Ruler detection for automatic scaling of fish images

Konovalov, D.A., Domingos, J.A., Bajema, C., White, R.D., and Jerry, D.R. (2017) Ruler detection for automatic scaling of fish images. In: Proceedings of the International Conference on Advances in Image Processing, pp. 90-95. From: ICAIP 2017: International Conference on Advances in Image Processing, 25-27 August 2017, Bangkok, Thailand.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: http://doi.acm.org/10.1145/3133264.31332...
 
1
3


Abstract

Fast and low-cost image collection and processing is often required in aquaculture farms for quality/size attributes and breeding programs. For example, the absolute physical dimensions of fish (in millimeters or inches) could be estimated from electronic images. The absolute scale of the photographed fish is often unknown or requires additional hardware, data- collection and/or management overheads. One cost and time effective solution is to capture the absolute scale (in pixels-per- millimeter or dots-per-inch) by including a measuring ruler in the photographed scene. To assist that type of workflow, this paper presents a relatively simple image-processing algorithm that automatically located a sufficiently large section of the ruler in a given image. The algorithm utilized the Fast Fourier Transform and was designed to be free from adjustable parameters and therefore did not require training. The algorithm was tested on 445 images of Barramundi (Asian sea bass, Lates calcarifer), where a millimeter-graded ruler was included in each image. The algorithm achieved precision of 98% (on the original, 10, 20, 70, 80 90 degree rotated images) and 95-96% on 40, 50, 60 degree rotated images. The test Barramundi images were released to public domain (on this publication) via https://github.com/dmitryako/BarraRulerDataset445.

Item ID: 51090
Item Type: Conference Item (Refereed Research Paper - E1)
Keywords: aquaculture, barramundi, computer vision, image processing, ruler detection
ISBN: 978-1-4503-5295-6
Funders: James Cook University (JCU)
Projects and Grants: JCU Division of Tropical Environment & Societies 2016 RIBG
Research Data: https://github.com/dmitryako/BarraRulerDataset445
Date Deposited: 21 Nov 2017 00:36
FoR Codes: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing @ 100%
SEO Codes: 83 ANIMAL PRODUCTION AND ANIMAL PRIMARY PRODUCTS > 8301 Fisheries - Aquaculture > 830102 Aquaculture Fin Fish (excl. Tuna) @ 100%
Downloads: Total: 3
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page