Ant-Snake model for Linear Feature Extraction from Satellite Image

2014 ◽  
Vol 13 (6) ◽  
pp. 4574-4582
Author(s):  
Jalal Amini ◽  
Leila Mohammadnia
Keyword(s):  
Feature Extraction ◽  
Satellite Images ◽  
Satellite Image ◽  
Ant Colony ◽  
Superior Performance ◽  
Linear Features ◽  
Snake Model ◽  
Parametric Curve ◽  
Linear Feature ◽  
Linear Feature Extraction

This paper proposes an optimized mathematical model for linear feature extraction from satellite images. The model is based on a developed ant colony model combined with the snake model (called Ant-Snake model) to identify and extract the linear features like roads from satellite images. The process is started with the developed ant colony model to recognize and identify interest object and then with a snake model extract object. The developed ant model is able to establish a pheromone matrix that represents the object information at each pixel position of the image, according to the movements of a number of ants which are dispatch to move on the image. And the snake model is a parametric curve which is allowed to deform from some arbitrary initial locations from pheromone matrix toward the desired final location by minimizing an energy function. Experimental results are provided to demonstrate the superior performance of the proposed approach.

An approximated Snake Function for Road Extraction from digital images

2014 ◽  
Vol 4 (3) ◽  
pp. 601-609
Author(s):  
Leyla Mohamadnia ◽  
Jalal Amini
Keyword(s):  
Satellite Images ◽  
Road Extraction ◽  
External Energy ◽  
Linear Features ◽  
Snake Model ◽  
Parametric Curve ◽  
Linear Feature ◽  
Linear Feature Extraction ◽  
Initial Location ◽  
Pheromone Information

This paper proposes an optimized mathematical model (Snake-ant) for linear feature extraction from satellite images. The model first uses the Ant Colony Optimization (ACO) to establish a pheromone matrix that represents the pheromone information at each pixel position of the image, according to the movements of a number of ants which are sent to move on the image. Next pheromone matrix is used in the snake model as external energy to extract the linear features like roads edges in image. Snake is a parametric curve which is allowed to deform from some arbitrary initial location toward the desired final location by minimizing an energy function based on the internal and external energy. Our approach is validated by a series of tests on satellite images.

scholarly journals LINEAR FEATURE EXTRACTION FOR SATELLITE IMAGES USING CNLS (CONTEXTUAL NONLINEAR SMOOTHING) ALGORITHM

2013 ◽  
pp. 6-10
Author(s):  
J.KRISHNA CHAITHANYA ◽  
DR.T.RAMA SHRI
Keyword(s):  
Feature Extraction ◽  
Satellite Images ◽  
Gabor Filter ◽  
Smoothing Algorithm ◽  
Phase Congruency ◽  
Linear Feature ◽  
Remotely Sensed Imagery ◽  
Linear Feature Extraction ◽  
Nonlinear Smoothing ◽  
Satellite Sensors

The satellite images present a great variety of features due to the trouble what returns their treatment is little delicate. The automated extraction of linear features from remotely sensed imagery has been the subject of extensive research over several decades. Recent studies show promise for extraction of feature information for applications such as updating geographic information systems (GIS). Research has been stimulated by the increase in available imagery in recent years following the launch of several airborne and satellite sensors. All the satellite images, which are going to be used in the present work, are going to be processed in the computer vision, for which the existing researchers are interested to analyze the synthetic images by feature extraction. These images contain many types of features. Indeed, the features are classified in 1-D feature such as step, roof and 2-D features such as corners, edges, and blocks. The satellite images present a great variety of features due to the trouble what returns their treatment is little delicate. In this we present a method for edge segmentation of satellite images based on 2-D Phase Congruency (PC) model. The proposed approach is composed by two steps: The contextual nonlinear smoothing algorithm (CNLS) is used to smooth the input images. Then, the 2D stretched Gabor filter (S-G filter) based on proposed angular variation is developed in order to avoid the multiple responses.

SUPERVISED REGULARIZATION LOCALITY-PRESERVING PROJECTION METHOD FOR FACE RECOGNITION

2012 ◽  
Vol 10 (06) ◽  
pp. 1250053 ◽  
Author(s):  
WEN-SHENG CHEN ◽  
WEI WANG ◽  
JIAN-WEI YANG ◽  
YUAN YAN TANG
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Small Sample Size ◽  
Small Sample ◽  
Superior Performance ◽  
Locality Preserving Projection ◽  
Feature Extraction Method ◽  
Linear Feature ◽  
Linear Feature Extraction ◽  
Locality Preserving

Locality-preserving projection (LPP) is a promising manifold-based dimensionality reduction and linear feature extraction method for face recognition. However, there exist two main issues in traditional LPP algorithm. LPP does not utilize the class label information at the training stage and its performance will be affected for classification tasks. In addition, LPP often suffers from small sample size (3S) problem, which occurs when the dimension of input pattern space is greater than the number of training samples. Under this situation, LPP fails to work. To overcome these two limitations, this paper presents a novel supervised regularization LPP (SRLPP) approach based on a supervised graph and a new regularization strategy. It theoretically proves that regularization matrix [Formula: see text] approaches to the original one as the regularized parameter tends to zero. The proposed SRLPP method is subsequently applied to face recognition. The experiments are conducted on two publicly available face databases, namely ORL database and FERET database. Compared with some existing LDA-based and LPP-based linear feature extraction approaches, experimental results show that our SRLPP approach gives superior performance.

scholarly journals Structural Damage Classification in a Jacket-Type Wind-Turbine Foundation Using Principal Component Analysis and Extreme Gradient Boosting

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2748
Author(s):  
Jersson X. Leon-Medina ◽  
Maribel Anaya ◽  
Núria Parés ◽  
Diego A. Tibaduiza ◽  
Francesc Pozo
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Wind Turbine ◽  
Structural Damage ◽  
Principal Component ◽  
Gradient Boosting ◽  
Damage Classification ◽  
Linear Feature ◽  
Linear Feature Extraction ◽  
Extreme Gradient Boosting

Damage classification is an important topic in the development of structural health monitoring systems. When applied to wind-turbine foundations, it provides information about the state of the structure, helps in maintenance, and prevents catastrophic failures. A data-driven pattern-recognition methodology for structural damage classification was developed in this study. The proposed methodology involves several stages: (1) data acquisition, (2) data arrangement, (3) data normalization through the mean-centered unitary group-scaling method, (4) linear feature extraction, (5) classification using the extreme gradient boosting machine learning classifier, and (6) validation applying a 5-fold cross-validation technique. The linear feature extraction capabilities of principal component analysis are employed; the original data of 58,008 features is reduced to only 21 features. The methodology is validated with an experimental test performed in a small-scale wind-turbine foundation structure that simulates the perturbation effects caused by wind and marine waves by applying an unknown white noise signal excitation to the structure. A vibration-response methodology is selected for collecting accelerometer data from both the healthy structure and the structure subjected to four different damage scenarios. The datasets are satisfactorily classified, with performance measures over 99.9% after using the proposed damage classification methodology.

scholarly journals DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification

2017 ◽  
Vol E100.D (9) ◽  
pp. 2249-2252 ◽  
Author(s):  
Seongkyu MUN ◽  
Minkyu SHIN ◽  
Suwon SHON ◽  
Wooil KIM ◽  
David K. HAN ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Transfer Learning ◽  
Event Classification ◽  
Acoustic Event ◽  
Linear Feature ◽  
Linear Feature Extraction ◽  
Non Linear
Sign in / Sign up

Export Citation Format

Share Document