|
|
|
|
|
|
Research on Spectral Reflectance Estimation Using Locally Weighted Linear Regression within k-Nearest Neighbors |
LU De-jun, CUAN Kai-xuan, ZHANG Wei-feng* |
School of Mathematics & Informatics, South China Agricultural University, Guangzhou 510642, China |
|
|
Abstract Many real applications require accurate color reproduction, such as textile, printing, art painting archiving and online product exhibition. The most accurate and informative way to represent a natural object’s color is to use its spectral reflectance. However, the very professional measuring instrument of spectrophotometer has the drawbacks of being expensive and having low measuring resolution and slow measuring speed. As digital cameras have become the most widely used devices for color acquisition, developing accurate reflectance estimation methods from RGB responses has received increasing attention. The aim of spectral reflectance estimation is to build estimation function between RGB tristimulus values and the spectral reflectance vector from training samples. Regression methods have been widely used for this problem. Recent studies have shown that natural objects’ reflectance resides on a lower dimensional submanifold which is embedded in the high-dimensional ambient Euclidean space. Due to the limitation of high dimensional and low training sample size, previous global regression approaches could not exploit the local manifold structure well and are prone to be over-fitting. Local linear regression method can improve the problem of overfitting, but the local learning method is susceptible to the influence of outliers, which will lead to under-fitting. Aiming at this problem, this paper proposes a spectral reflectance estimation method based on locally weighted linear regression, which gives different weights to each local training sample within a k-nearest neighbor constraint. The experimental results show that the method based on locally weighted linear regression can make more effective use of local information, alleviate the over-fitting and under-fitting and reconstruct the spectral reflectance more accurately.
|
Received: 2017-10-24
Accepted: 2018-03-06
|
|
Corresponding Authors:
ZHANG Wei-feng
E-mail: zhangwf@scau.edu.cn
|
|
[1] Fu X, Liao Y, Zeng D, et al. IEEE Transactions on Image Processing, 2015, 24(12): 4965.
[2] Matsuoka R, Baba T, Okuda M. Proc IEEE International Conference on Image Processing, 2015. 407.
[3] Eckhard T, Valero E M, Hernandez-Andres J, et al. Applied Optics, 2014, 53(4): 709.
[4] Xu P, Xu H, Diao C, et al. Applied Optics, 2017, 56(30): 8461.
[5] Van Trigt C. Journal of the Optical Society of America A, 1990, 7(10): 1891.
[6] Heikkinen V, Camara C, Hirvonen T, et al. Journal of the Optical Society of America A, 2016, 33(6): 1095.
[7] Liu Z, Liu Q, Gao G, et al. Optics Express, 2017, 25(11): 12435.
[8] Lansel S, Parmar M, Wandell B A. Proc. SPIE, Computation Iamging Ⅶ, 2009, 7246: 72460D.
[9] Zhang W F, Tang G, Dai D Q, et al. Optics Letters, 2011, 36(19): 3933-5.
[10] Zhang W F, Yang P, Dai D Q, et al. Proc 9th International Symposium on Neural Networks (ISNN), 2012, Part 1: 116.
[11] Zhang W F, Lu D J. Proc IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2015. 2996.
[12] Cleveland W S, Devlin S J. Journal of the American Statistical Association, 1988, 83(403): 596.
[13] Spectral Color Research Group, University of Eastern Finland, http://www.uef.fi/web/spectral/-spectral-database.
[14] Barnard K, Martin L, Funt B, et al. Color Research & Application,2002, 27(3): 147. |
[1] |
MA Yuan, LI Ri-hao, ZHANG Wei-feng*. Research on the Training Samples Selection for Spectral Reflectance
Reconstruction Based on Improved Weighted Euclidean Distance[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3924-3929. |
[2] |
JIANG Wan-li1, 2, SHI Jun-sheng1, 2*, JI Ming-jiang1, 2. Establishment of Visible and NIR Spectral Reflectance Database of Plant Leaves and Principal Component Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2366-2373. |
[3] |
JIANG Dan-yang1, WANG Zhi-feng1*, GAO Cheng1, 2, LI Chang-jun1. Spectral Reflectance Reconstruction With Color Constancy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1044-1048. |
[4] |
LI Fu-hao, LI Chang-jun*. Spectral Reflectance Reconstruction Based on Camera Raw RGB Using Weighted Third-Order Polynomial and Wiener Estimation[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3281-3285. |
[5] |
LIU Si-xiang1, 2, FAN Wei-hua1, 2, GUO Hui1, ZHAO Hui1, JIN Qing-hui1, 2*. Application of Machine Learning in Determination of Nitrate Nitrogen Based on Ultraviolet Spectrophotometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(04): 1179-1182. |
[6] |
YANG Ping1, LIAO Ning-fang1, SONG Hong2 . Study of Approaches to Spectral Reflectance Reconstruction Based on Digital Camera [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(05): 1176-1180. |
|
|
|
|