Chenxuan Yang

Bio: Chenxuan Yang is an academic researcher. The author has contributed to research in topics: Pattern recognition (psychology) & Artificial intelligence. The author has an hindex of 1, co-authored 2 publications receiving 5 citations.

Infrared and visible image fusion based on QNSCT and Guided Filter

Abstract: Image fusion is the process of fusing multiple images of the same scene to obtain a more informative image for human eye perception. In this paper, a new fusion framework based on Quaternion Non-Subsampled Contourlet Transform (QNSCT) and Guided Filter detail enhancement is designed to address the problems of inconspicuous infrared targets and poor background texture in Infrared and visible image fusion. The proposed method uses the quaternion wavelet transform for the first time instead of the traditional Non-Subsampled Pyramid Filter Bank structure in the Non-Subsampled Contourlet Transform (NSCT). The flexible multi-resolution of quaternion wavelet and the multi-directionality of NSCT are fully utilized to refine the multi-scale decomposition scheme. On the other hand, the coefficient matrix obtained from the proposed QNSCT algorithm is fused using a weight refinement algorithm based on the guided filter. The fusion scheme is divided into four steps. First, the Infrared and visible images are decomposed into multi-directional and multiscale coefficient matrices using QNSCT. The experimental results show that the proposed algorithm not only extracts important visual information from the source image, but also preserves the texture information in the scene better. Meanwhile, the scheme outperforms state-of-the-art methods in both subjective and objective evaluations.

Bloodstain Identification Based on Visible/Near-Infrared Hyperspectral Imaging With Convolutional Neural Network

Abstract: Blood samples are easily damaged in traditional bloodstain detection and identification. In complex scenes with interfering objects, bloodstain identification may be inaccurate, with low detection rates and false-positive results. In order to meet these challenges, we propose a bloodstain detection and identification method based on hyperspectral imaging and mixed convolutional neural networks, which enables fast and efficient non-destructive identification of bloodstains. In this study, we apply visible/near-infrared reflectance hyperspectral imaging in the 380–1000 nm spectral region to analyze the shape, structure, and biochemical characteristics of bloodstains. Hyperspectral images of bloodstains on different substrates and six bloodstain analogs are experimentally obtained. The acquired spectral pixels are pre-processed by Principal Component Analysis (PCA). For bloodstains and different bloodstain analogs, regions of interest are selected from each substance to obtain pixels, which are further used in convolutional neural network (CNN) modeling. After the mixed CNN modeling is completed, pixels are selected from the hyperspectral images as a test set for bloodstains and bloodstain analogs. Finally, the bloodstain recognition ability of the mixed 2D-3D CNN model is evaluated by analyzing the kappa coefficient and classification accuracy. The experimental results show that the accuracy of the constructed CNN bloodstain identification model reaches 95.4%. Compared with other methods, the bloodstain identification method proposed in this study has higher efficiency and accuracy in complex scenes. The results of this study will provide a reference for the future development of the bloodstain online detection system.

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

Abstract: In this paper, we introduce a deep neural network (DNN) for forecasting the intra-day solar irradiance, photovoltaic PV plants, regardless of whether or not they have energy storage, can benefit from the work being done here. The proposed DNN utilises a number of different methodologies, two of which are cloud motion analysis and machine learning, in order to make forecasts regarding the climatological conditions of the future. In addition to this, the accuracy of the model was evaluated in light of the data sources that were easily accessible. In general, four different cases have been investigated. According to the findings, the DNN is capable of making more accurate and reliable predictions of the incoming solar irradiance than the persistent algorithm. This is the case across the board. Even without any actual data, the proposed model is considered to be state-of-the-art because it outperforms the current NWP forecasts for the same time horizon as those forecasts. When making predictions for the short term, using actual data to reduce the margin of error can be helpful. When making predictions for the long term, however, weather information can be beneficial.

Double-function enhancement algorithm for lowillumination images based on Retinex theory

Abstract: In order to solve the problems of noise amplification and excessive enhancement caused by low contrast and uneven illumination in the process of low-illumination image enhancement, a high-quality image enhancement algorithm is proposed in this paper. First, the total-variation model is used to obtain the smoothed V- and S-channel images, and the adaptive gamma transform is used to enhance the details of the smoothed V-channel image. Then, on this basis, the improved multi-scale retinex algorithms based on the logarithmic function and on the hyperbolic tangent function, respectively, are used to obtain different V-channel enhanced images, and the two images are fused according to the local intensity amplitude of the images. Finally, the three-dimensional gamma function is used to correct the fused image, and then adjust the image saturation. A lightness-order-error (LOE) approach is used to measure the naturalness of the enhanced image. The experimental results show that compared with other classical algorithms, the LOE value of the proposed algorithm can be reduced by 79.95% at most. Compared with other state-of-the-art algorithms, the LOE value can be reduced by 53.43% at most. Compared with some algorithms based on deep learning, the LOE value can be reduced by 52.13% at most. The algorithm proposed in this paper can effectively reduce image noise, retain image details, avoid excessive image enhancement, and obtain a better visual effect while ensuring the enhancement effect.

A novel dimensionality reduction algorithm for Cholangiocarcinoma hyperspectral images

Abstract: Medical hyperspectral imagery (HSI) has become a promising auxiliary diagnostic tool in the field of medical diagnosis and being offered noninvasive disease diagnosis in many cases. However, the huge number of spectral bands may lead to the curse of dimensionality and increase computational complexity. Thus, dimensionality reduction (DR) is an essential step for hyperspectral preprocessing. To maintain the cubic nature of HSI and extract more discriminative and representative information from original data, we proposed a novel DR method termed tensor-based weight-modified multi-manifold discriminant analysis (TWMDA). In this paper, two weight modified intra-class and inter-class adjacency affinity matrices are constructed to make full use of the class information and strengthen the power of capturing discriminant information from high-dimensional data. After that, balancing the effect of within-class adjacency compactness and between-class adjacency separation to obtain better classification performance in tensor space instead of vector space. Experimental results on Cholangiocarcinoma (CCA) microscope hyperspectral data sets prove the efficiency and superiority of the proposed method. Hence, this novel DR approach would be more beneficial for cancer diagnosis based on HSI.