Reaching behind Specular Highlights by Registration of Two Images of Broiler Viscera

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

The manual postmortem inspection of broilers and their viscera is becoming a bottleneck as the slaughter rate increases. Computer vision can assist veterinarians during the inspection, but specular highlights can hide crucial details when inspecting for diseases on the viscera set. This study aims to restore details behind these specular highlights by capturing two images of the same viscera using shifting light positions. The dataset consists of images captured in-line at a poultry processing plant. The method achieves an average SSIM score of 0.96 over a test set of 100 image sets. The result is visually pleasing images with correct textural information instead of specular highlights.
Original languageEnglish
Title of host publicationProceedings of the 14th Asian Conference on Computer Vision
Publication date2019
Publication statusAccepted/In press - 2019

Fingerprint

Inspection
Poultry
Computer vision
Processing

Cite this

Jørgensen, A., Pedersen, M., Gade, R., Fagertun, J., & Moeslund, T. B. (Accepted/In press). Reaching behind Specular Highlights by Registration of Two Images of Broiler Viscera. In Proceedings of the 14th Asian Conference on Computer Vision
@inproceedings{3dd422f225bf424bbbdaaa42153b141f,
title = "Reaching behind Specular Highlights by Registration of Two Images of Broiler Viscera",
abstract = "The manual postmortem inspection of broilers and their viscera is becoming a bottleneck as the slaughter rate increases. Computer vision can assist veterinarians during the inspection, but specular highlights can hide crucial details when inspecting for diseases on the viscera set. This study aims to restore details behind these specular highlights by capturing two images of the same viscera using shifting light positions. The dataset consists of images captured in-line at a poultry processing plant. The method achieves an average SSIM score of 0.96 over a test set of 100 image sets. The result is visually pleasing images with correct textural information instead of specular highlights.",
author = "Anders J{\o}rgensen and Malte Pedersen and Rikke Gade and Jens Fagertun and Moeslund, {Thomas B.}",
year = "2019",
language = "English",
booktitle = "Proceedings of the 14th Asian Conference on Computer Vision",

}

Reaching behind Specular Highlights by Registration of Two Images of Broiler Viscera. / Jørgensen, Anders; Pedersen, Malte; Gade, Rikke; Fagertun, Jens; Moeslund, Thomas B.

Proceedings of the 14th Asian Conference on Computer Vision. 2019.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Reaching behind Specular Highlights by Registration of Two Images of Broiler Viscera

AU - Jørgensen, Anders

AU - Pedersen, Malte

AU - Gade, Rikke

AU - Fagertun, Jens

AU - Moeslund, Thomas B.

PY - 2019

Y1 - 2019

N2 - The manual postmortem inspection of broilers and their viscera is becoming a bottleneck as the slaughter rate increases. Computer vision can assist veterinarians during the inspection, but specular highlights can hide crucial details when inspecting for diseases on the viscera set. This study aims to restore details behind these specular highlights by capturing two images of the same viscera using shifting light positions. The dataset consists of images captured in-line at a poultry processing plant. The method achieves an average SSIM score of 0.96 over a test set of 100 image sets. The result is visually pleasing images with correct textural information instead of specular highlights.

AB - The manual postmortem inspection of broilers and their viscera is becoming a bottleneck as the slaughter rate increases. Computer vision can assist veterinarians during the inspection, but specular highlights can hide crucial details when inspecting for diseases on the viscera set. This study aims to restore details behind these specular highlights by capturing two images of the same viscera using shifting light positions. The dataset consists of images captured in-line at a poultry processing plant. The method achieves an average SSIM score of 0.96 over a test set of 100 image sets. The result is visually pleasing images with correct textural information instead of specular highlights.

M3 - Article in proceeding

BT - Proceedings of the 14th Asian Conference on Computer Vision

ER -