For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Extraction Method of Scallop Area from Sand Seabed Images
Koichiro ENOMOTO Masashi TODA Yasuhiro KUWAHARA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/01/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Pattern Recognition
scallop, fishery resource investigation, automatic counting, image processing,
Full Text: PDF(1.8MB)>>
The results of fishery investigations are used to estimate the catch size, times fish are caught, and future stock in the fish culture industry. In Tokoro, Japan, scallop farms are located on gravel and sand seabed. Seabed images are necessary to visually estimate the number of scallops of a particular farm. However, there is no automatic technology for measuring resources quantities and so the current investigation technique is the manual measurement by experts. We propose a method to extract scallop areas from images of sand seabed. In the sand field, we can see only the shelly rim because the scallop is covered with sand and opens and closes its shell while it is alive and breathing. We propose a method to extract the shelly rim areas under varying illumination, extract the scallop areas using the shelly rims based on professional knowledge of the sand field, explain the results, and evaluate the method's effectiveness.