Colour Object Classification Using the Fusion of Visible and Near-Infrared Spectra

Shin, Hee-Sang; Reyes, Napoleon H.; Barczak, Andre L. C.; Chan, Chee Seng

doi:10.1007/978-3-642-15246-7_46

Cited by 5 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As identified in Section 2 , there are only a few datasets that span both the visible and NIR regions. The information in NIR is valuable for material classification [ 45 , 46 , 47 ], and the identification of textile fibers [ 48 ] and minerals [ 49 ]. Although some of the hyperspectral datasets provide information in the NIR region, they are either for specific samples, as in [ 41 , 42 , 43 ], or consist of outdoor scenes with many objects, as in [ 28 , 32 ].…”

Section: Comparison Of Hytexila With Existing Hyperspectral Datasementioning

confidence: 99%

HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images

Khan

Mihoubi

Mathon

et al. 2018

Sensors

View full text Add to dashboard Cite

We present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study spatial and spectral textures. In this paper we discuss the calibration of the data and the method for addressing the distortions during image acquisition. We provide a spectral analysis based on non-negative matrix factorization to quantify the spectral complexity of the samples and extend local binary pattern operators to the hyperspectral texture analysis. The results demonstrate that although the spectral complexity of each of the textures is generally low, increasing the number of bands permits better texture classification, with the opponent band local binary pattern feature giving the best performance.

show abstract

Section: Comparison Of Hytexila With Existing Hyperspectral Datasementioning

confidence: 99%

HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images

Khan

Mihoubi

Mathon

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

Adaptive Colour Calibration for Object Tracking under Spatially-Varying Illumination Environments

Shin

Reyes

Barczak

2011

Neural Information Processing

View full text Add to dashboard Cite

Proposal for a New Separation Method for Reproducing Images with Properties in the Visible and Near-Infrared Spectrum

Gršić,

Plehati,

Bogović

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Painting dyes and artworks exhibit duality with different states in the visible (V) and near-infrared (Z) spectrum. “V” denotes the solar spectrum ranging from 400 to 750 nm, while “Z” indicates the solar spectrum up to 1000 nm. The infrared state of an artwork can be an independent, “hidden” image. The paper demonstrates a new procedure of graphic preparation for the separation of process inks for reproducing artworks in monographs, with a focus on integration in the visible and near-infrared spectrum. The practical part of the paper uses the Projectina PAG B50 forensic scanner, which is equipped with 24 filters for blocking light from 220 to 1000 nm. Image reproduction involves photography of artwork in RGB, then conversion into CMY, with the addition of K from the Z image. “VZ” separation is introduced into the reproduction of the artwork, simulating the dual states of the original artwork. The GCR procedure is applied by subtracting CMY but based on information for the K component that is equal in the Z image. This process provides a deeper understanding of artworks and offers extended information about their state in the visible and near-infrared part of the spectrum.

show abstract

Colour Object Classification Using the Fusion of Visible and Near-Infrared Spectra

Cited by 5 publications

References 17 publications

HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images

HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images

Adaptive Colour Calibration for Object Tracking under Spatially-Varying Illumination Environments

Proposal for a New Separation Method for Reproducing Images with Properties in the Visible and Near-Infrared Spectrum

Contact Info

Product

Resources

About