scholarly journals Linear colour segmentation revisited

Author(s):  
Anna Smagina ◽  
Valentina Bozhkova ◽  
Sergey Gladilin ◽  
Dmitry Nikolaev
Keyword(s):  
Author(s):  
Pauleen Ong ◽  
Muhammad Suzuri Hitam ◽  
Zainuddin Bachok ◽  
Mohd Safuan Che Din

At present, marine scientists employ manual method to estimate the components in coral reef environment, where Coral Point Count with Excel extensions (CPCe) software is used to determine the coral reef components and substrate coverage. This manual process is laborious and time consuming, and needs experts to conduct the survey. In this paper, a prototype for estimating the distribution of sand cover in coral reef environment from still images by using colour extraction methods was introduced. The colour segmentation called delta E was used to calculate the colour difference between two colour samples. Another method used was colour threshold by setting the range of sand colour pixels. The system was developed by using a MATLAB software with image processing toolbox. The developed system was semi-automatic computer-based system that can be used by researchers even with little knowledge and experience to estimate the percentage of sand coverage in coral reef still images.


2017 ◽  
Vol 853 ◽  
pp. 012012 ◽  
Author(s):  
Riries Rulaningtyas ◽  
Andriyan B Suksmono ◽  
Tati L R Mengko ◽  
Putri Saptawati

2007 ◽  
Vol 4 (3) ◽  
pp. 91-100
Author(s):  
F. Montes-Gonzalez ◽  
P. Bautista-Cabrera ◽  
V. Escobar-Ruiz

The use of effective central selection provides flexibility in design by offering modularity and extensibility. In earlier papers we have focused on the development of a simple centralized selection mechanism. Our current goal is to integrate evolutionary methods in the design of non-sequential behaviours and the tuning of specific parameters of the selection model. The foraging behaviour of an animal robot (animat) has been modelled in order to integrate the sensory information from the robot to perform selection that is nearly optimized by the use of genetic algorithms. In this paper we present how selection through optimization finally arranges the pattern of presented behaviours for the foraging task. Hence, the execution of specific parts in a behavioural pattern may be ruled out by the tuning of these parameters. Furthermore, the intensive use of colour segmentation from a colour camera for locating a cylinder sets a burden on the calculations carried out by the genetic algorithm.


2015 ◽  
Vol 9 (12) ◽  
pp. 1064-1072 ◽  
Author(s):  
Tom Toulouse ◽  
Xavier Maldague ◽  
Lucile Rossi ◽  
Moulay Akhloufi ◽  
Turgay Celik

Sign in / Sign up

Export Citation Format

Share Document