Paper Info
Title
DCT-based characterization of milk products using diffuse reflectance images
Abstract
We propose to use the two-dimensional Discrete Cosine Transform (DCT) for decomposition of diffuse reflectance images of laser illumination on milk products in different wavelengths. Based on the prior knowledge about the characteristics of the images, the initial feature vectors are formed at each wavelength. The low order DCT coefficients are used to quantify the optical properties. In addition, the entropy information of the higher order DCT coefficients is used to include the illumination interference effects near the incident point. The discrimination powers of the features are computed and used to do wavelength and feature selection. Using the selected features of just one band, we could characterize and discriminate eight different milk products. Comparing this result with the current characterization method based of a fitted log-log linear model, shows that the proposed method can discriminate milk from yogurt products better.
Year
DOI
Venue
2013
10.1109/ICDSP.2013.6622669
DSP
Keywords
Field
DocType
diffuse reflectance images,image processing,discrete cosine transform,light interference,diffuse reflectance image,two-dimensional discrete cosine transform,milk products,optical properties,dct-based characterization,discrete cosine transforms,discrimination power,illumination interference,feature extraction,yogurt products,dairy products,entropy information,feature vectors,feature selection,entropy,laser illumination,log-log linear model,reflectivity,optical imaging
Computer vision,Feature vector,Pattern recognition,Feature selection,Discrete cosine transform,Image processing,Feature extraction,Interference (wave propagation),Artificial intelligence,Entropy (information theory),Mathematics,Wavelength
Conference
ISSN
Citations 
PageRank 
1546-1874
0
0.34
References 
Authors
3
4
Name
Order
Citations
PageRank
Sara Sharifzadeh1182.98
Jacob L. Skytte200.34
Line Harder Clemmensen3346.52
Bjarne Ersbøll445038.06