- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Oil Spill Detection and Mitigation
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Advanced Vision and Imaging
- Advanced Mathematical Modeling in Engineering
- Medical Image Segmentation Techniques
- Numerical methods in inverse problems
- Urban Heat Island Mitigation
- Educational Reforms and Innovations
- Drug Transport and Resistance Mechanisms
- Education, Innovation and Language Studies
- Nonlinear Partial Differential Equations
- Gut microbiota and health
- Second Language Acquisition and Learning
- Graph Theory and Algorithms
- Higher Education and Teaching Methods
- Industrial Vision Systems and Defect Detection
- Advanced Algorithms and Applications
- Ubiquitin and proteasome pathways
- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Image and Signal Denoising Methods
- Image Retrieval and Classification Techniques
Second Affiliated Hospital of Nanchang University
2019-2024
Nanchang University
2019-2024
Taiyuan University of Technology
2024
Shaanxi Normal University
2024
Wuhan Donghu University
2019-2024
First Affiliated Hospital of Gannan Medical University
2024
Dalian University of Foreign Languages
2011-2023
Guizhou University of Finance and Economics
2023
Hebei University of Science and Technology
2021
Soochow University
2020
Abstract Fluorescent background is a major problem in recoding the Raman spectra of many samples, which swamps or obscures signals. The should be suppressed order to perform further qualitative quantitative analysis spectra. For this purpose, an intelligent background‐correction algorithm developed, simulates manual procedure intelligently. It basically consists three aspects: (1) accurate peak position detection spectrum by continuous wavelet transform (CWT) with Mexican Hat as mother...
Accurate point matching is a critical and challenging process in feature-based image registration. In this paper, simple robust feature algorithm, called Restricted Spatial Order Constraints (RSOC), proposed to remove outliers for registering aerial images with monotonous backgrounds, similar patterns, low overlapping areas, large affine transformation. RSOC, both local structure global information are considered. Based on adjacent spatial order, an invariant descriptor defined, formulated...
Vulvovaginal candidiasis (VVC) is the second most common cause of vaginal infection globally after bacterial vaginosis (BV) and associated with adverse reproductive obstetric outcomes, including preterm delivery, sexually transmitted infections pelvic inflammatory disease. Although effective control VVC achievable use traditional treatment strategies (i.e., antifungals), possibility drug intolerance, failure recurrence, as well appearance antifungal-resistant Candida species remain critical...
In the present study, probiotic compounds were studied through clinical and animal model verification to try find auxiliary treatment measures after gastrectomy, explore their potential mechanism.
Platinum-based antitumor drugs are broad-spectrum agents with unique mechanisms of action. Combination chemotherapy regimens based on platinum commonly used in cancer treatment. However, these can cause various adverse reactions the human body through different routes administration, including reproductive toxicity, genetic and embryonic developmental toxicity. Preventing effects is crucial to enhance patients' quality life reduce healthcare costs. This article discusses types history active...
Edge detection is a crucial approach for the location and acreage calculation of oil slick when spills on sea. In this paper, in view intensity inhomogeneity, high noise, blurring infrared (IR) aerial images, novel algorithm proposed to detect edges IR images. algorithm, we define an energy function model combining region-scalable-fitting concept global minimization active contour (GMAC) model. The avoids existence local minima meanwhile deals with weak edge boundaries exiting spill process...
Intrauterine adhesion (IUA) is one of the most common diseases reproductive system. Due to high postoperative recurrence rate IUA, it crucial identify possible causes pathogenesis and this disease. In present study, a high‑throughput sequencing approach was applied compare vaginal microbiota between healthy women [healthy secretion (HVS) group] patients with IUA [intrauterine patients' (IAVS) group]. The results indicated that had little effect on number bacterial species. However, at phylum...
Currently, the main difficulty in separating land surface temperature (LST) and emissivity (LSE) from field-measured hyperspectral Thermal Infrared (TIR) data lies solving radiative transfer equation (RTE). Based on theory of wavelet transform (WT), this paper proposes a method for accurately effectively LSTs LSEs TIR data. We show that number unknowns RTE can be reduced by decomposing reconstructing LSE spectrum, thus making solvable. The final results errors introduced WT are negligible....
Accurate point matching is widely used, and it a critical challenging process in feature-based image registration. To improve feature accuracy on putative matches with heavy outliers similar local structures, an accurate robust algorithm based minimum relative motion entropy (MRME) proposed, which the between their K-nearest neighbors formulated. Based clustering result, defined to find coincident motions. According motions MRME, are removed two-stage match strategy. With quasi-linear time...
Image registration is a crucial progress in detecting oil spilled on the sea and also important for estimating volume of spill, especially when one image cannot cover entire polluted region. In this article, new algorithm proposed to register geometrically distorted aerial images spill accurately automatically. There are two stages algorithm: coarse fine registration. Invariants-based similarity relative space distance applied matching. Then improved iterative closest point (ICP) used...
Due to the existence of repetitive patterns, ambiguous features, and similar local structures in remote sensing images, it is inevitable that outliers with pseudoisomorphic are preserved as inliers, which makes point matching still a challenging problem. To improve accuracy feature matching, discriminative algorithm named structure consensus constraint proposed remove from putative correspondences find two graphs composed inliers. First, descriptor evaluate corresponding similarity K-nearest...
With the increasing demand of society for sports rehabilitation, many colleges and universities have set up rehabilitation biomechanics specialty, which has been listed as a professional basic course in some universities. However, there are still problems experimental teaching this course, such failure to recognize human movements medical images timely manner, makes it impossible judge whether motion standard. multi feature image fusion can become new method, widely used application research...
This paper propose a novel adaptive multi-bit digital image watermarking algorithm based on discrete cosine transform and human visual system. has several characteristics: first, embed 2 bits water-marking information into one embedding point is realized. Second, HVS property used to watermark adaptively in the texture direction of insensitive area. Experimental results show that proposed scheme imperceptible robust against various signal processing such as cropping, JPEG compression,...
Feature matching is a crucial and challenging process in feature-based image registration. Mismatch always inevitable registration for the feature methods that just use local features, no matter how powerful discrimination of point descriptor is. To solve this problem, paper, relative moment affine invariants are used to compare similarity two triangles, then new global method proposed match points accurately based on graph structure. In process, Genetic Algorithm applied find most similar...
Accurate point matching is a crucial and challenging process in feature-based image registration, especially for images with monotonous background, In this paper, we propose robust algorithm registration which integrates cyclic string method two decision criteria, i. e., the stability accuracy of transformation error. algorithm, filtering strategy designed to eliminate dubious matches get exactly matched sets. The performance proposed evaluated by registering typical pairs containing...
1. Bresson X, Chan T. Fast dual minimization of the vectorial total variation norm and applications to color image processing. Inverse Problems Imaging 2008; 2(4): 455-484. http://dx.doi.org/10.3934/ipi.... CrossRef Google Scholar
Feature matching is a critical and challenging process in feature-based image registration. In this paper, robust feature point method, combined Scale-Invariant Transform (SIFT) Support Vector Machine (SVM), proposed to match features for registering dynamic aerial images. every described by 128 dimensional SIFT descriptor as training vector. Then model built SVM. Using model, points are classified into two categories, one matched set the other unmatched set. Three pairs of infrared (IR)...