Abstract: A pan-sharpening method based on multimodal texture correction and adaptive edge detail fusion is provided, including: fusing upsampled low-resolution multispectral (LRMS) images with panchromatic images to obtain fused images; respectively extracting intensity components of the LRMS image and the fused image; inputting the intensity components and the panchromatic images into a multimodal texture correction model, and performing optimization solution on the multimodal texture correction model through optimization method to obtain texture-corrected images; extracting details of the texture-corrected images and applying edge protection to obtain first image details; extracting details of the upsampled LRMS image and applying edge protection to obtain second image details; performing adaptive fusion on the first image details and the second image details to obtain detail information; and adding the detail information to the upsampled LRMS image to obtain final high-resolution multispectral (HRMS) images.

Abstract: A hyperspectral target detection method of a binary-classification encoder network based on a momentum update is provided, and includes following steps: converting an acquired 3-D hyperspectral image into a hyperspectral image in a 2-D matrix form, performing a clustering to obtain a clustering result, and initializing a centroid; based on the clustering result, using Euclidean distance to find pixels adjacent to each centroid as pure background pixels and target pixels, and screening pure pixels; constructing a background-target training sample set based on the pure pixels, constructing a binary-classification encoder network based on a momentum update through the background-target training sample set, calculating a loss function, and optimizing to obtain a trained binary-classification encoder network; inputting the hyperspectral image in the 2-D matrix form into the trained binary-classification encoder network, and outputting a final detection map.

Abstract: The invention discloses a cutting housing for separating sections of roll paper and a method for cutting and separating sections of roll paper. The cutting housing for separating sections of roll paper comprises a shell with a roll paper channel running through the length of the shell from front to back, and two opposite sides surrounding the roll paper channel, wherein the roll paper channel can accommodate roll paper, with one end open for the roll paper to pass through; at least one side is equipped with a cutting channel and a cutting blade, and the cutting channel extends roughly along the length of the shell and connects the roll paper channel with the exterior of the shell; and the cutting blade is arranged in the cutting channel for manually separating sections of roll paper that enter the cutting channel.

Abstract: A method for constructing a support vector machine of a nonparallel structure is provided. On the basis of a traditional parallel support vector machine (SVM), a least square term of samples is added, an additional empirical risk minimization term and an offset constraint term are added to an original optimization problem, so as to obtain two nonparallel hyperplanes respectively, and a new nonparallel support vector machine with additional empirical risk minimization is formed. The method includes: preprocessing data, solving a Lagrange multiplier of a positive-class hyperplane, solving a Lagrange multiplier of a negative-class hyperplane, solving parameters of positive-class and negative-class hyperplanes, and determining a class of a new data point. Through the new method, a new nonparallel vector machine algorithm is proposed to further improve classification accuracy of hyperspectral images on the basis of the algorithm itself, so as to obtain better classification performance.

Abstract: A collaborative active learning classification method for hyperspectral images based on capsule networks is provided in the application, the method trains base classifiers CapsViT and CapsGLOM using an initial training set; calculates BvSB values of candidate samples using the CapsViT; uses the CapsGLOM to predict labels of the candidate samples; sorts the candidate samples according to the BvSB values; puts the candidate samples after sorting into corresponding collectors according to category labels estimated by the CapsGLOM; labels information samples; updates the initial training set and candidate sample set and retrains the CapsViT and CapsGLOM; and obtains the classification results based on CapsViT and CapsGLOM after iteration.

Abstract: A hand-pushed paper cutting apparatus comprises a main body and a blade assembly installed on the main body. The main body has at least one end face oriented toward paper, and the end face is configured as a cutting face. The cutting face is provided with a receiving groove for installing the blade assembly. The blade assembly comprises a blade holder and a blade, and a gap exists between the blade holder and an inner wall of the receiving groove and is designated as a cutting area.

Abstract: A hyperspectral target detection method of a binary-classification encoder network based on a momentum update is provided, and includes following steps: converting an acquired 3-D hyperspectral image into a hyperspectral image in a 2-D matrix form, performing a clustering to obtain a clustering result, and initializing a centroid; based on the clustering result, using Euclidean distance to find pixels adjacent to each centroid as pure background pixels and target pixels, and screening pure pixels; constructing a background-target training sample set based on the pure pixels, constructing a binary-classification encoder network based on a momentum update through the background-target training sample set, calculating a loss function, and optimizing to obtain a trained binary-classification encoder network; inputting the hyperspectral image in the 2-D matrix form into the trained binary-classification encoder network, and outputting a final detection map.

Abstract: A collaborative active learning classification method for hyperspectral images based on capsule networks is provided in the application, the method trains base classifiers CapsViT and CapsGLOM using an initial training set: calculates BvSB values of candidate samples using the CapsViT: uses the CapsGLOM to predict labels of the candidate samples; sorts the candidate samples according to the BvSB values: puts the candidate samples after sorting into corresponding collectors according to category labels estimated by the CapsGLOM; labels information samples; updates the initial training set and candidate sample set and retrains the CapsViT and CapsGLOM; and obtains the classification results based on CapsViT and CapsGLOM after iteration.

Abstract: A method for constructing a support vector machine of a nonparallel structure is provided. On the basis of a traditional parallel support vector machine (SVM), a least square term of samples is added, an additional empirical risk minimization term and an offset constraint term are added to an original optimization problem, so as to obtain two nonparallel hyperplanes respectively, and a new nonparallel support vector machine with additional empirical risk minimization is formed. The method includes: preprocessing data, solving a Lagrange multiplier of a positive-class hyperplane, solving a Lagrange multiplier of a negative-class hyperplane, solving parameters of positive-class and negative-class hyperplanes, and determining a class of a new data point. Through the new method, a new nonparallel vector machine algorithm is proposed to further improve classification accuracy of hyperspectral images on the basis of the algorithm itself, so as to obtain better classification performance.

Abstract: A novel usage of catalpol.