Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network
This paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/α decomposition, and the GLCM-based texture features. Then, a probabilistic neural network (PNN) was adopted for classification, and a novel algorithm proposed to enhance its performa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2009-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/9/9/7516/ |
| _version_ | 1818040719061811200 |
|---|---|
| author | Lenan Wu Nabil Neggaz Shuihua Wang Geng Wei Yudong Zhang |
| author_facet | Lenan Wu Nabil Neggaz Shuihua Wang Geng Wei Yudong Zhang |
| author_sort | Lenan Wu |
| collection | DOAJ |
| description | This paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/α decomposition, and the GLCM-based texture features. Then, a probabilistic neural network (PNN) was adopted for classification, and a novel algorithm proposed to enhance its performance. Principle component analysis (PCA) was chosen to reduce feature dimensions, random division to reduce the number of neurons, and Brent’s search (BS) to find the optimal bias values. The results on San Francisco and Flevoland sites are compared to that using a 3-layer BPNN to demonstrate the validity of our algorithm in terms of confusion matrix and overall accuracy. In addition, the importance of each improvement of the algorithm was proven. |
| first_indexed | 2024-12-10T08:18:59Z |
| format | Article |
| id | doaj.art-6ea98be2da0f4f43b0a8d628ebe6a947 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T08:18:59Z |
| publishDate | 2009-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6ea98be2da0f4f43b0a8d628ebe6a9472022-12-22T01:56:23ZengMDPI AGSensors1424-82202009-09-01997516753910.3390/s90907516Remote-Sensing Image Classification Based on an Improved Probabilistic Neural NetworkLenan WuNabil NeggazShuihua WangGeng WeiYudong ZhangThis paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/α decomposition, and the GLCM-based texture features. Then, a probabilistic neural network (PNN) was adopted for classification, and a novel algorithm proposed to enhance its performance. Principle component analysis (PCA) was chosen to reduce feature dimensions, random division to reduce the number of neurons, and Brent’s search (BS) to find the optimal bias values. The results on San Francisco and Flevoland sites are compared to that using a 3-layer BPNN to demonstrate the validity of our algorithm in terms of confusion matrix and overall accuracy. In addition, the importance of each improvement of the algorithm was proven.http://www.mdpi.com/1424-8220/9/9/7516/polarimetric SARProbabilistic neural networkgray-level co-occurrence matrixprinciple component analysisBrent’s Search |
| spellingShingle | Lenan Wu Nabil Neggaz Shuihua Wang Geng Wei Yudong Zhang Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network Sensors polarimetric SAR Probabilistic neural network gray-level co-occurrence matrix principle component analysis Brent’s Search |
| title | Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network |
| title_full | Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network |
| title_fullStr | Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network |
| title_full_unstemmed | Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network |
| title_short | Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network |
| title_sort | remote sensing image classification based on an improved probabilistic neural network |
| topic | polarimetric SAR Probabilistic neural network gray-level co-occurrence matrix principle component analysis Brent’s Search |
| url | http://www.mdpi.com/1424-8220/9/9/7516/ |
| work_keys_str_mv | AT lenanwu remotesensingimageclassificationbasedonanimprovedprobabilisticneuralnetwork AT nabilneggaz remotesensingimageclassificationbasedonanimprovedprobabilisticneuralnetwork AT shuihuawang remotesensingimageclassificationbasedonanimprovedprobabilisticneuralnetwork AT gengwei remotesensingimageclassificationbasedonanimprovedprobabilisticneuralnetwork AT yudongzhang remotesensingimageclassificationbasedonanimprovedprobabilisticneuralnetwork |