Home // ACHI 2022, The Fifteenth International Conference on Advances in Computer-Human Interactions // View article

Detection of Pinbones in Japanese Shime-saba

Authors:
Hisayoshi Ito
Oky Dicky Ardiansyah Prima
Takehiro Sasaki

Keywords: infrared imaging; bone detection; image geometry; template matching; computer vision

Abstract:
Shime-saba is a Japanese seafood marinated in salt and rice vinegar, which makes it last longer and gives it a sashimi-like flavor. The vinegar softens most bones, but pinbones remain hard and need to be removed. The food processing industry manually removes these bones. However, this process needs to be automated to cope with the shortage of human resources. This study attempts to detect the location of the tips of pinbones by using infrared imaging techniques to highlight bone features and quantifying these features based on image geometry. The shape of the response image obtained by correlating the gaussian template image to the infrared- irradiated shime-saba image revealed that the tip of the remaining bone resembled convex-up shapes. These shapes were detected by applying a quadratic surface equation to the resulting image after pre-processed, allowing the location of the tips of pinbones to be determined by picking their maxima. Future work will include a deep learning solution to improve the detection accuracy of pinbones.

Pages: 22 to 25

Copyright: Copyright (c) IARIA, 2022

Publication date: June 26, 2022

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-982-9

Location: Porto, Portugal

Dates: from June 26, 2022 to June 30, 2022