Hybrid Sub-space Detection Technique for Effective Hyperspectral Image Classification

Mishu, Sadia Zaman; Hossain, Md. Ali; Ahmed, Boshir

doi:10.1109/ic4me2.2018.8465623

Cited by 6 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In paper [2] PCA has been combined with QMI and 99% accuracy is obtained. But among 16 classes of AVIRIS dataset only 5 classes have been used which is not sufficient for analysis.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, these sensors provide high volume of data. For instance, AVIRIS sensor captures data in 220 different wavelengths of the bands with a spectral resolution of 0.01µm that covers from visible light to (near) infrared region of electromagnetic wave spectrum to denote narrow absorption features which provide strong discrimination capability in data inspection [2,3]. This high dimensional data provides many research chanllenges as it requires more processing time.…”

Section: Introductionmentioning

confidence: 99%

“…It also suffer from the curse of dimensionality problem which refers to that the classification accuracy increases with increase of the no of features and starts to decrese after a certain value of the no of bands. This effect occurs due to the imbalance of the ratio between the no of bands and the no of training samples which reduces the overall classification accuracy [2,4]. Conversely, the close and contiguous bands are extremely correlated and some of them are redundant which are not important for classification [2].…”

Section: Introductionmentioning

confidence: 99%

“…This effect occurs due to the imbalance of the ratio between the no of bands and the no of training samples which reduces the overall classification accuracy [2,4]. Conversely, the close and contiguous bands are extremely correlated and some of them are redundant which are not important for classification [2]. These challanging research problems motivate us to extract relevant features with a view to improve classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…The mutual information(MI) is a widely used feature selection method. It is non parametric so it does not rely on the assumption about the shape of the distribution of the input parameters [2]. It has been widely used as a similarity measure for different types of imaging applications such as feature reduction [10], registration of image [11] and image clustering [12] etc.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hybrid Subspace Detection based on Spectral and Spatial Information for Effective Hyperspectral Image Classification

Zaman¹,

Ahmed²

2019

IJCA

Self Cite

View full text Add to dashboard Cite

Subspace detection of remote sensing hyperspectral image data cube has become an important area of research because of the challenges of dealing with high dimensional feature space for efficient identification of ground objects. Standard feature extraction method such as Principal Component Analysis (PCA) has several shortcomings as it depends solely on global variance of the data set generated ignoring the low variant components. In this paper these limitations are addressed and alternatively Folded-PCA (FPCA) is used for feature extraction. FPCA has some advantages over PCA as it utilizes both local and global structures of the image and requires comparatively less computational cost and memory. These properties make it suitable for feature extraction therefore our proposed method combines it with Quadratic Mutual Information (QMI) for the task of feature reduction. In this research, QMI is utilized as a means of feature selection over the new features generated from FPCA to obtain an informative subspace. The proposed method is named as (FPCA-QMI). It is tested on two hyperspectral datasets one is real mixed agricultural land and another one is an university area. Finally Kernel Support Vector Machine (KSVM) technique is applied to measure the classification accuracy of these two datasets. From the experimental analysis it is observed that the proposed method can detect effective subspace and obtains the highest accuracy of 98.0328% and 99.0431% on two real hyperspectral images which is better than the baseline approaches.

show abstract

“…In paper [2] PCA has been combined with QMI and 99% accuracy is obtained. But among 16 classes of AVIRIS dataset only 5 classes have been used which is not sufficient for analysis.…”

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%