Material recognition by feature classification using time-of-flight camera

Abstract

Starting from the information returned by the depth sensor, different features of interest have been extracted using transforms such as Fourier, discrete cosine, Hilbert, chirp-z, and Karhunen-Loève. Such features have been used to build a training and a validation set useful to feed a classifier (J48) able to accomplish the material recognition step. The effectiveness of the proposed methodology has been experimentally tested. Good predictive accuracies of materials have been obtained. Moreover, experiments have shown that the combination of multiple transforms increases the robustness and reliability of the computed features, although the shutter value can heavily affect the prediction rates.

Material Recognition Sensor Array by Electrostatic Induction and Triboelectric Effects

“…As far as we know, except for some reports using the physical-properties of materials, such as temperature, texture, robustness, and piezoelectric properties, most material recognition reported is actual object recognition, and it needs a large amount of image data about the positions, shapes and colors of the objects. [8][9][10][11][12][13][14][15][16] Triboelectric effect was successfully used in triboelectric nanogenerators (TENG) by Wang et al [17] and, ever since then, many valuable researches have been done in improving the energy transfer efficiency, pressure, and distance sensors, selfpowered system etc. [18][19][20][21][22][23] Moreover, theoretical model serves as guidance that triboelectric output performance can be affected by several factors such as film thickness, area size, dielectric properties, and gap distance.…”

Recent Advances in 3D Data Acquisition and Processing by Time-of-Flight Camera

“…(3) Object detection helps us to monitor in sensitive areas [8], [14], [48]. 4Machine vision: industry locating, guidance and the volume forecast [35].…”

Understanding the Risks and Harms of Management of Incidental Thyroid Nodules

“…In an ACR case study, implementation of ACR white paper recommendations for incidental thyroid nodules in a large practice resulted in increased reporting of significant nodules (from 34% to 76%) and fewer recommendations for ultrasonographic workup of lesions considered to be insignificant (from 35% to 7%), with substantial cost savings of more than $300 000 for the hospital system. With upcoming Centers for Medicare & Medicaid Services mandates for implementation of decision support for determining appropriateness of imaging studies, these recommendations could readily be incorporated into decision-support systems.…”