Home // VISUAL 2016, The First International Conference on Applications and Systems of Visual Paradigms // View article

A Method of Object Identification Based on Sea Image Processing

Authors:
Jing Zhang
Shaoyan Rao
Tianchi Zhang

Keywords: dolphin identification; sea image processing; target image segmentation; growth model; SIFT feature matching algorithm

Abstract:
Currently, the technological evolution has led to the birth of the image processing discipline which processes and analyzes images in different fields including marine image processing. Identifying a dolphin from a picture which has sea feature is difficult because the background of the picture is complex and has some similarities with the target. For this reason, we make a thorough research on the target segmentation and the existing identification algorithms used to solve this problem. In this paper, we will present a new segmentation algorithm based on clustering threshold in the RGB color space to process dolphin images. We will combine it with the SIFT algorithm for image post-processing feature extraction. Then we will present how to build a dolphin growth model to identify a dolphin.

Pages: 36 to 40

Copyright: Copyright (c) IARIA, 2016

Publication date: November 13, 2016

Published in: conference

ISSN: 2519-8645

ISBN: 978-1-61208-520-3

Location: Barcelona, Spain

Dates: from November 13, 2016 to November 17, 2016