Gabor Features Extraction and Land-Cover Classification of Urban Hyperspectral Images for Remote Sensing Applications

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 15; p. 2914
• Main Authors: Cruz-Ramos, Clara, Garcia-Salgado, Beatriz P., Reyes-Reyes, Rogelio, Ponomaryov, Volodymyr, Sadovnychiy, Sergiy
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2021
• Subjects: Accuracy; Algorithms; artificial neural network; Artificial neural networks; Classification; Data processing; Decision making; dimension reduction; Discriminant analysis; Feature extraction; gabor features; Gray scale; Hyperspectral imaging; Image classification; Information retrieval; Land cover; Machine learning; Methods; Neural networks; Normalized difference vegetative index; Pipelines; Principal components analysis; Remote sensing; Representations; Saturation (color); Support vector machines; Texture; Training; urban hyperspectral images
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs13152914

The principles of the transform stage of the extract, transform and load (ETL) process can be applied to index the data in functional structures for the decision-making inherent in an urban remote sensing application. This work proposes a method that can be utilised as an organisation stage by reducing the data dimension with Gabor texture features extracted from grey-scale representations of the Hue, Saturation and Value (HSV) colour space and the Normalised Difference Vegetation Index (NDVI). Additionally, the texture features are reduced using the Linear Discriminant Analysis (LDA) method. Afterwards, an Artificial Neural Network (ANN) is employed to classify the data and build a tick data matrix indexed by the belonging class of the observations, which could be retrieved for further analysis according to the class selected to explore. The proposed method is compared in terms of classification rates, reduction efficiency and training time against the utilisation of other grey-scale representations and classifiers. This method compresses up to 87% of the original features and achieves similar classification results to non-reduced features but at a higher training time.