A New Perspective on Material Classification and Ink Identification

Shiradkar, Rakesh; Shen, Li; Landon, George V.; Ong, Sim Heng; Tan, Ping

doi:10.1109/cvpr.2014.291

Cited by 12 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to understand whether the training data is biased, the feature vectors of the four materials used in the experiments are investigated. Each material used in the experiments has its specific property on reflectance [ 28 ], which can be shown in Figure 9 . Figure 9 plots the first four feature vectors of the four materials.…”

Section: Discussionmentioning

confidence: 99%

Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Yao

Xin

2023

Sensors

View full text Add to dashboard Cite

Spectral reflectance reconstruction for multispectral images (such as Weiner estimation) may perform sub-optimally when the object being measured has a texture that is not in the training set. The accuracy of the reconstruction is significantly lower without training samples. We propose an improved reflectance reconstruction method based on L1-norm penalization to solve this issue. Using L1-norm, our method can provide the transformation matrix with the favorable sparse property, which can help to achieve better results when measuring the unseen samples. We verify the proposed method by reconstructing spectral reflection for four types of materials (cotton, paper, polyester, and nylon) captured by a multispectral imaging system. Each of the materials has its texture and there are 204 samples in each of the materials/textures in the experiments. The experimental results show that when the texture is not included in the training dataset, L1-norm can achieve better results compared with existing methods using colorimetric measure (i.e., color difference) and shows consistent accuracy across four kinds of materials.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Yao

Xin

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Founded on this observation, similarities and discrepancies among the inks were detected based on their similar or different optical behavior. Computational analysis was used to determine slight differences among inks and improve their characterization so that a better understanding of inks and texts could be achieved [30].…”

Section: Image Processing and Image Analysismentioning

confidence: 99%

Contemporary approach in the study of a Byzantine-illuminated manuscript on parchment

Kokla

2021

Eur. Phys. J. Plus

View full text Add to dashboard Cite

The aim of this study was the application of image-based techniques on the texts and painted elements of a manuscript whose date of manufacture is attributable to the twelfth century. The application of the proposed methodology resulted in documentation of the ink and pigment types used, the change on writings, the repainting on some old initial letters with more artistic initials of later times, as well as, later changes on the illuminations of the manuscript. A large quantity of information was recovered applying imaging techniques in different wavelength bands, which was combined with the historical and paleographical knowledge, while some of knowledge was evaluated using targeted scanning electron microscopy with energy-dispersive X-ray (SEM/EDX) analysis of chosen inks and pigments. Furthermore, computational visual analysis was applied on the multispectral images in order to investigate the range of black inks used on an entire page of the manuscript. In this way, it is possible to identify all inks found on all pages of the manuscript. Thus, the imaging techniques can play a crucial role in the study of materials on a low budget, without expensive analytical techniques being required. The proposed methodology provided important information, not only on the characterization of the manufacture materials but on their preservation conditions, as well. The documented preservation status of the inks and pigments allowed the application of more precise conservation treatments under full control.

show abstract

“…Recently, Shiradkar et al proposed ink classification using 1D BRDF slices. 26 As described above, Gu and Liu 5 propose per-pixel material classification using spectral BRDF images captured with coded illumination. More details on their capture system are provided in the next section.…”

Section: Materials Classificationmentioning

confidence: 99%

Learning Optimal Incident Illumination using Spectral Bidirectional Reflectance Distribution Function Images for Material Classification

Skaff¹,

Tin²,

Martinello³

2015

jist

View full text Add to dashboard Cite

This article introduces a novel algorithm to learn optimal incident illumination for material classification using spectral bidirectional reflectance distribution function (BRDF) images. The method performs a joint selection of incident angle and spectral band in two steps: (1) clustering and selecting incident angles using statistics on the spectral BRDF images for a specific material, and (2) searching for the optimal angles and spectral bands that maximize material discriminability, which we measure in classification performance. The benefits of reducing the number of incident illumination angles include improving material classification, reducing computational time and storage, and allowing for a less cumbersome and potentially mobile imaging system. The authors show that their approach provides comparable material classification performance when using a reduced number of incident illuminations as compared with when using a larger number. They also compare their approach with prior work.

show abstract

A New Perspective on Material Classification and Ink Identification

Cited by 12 publications

References 16 publications

Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Contemporary approach in the study of a Byzantine-illuminated manuscript on parchment

Learning Optimal Incident Illumination using Spectral Bidirectional Reflectance Distribution Function Images for Material Classification

Contact Info

Product

Resources

About