Yu Chen

The increase in the spectral and spatial information of hyperspectral imagery poses challenges in classification due to the fact that spectral bands are highly correlated, training samples may be limited, and high resolution may increase intraclass difference and interclass similarity. In this paper, in order to better handle these problems, a Caps-TripleGAN framework is proposed by exploring the 1-D structure triple generative adversarial network (TripleGAN) for sample generation and integrating CapsNet for hyperspectral image classification. Moreover, spatial information is utilized to verify the learning capacity and discriminative ability of the Caps-TripleGAN framework. The experimental results obtained with three real hyperspectral data sets confirm that the proposed method outperforms most of the state-of-the-art methods.

Yu Chen, Lingfei Wu, Mohammed J. Zaki. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.

This paper introduces the method for defect recognition of power transmission lines based on Histogram of Oriented Gradients (HOG) algorithm and Support Vector Machine (SVM) algorithm. Firstly, this paper investigates the key technologies in the system including image preprocessing, feature extraction methods, feature dimension reduction and classifiers. Secondly, according to the characteristics of power transmission line images, HOG is used to extract image features. HOG is a dense descriptor for the local overlapping area of the image. It constructs the feature by calculating the gradient direction histogram of the local region. Principal Component Analysis (PCA) method is applied to solve the feature dimension explosion. It can be used to extract the main feature components of the data and often used for dimensionality reduction of high-dimensional data. Thirdly, the SVM algorithm is used for classification. In the field of machine learning, it is a supervised learning model, which is usually used for pattern recognition, classification and regression analysis. The Directed Acyclic Graph (DAG) multi-classifiers is designed for the defect recognition of power transmission lines, such as normal lines, strand breakage lines and foreign-matter lines. In addition, the experimental results show that when the size of the pixel cell is 32*32 and the PCA contribution rate is 99%, the image processing has the best defect recognition performance, the processing speed of each image is 0.539 seconds and the average recognition accuracy is 84.3%.