Hyperspectral Image Classification Using Fast and Adaptive Bidimensional Empirical Mode Decomposition With Minimum Noise Fraction

Yang, Ming‐Der; Huang, Kai-Shiang; Yang, Yeh Fen; Liangyou, Lu; Zhang, Feng; Tsai, Hui Ping

doi:10.1109/lgrs.2016.2618930

Cited by 28 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where FG indicates the foreground; µ and σ are the mean and the standard deviation, respectively. Furthermore, to eliminate salt-and-pepper noise, a median filter was used to polish the foreground [49].…”

Section: Moving Object Recognitionmentioning

confidence: 99%

Geometric Recognition of Moving Objects in Monocular Rotating Imagery Using Faster R-CNN

et al. 2020

Self Cite

View full text Add to dashboard Cite

Moving object detection and tracking from image sequences has been extensively studied in a variety of fields. Nevertheless, observing geometric attributes and identifying the detected objects for further investigation of moving behavior has drawn less attention. The focus of this study is to determine moving trajectories, object heights, and object recognition using a monocular camera configuration. This paper presents a scheme to conduct moving object recognition with three-dimensional (3D) observation using faster region-based convolutional neural network (Faster R-CNN) with a stationary and rotating Pan Tilt Zoom (PTZ) camera and close-range photogrammetry. The camera motion effects are first eliminated to detect objects that contain actual movement, and a moving object recognition process is employed to recognize the object classes and to facilitate the estimation of their geometric attributes. Thus, this information can further contribute to the investigation of object moving behavior. To evaluate the effectiveness of the proposed scheme quantitatively, first, an experiment with indoor synthetic configuration is conducted, then, outdoor real-life data are used to verify the feasibility based on recall, precision, and F1 index. The experiments have shown promising results and have verified the effectiveness of the proposed method in both laboratory and real environments. The proposed approach calculates the height and speed estimates of the recognized moving objects, including pedestrians and vehicles, and shows promising results with acceptable errors and application potential through existing PTZ camera images at a very low cost.

show abstract

Section: Moving Object Recognitionmentioning

confidence: 99%

Geometric Recognition of Moving Objects in Monocular Rotating Imagery Using Faster R-CNN

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bidimensional empirical mode decomposition (BEMD) and fast and adaptive bidimensional empirical mode decomposition (FABEMD) were further developed to solve envelope surface calculations for two-dimensional images [44,45]. In a previous study by Yang et al [46], a combination of MNF and FABEMD processes was proposed for HSI classification using a SVM classifier. The study reported the effective elimination of noise effects to obtain a higher classification accuracy (overall accuracy 98.14%) than traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification

Yang

Huang²,

Tsai

2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

The critical issue facing hyperspectral image (HSI) classification is the imbalance between dimensionality and the number of available training samples. This study attempted to solve the issue by proposing an integrating method using minimum noise fractions (MNF) and Hilbert–Huang transform (HHT) transformations into artificial neural networks (ANNs) for HSI classification tasks. MNF and HHT function as a feature extractor and image decomposer, respectively, to minimize influences of noises and dimensionality and to maximize training sample efficiency. Experimental results using two benchmark datasets, Indian Pine (IP) and Pavia University (PaviaU) hyperspectral images, are presented. With the intention of optimizing the number of essential neurons and training samples in the ANN, 1 to 1000 neurons and four proportions of training sample were tested, and the associated classification accuracies were evaluated. For the IP dataset, the results showed a remarkable classification accuracy of 99.81% with a 30% training sample from the MNF1–14+HHT-transformed image set using 500 neurons. Additionally, a high accuracy of 97.62% using only a 5% training sample was achieved for the MNF1–14+HHT-transformed images. For the PaviaU dataset, the highest classification accuracy was 98.70% with a 30% training sample from the MNF1–14+HHT-transformed image using 800 neurons. In general, the accuracy increased as the neurons increased, and as the training samples increased. However, the accuracy improvement curve became relatively flat when more than 200 neurons were used, which revealed that using more discriminative information from transformed images can reduce the number of neurons needed to adequately describe the data as well as reducing the complexity of the ANN model. Overall, the proposed method opens new avenues in the use of MNF and HHT transformations for HSI classification with outstanding accuracy performance using an ANN.

show abstract

“…In computer vision, for example, in handwritten verifications, the shape of the extrema points are used to identify the shape of a signature [1] [2]. Other than that, video and image processing also apply extrema points by using a bi-dimensional empirical mode [3][4] [5] for standard images, video and hyperspectral images. In this paper, extrema points helped to determine the region of interest (ROI) in an image of the iris.…”

Section: Introductionmentioning

confidence: 99%

Extrema Points Application in Determining Iris Region of Interest

Othman

Abdullah

Ahmad

et al. 2019

EJSMT

View full text Add to dashboard Cite

Extrema points are usually applied to solve everyday problems, for example, to determine the potential of a created tool and for optimisation. In this study, extrema points were used to help determine the region of interest (ROI) for the iris in iris recognition systems. Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition techniques on the images of one or both irises of an individual's eyes, where the complex patterns are unique, stable, and can be seen from a distance. In order to obtain accurate results, the iris must be localised correctly. Hence, to address this issue, this paper proposed a method of iris localisation in the case of ideal and non-ideal iris images. In this study, the algorithm was based on finding the classification for the region of interest (ROI) with the help of a Support Vector Machine (SVM) by applying a histogram of grey level values as a descriptor in each region from the region growing technique. The valid ROI was found from the probabilities graph of the SVM obtained by looking at the global minimum conditions determined by a second derivative model in a graph of functions. Furthermore, the model from the global minimum condition values was used in the test phase, and the results showed that the ROI image obtained helped in the elimination of sensitive noise with the involvement of fewer computations, while reserving relevant information.

show abstract

Hyperspectral Image Classification Using Fast and Adaptive Bidimensional Empirical Mode Decomposition With Minimum Noise Fraction

Cited by 28 publications

References 28 publications

Geometric Recognition of Moving Objects in Monocular Rotating Imagery Using Faster R-CNN

Geometric Recognition of Moving Objects in Monocular Rotating Imagery Using Faster R-CNN

Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification

Extrema Points Application in Determining Iris Region of Interest

Contact Info

Product

Resources

About