Kernel based learning approach for satellite image classification using support vector machine

2011 ◽  
Author(s):  
S. Manthira Moorthi ◽  
Indranil Misra ◽  
Rajdeep Kaur ◽  
Nikunj P Darji ◽  
R. Ramakrishnan
Keyword(s):  
Support Vector Machine ◽  
Image Classification ◽  
Satellite Image ◽  
Support Vector ◽  
Learning Approach ◽  
Satellite Image Classification

scholarly journals A One-shot Learning Approach to Image Classification using Genetic Programming

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
M Johnston
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Genetic Programming ◽  
Image Classification ◽  
Local Binary Patterns ◽  
Support Vector ◽  
Learning Approach ◽  
Data Sets ◽  
Domain Specific ◽  
International Publishing

In machine learning, it is common to require a large number of instances to train a model for classification. In many cases, it is hard or expensive to acquire a large number of instances. In this paper, we propose a novel genetic programming (GP) based method to the problem of automatic image classification via adopting a one-shot learning approach. The proposed method relies on the combination of GP and Local Binary Patterns (LBP) techniques to detect a predefined number of informative regions that aim at maximising the between-class scatter and minimising the within-class scatter. Moreover, the proposed method uses only two instances of each class to evolve a classifier. To test the effectiveness of the proposed method, four different texture data sets are used and the performance is compared against two other GP-based methods namely Conventional GP and Two-tier GP. The experiments revealed that the proposed method outperforms these two methods on all the data sets. Moreover, a better performance has been achieved by Naïve Bayes, Support Vector Machine, and Decision Trees (J48) methods when extracted features by the proposed method have been used compared to the use of domain-specific and Two-tier GP extracted features. © Springer International Publishing 2013.

scholarly journals Automatic Generation Of Training Data For Hyperspectral Image Classification Using Support Vector Machine

2015 ◽  
Vol XL-7/W3 ◽  
pp. 575-580 ◽  
Author(s):  
B. Abbasi ◽  
H. Arefi ◽  
B. Bigdeli ◽  
S. Roessner
Keyword(s):  
Support Vector Machine ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Satellite Image ◽  
Automatic Generation ◽  
Training Data ◽  
Experimental Result ◽  
Support Vector ◽  
Feature Descriptors

An image classification method based on Support Vector Machine (SVM) is proposed on hyperspectral and 3K DSM data. To obtain training data we applied an automatic method relating to four classes namely; building, grass, tree, and ground pixels. First, some initial segments regarding to building, tree, grass, and ground pixels are produced using different feature descriptors. The feature descriptors are generated using optical (hyperspectral) as well as range (3K DSM) images. The initial building regions are created using DSM segmentation. Fusion of NDVI and elevation information assist us to provide initial segments regarding to the grass and tree areas. Also, we created initial segment regarding to ground pixel after geodesic based filtering of DSM and elimination of the non-ground pixels. To improve classification accuracy, the hyperspectral image and 3K DSM were utilized simultaneously to perform image classification. For obtaining testing data, labelled pixels was divide into two parts: test and training. Experimental result shows a final classification accuracy of about 90% using Support Vector Machine. In the process of satellite image classification; provided by 3K camera. Both datasets correspond to Munich area in Germany.

scholarly journals A One-shot Learning Approach to Image Classification using Genetic Programming

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
M Johnston
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Genetic Programming ◽  
Image Classification ◽  
Local Binary Patterns ◽  
Support Vector ◽  
Learning Approach ◽  
Data Sets ◽  
Domain Specific ◽  
International Publishing

In machine learning, it is common to require a large number of instances to train a model for classification. In many cases, it is hard or expensive to acquire a large number of instances. In this paper, we propose a novel genetic programming (GP) based method to the problem of automatic image classification via adopting a one-shot learning approach. The proposed method relies on the combination of GP and Local Binary Patterns (LBP) techniques to detect a predefined number of informative regions that aim at maximising the between-class scatter and minimising the within-class scatter. Moreover, the proposed method uses only two instances of each class to evolve a classifier. To test the effectiveness of the proposed method, four different texture data sets are used and the performance is compared against two other GP-based methods namely Conventional GP and Two-tier GP. The experiments revealed that the proposed method outperforms these two methods on all the data sets. Moreover, a better performance has been achieved by Naïve Bayes, Support Vector Machine, and Decision Trees (J48) methods when extracted features by the proposed method have been used compared to the use of domain-specific and Two-tier GP extracted features. © Springer International Publishing 2013.

scholarly journals Homogeneity Distance Classification Algorithm (HDCA): A Novel Algorithm for Satellite Image Classification

2019 ◽  
Vol 11 (5) ◽  
pp. 546 ◽  
Author(s):  
Mohammad Firozjaei ◽  
Iman Daryaei ◽  
Amir Sedighi ◽  
Qihao Weng ◽  
Seyed Alavipanah
Keyword(s):  
Image Classification ◽  
Search Algorithm ◽  
Satellite Image ◽  
Gravitational Search Algorithm ◽  
Feature Space ◽  
Classification Algorithm ◽  
Manhattan Distance ◽  
Support Vector ◽  
Satellite Image Classification ◽  
Novel Algorithm

Image classification is one of the most common methods of information extraction from satellite images. In this paper, a novel algorithm for image classification based on gravity theory was developed, which was called “homogeneity distance classification algorithm (HDCA)”. The proposed HDCA used texture and spectral information for classifying images in two iterative supplementary computing stages: (1) merging, (2) traveling and escaping operators. The HDCA was equipped by a new concept of distance, the weighted Manhattan distance (WMD). Moreover, an improved gravitational search algorithm (IGSA) was applied for selecting features and determining optimal feature space scale in HDCA. In the case of multispectral satellite image classification, the proposed method was compared with two well-known classification methods, Maximum Likelihood classifier (MLC) and Support Vector Machine (SVM). The results of the comparison indicated that overall accuracy values for HDCA, MLC, and SVM are 95.99, 93.15, and 95.00, respectively. Furthermore, the proposed HDCA method was also used for classifying hyperspectral reference datasets (Indian Pines, Salinas and Salinas-A scene). The classification results indicated substantial improvement over previous algorithms and studies by 2% in Indian Pines dataset, 0.7% in the Salinas dataset and 1.2% in the Salinas-A scene. These experimental results demonstrate that the proposed algorithm can classify both multispectral and hyperspectral remote sensing images with reliable accuracy because this algorithm uses the WMD in the classification process and the IGSA to select automatically optimal features for image classification based on spectral and texture information.

Sign in / Sign up

Export Citation Format

Share Document