Skip to main content

An Supervised Artificial Neural Network Method for Sattelite Image Segmentation

Image segmentation is an important step in image processing (image processing). The main purpose of segmentation is to simplify and or to change the representation of an image into a form that is easier to analyze. Already there are several methods of image segmentation are found, but most of these methods are not suitable for satellite imagery and -Method method requires a knowledge of the initial (a priori knowledge). To overcome these problems, a satellite image segmentation method is developed using an artificial neural network method without learning (unsupervised) called Kohonen's self-organizing map and threshold technique.


Self-organizing map (SOM) is used to adjust the gray level of the pixel based on the value of the color 3-Dimensional (multiple bands) into a 2-Dimensional. In SOM, the input signal of n-tuple and group-kelompoksebanyak m clusters. Each input is connected to all the units are full. Weights obtained by random and small value that will determine the status of the end (final state). The tissue was prepared by orthogonal grid cluster units (neurons), each of which is associated with three internal weights of three layers of satellite imagery. At each step in the training phase, the cluster unit with very coco weight k with the input pattern will be chosen to be the value of the winner (the Winner) by using the minimum euclidean distance (see formula).
Then a threshold technique is used to group (cluster) of the image into separate areas, this method is called TSOM. The study was conducted on two different satellite images prove that the stability, homogeneity, and efficiency of the method compared with iterative methods TSOM self -organizing the data analysis (ISODATA). The stability and homogeneity of the two methods is determined using the procedure selected based on functional models.

Advantages
1 Does not require a prior knowledge or learning (unsupervised).
2 More stable than the ISODATA.
3 two times faster than the ISODATA when running.

Disadvantages
The efficiency of the method depends on the number of iterations and the threshold value is selected manually.

Comments

Popular posts from this blog

Why Programmers Should Wear Framework (CodeIgniter or Yii)

The framework can be interpreted simply as a library containing a collection of functions / procedures and classes for specific purposes that are ready to be used so that it can facilitate and accelerate the work of a programmer, without having to create a function or class from the start. Advantages of using the framework are: provide a good structure in our program. Sometimes as programmers, we can create our program structure. the framework, we can make the program more structured, easy to manage, easy to develop. well for those that have been used to make the program itself, usually on their own to create a framework in the program can easily develop, that could be a problem is the use of this framework is the subjective easily according to our perspective. with a framework that is used by many people, it will provide the structure and way of working standards for our applications. The more people who use it, it means a lot of people who agree with the way the framework w...

Indra, Radar Made in Indonesia

Wants to prove that Indonesia is not inferior to other nations, Electronics and Telecommunications Research Center Indonesian Institute of Sciences (LIPI PPET) and a division of PT Solutions 247 Radar and Communications System (RCS) makes maritime radar. Since 2006, PPET LIPI has developed two versions of the radar. Namely radar coastal surveillance and navigation radar ship. In its development, the maritime radar to be named while Indonesian Radar (Indra). To distinguish, ship navigation radar developed by PT Solutions 247-RCS named Indra-1 and a coastal surveillance radar developed by PPET-LIPI named Indra-2. Both of these radar technology frequency-modulated continuous wave (FMCW) so that the power consumption and size is much smaller than the radar radars in the market. Indra-1 managed to detect and measure the distance of a ship that was sailing with accuracy. We are proud of this result. This is proof that we can make the radar is built and functioning properly. Having escape...

Microsoft Windows 10 IOT Can for Raft Robot

Thinking of creating a project Internet of Things (IOT) or a robot? Microsoft promises ease to assemble with Windows 10 Starter Kit IOT. In the Starter Kit package for Windows IOT Core and Raspberry Pi 2, supplied equipment such as sensors, electronic components, and various types of cables that are compatible with Windows 10. Package offered by Microsoft in collaboration with Adafruit's online community allows users to create a prototype and build a machine that could send back information to a database. For example, the starter kit can be used to make weather stations that generate data based on interaction with the environment, or communicate with analog photocell sensor to measure light intensity. In fact, the starter kit can also be used to create a robot with wheels legs that can be controlled via a joystick and a Raspberry Pi Unfortunately, the starter kit is sold out in just a few minutes after it was released. But when stocked again later, for those who are interested ...