightness is computed to properly address the characteristic of the image. We propose an image contrast enhancement method that adds texture components of NIR images to RGB image with using JND value obtained from RGB images as weights.
KW - Contrast Enhancement
KW - Just Noticeable Difference
KW - RGB-NIR Enhancement
KW - Texture Enhancement
UR - https://www.scopus.com/pages/publications/85070355557
U2 - 10.1109/ICCCAS.2018.8769208
DO - 10.1109/ICCCAS.2018.8769208
M3 - Conference contribution
AN - SCOPUS:85070355557
T3 - 10th International Conference on Communications, Circuits and Systems, ICCCAS 2018
SP - 422
EP - 425
BT - 10th International Conference on Communications, Circuits and Systems, ICCCAS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Communications, Circuits and Systems, ICCCAS 2018
Y2 - 22 December 2018 through 24 December 2018
ER -