Improvement of Multichannel Image Classification by Combining Elementary Classifiers
| Autor: | Galina Proskura, Irina Vasilyeva, Vladimir V. Lukin |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0209 industrial biotechnology
Contextual image classification business.industry Computer science Posterior probability ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition 02 engineering and technology Image segmentation Class (biology) Convolution Image (mathematics) Support vector machine 020901 industrial engineering & automation Computer Science::Computer Vision and Pattern Recognition Multilayer perceptron 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | 2019 IEEE International Scientific-Practical Conference Problems of Infocommunications, Science and Technology (PIC S&T). |
| DOI: | 10.1109/picst47496.2019.9061380 |
| Popis: | A post-classification processing technique for multi-channel images that includes three stages is proposed. The purpose of the first stage is to correct decisions of pixel-by-pixel classifiers based on estimates of classes’ posterior probabilities. At the second stage, a logical convolution of the classification layers is performed which makes it possible to select the most probable class. At the final stage, local spatial filtering of pre-segmented image is done which is performed in the neighborhood of detected segments’ edges. The post-classification processing effectiveness is verified for satellite images. It is demonstrated that the proposed post-classification processing procedure can significantly increase the probability of recognizing poorly distinguishable classes and improve overall accuracy of image classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|