@ARTICLE\{IMM2014-06772,
    author       = "S. Sharifzadeh and L. H. Clemmensen and C. Borggaard and S. St{\o}ier and B. K. Ersb{\o}ll",
    title        = "Supervised feature selection for linear and non-linear regression of Lab color from multispectral images of meat",
    year         = "2014",
    keywords     = "Lab color space, Multispectral imaging, Sparse regression, Artificial neural networks, Support vector machine, Supervised feature selection",
    pages        = "211-217",
    journal      = "Engineering Applications of Artificial Intelligence",
    volume       = "27",
    editor       = "",
    number       = "",
    publisher    = "",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/6772-full.html",
    abstract     = "In food quality monitoring, color is an important indicator factor of quality. The CIELab (L\&\#8270;a\&\#8270;b\&\#8270;) color space as a device independent color space is an appropriate means in this case. The commonly used colorimeter instruments can neither measure the L\&\#8270;a\&\#8270;b color in a wide area over the target surface nor in a contact-less mode. However, developing algorithms for conversion of food items images into L\&\#8270;a\&\#8270;b color space can solve both of these issues. This paper addresses the problem of L\&\#8270;a\&\#8270;b color prediction from multispectral images of different types of raw meat. The efficiency of using multispectral images instead of the standard {RGB} is investigated. In addition, it is demonstrated that due to the fiber structure and transparency of raw meat, the prediction models built on the standard color patches do not work for raw meat test samples. As a result, multispectral images of different types of meat samples (430–970 nm) were used for training and testing of the L\&\#8270;a\&\#8270;b prediction models. Finding a sparse solution or the use of a minimum number of bands is of particular interest to make an industrial vision set-up simpler and cost effective. In this paper, a wide range of linear, non-linear, kernel-based regression and sparse regression methods are compared. In order to improve the prediction results of these models, we propose a supervised feature selection strategy which is compared with the Principal component analysis (PCA) as a pre-processing step. The results showed that the proposed feature selection method outperforms the {PCA} for both linear and non-linear methods. The highest performance was obtained by linear ridge regression applied on the selected features from the proposed Elastic net (EN) -based feature selection strategy. All the best models use a reduced number of wavelengths for each of the L\&\#8270;a\&\#8270;b components."
}