A5042834420- Image Enhancement Techniques
- Visual Attention and Saliency Detection
- Advanced Image Fusion Techniques
- AI in cancer detection
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Power Line Inspection Robots
- Advanced Neural Network Applications
- Image and Signal Denoising Methods
- Industrial Vision Systems and Defect Detection
- Digital Media Forensic Detection
- Image and Object Detection Techniques
- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Energy Load and Power Forecasting
- Olfactory and Sensory Function Studies
- Radiomics and Machine Learning in Medical Imaging
- Digital Imaging for Blood Diseases
- Gene expression and cancer classification
- Face and Expression Recognition
- Robotics and Sensor-Based Localization
North China Electric Power University
2010-2019
Qatar University
2019
Shenyang Agricultural University
2019
Yuan Ze University
2019
Utah State University
1998-2016
Harbin Institute of Technology
2012
Accurate and timely detection of insulator flashover on power transmission lines is paramount importance to utilities. Most available solutions mainly focus the exploitation mechanism or discharge area detection, rather than identification a damaged due flashovers using captured aerial images. To this end, paper proposes multi-saliency aggregation-based porcelain fault approach. The target determined Faster-Pixelwise Image Saliency by Aggregating (F-PISA) algorithm based color structural...
During an automatic power transmission line inspection, a large number of images are collected by unmanned aerial vehicles (UAVs) to detect existing defects in components, especially insulators. However, with twin insulator strings the inspection images, when umbrella skirts rear string obstructed front string, defect detection becomes difficult. To solve this problem, we propose method self-shattering insulators based on spatial features contained images. Firstly, segmented according...
In the application of deep learning to unmanned aerial vehicle (UAV) autonomous inspection, a problem about insufficiency both quantity and quality for insulator images emerges. light this situation, sample expansion method based on combination statute 3D modelling technology is proposed. Its feasibility verified in convolutional neural network by using five kinds simulated samples. The classification accuracy acquired proposed higher comparison experimental results, which proves its...
Tumor saliency estimation aims to localize tumors by modeling the visual stimuli in medical images. However, it is a challenging task for breast ultrasound due complicated anatomic structure of and poor image quality; existing approaches only model generic stimuli, e.g., local global contrast, location, feature correlation, achieve performance tumor estimation. In this paper, we propose novel optimization estimate utilizing anatomy. First, anatomy decompose into layers using...
The level set methods have provided powerful frameworks for image segmentation. However, to obtain accurate boundaries of the objects, especially when they weak edges or inhomogeneous intensities, is still a very challenging task. Actually, we studied popular existing approaches and discovered that failed segment images with intensities in many cases. weak/blurry cause uncertainty fuzziness In this paper, novel fuzzy approach proposed. At first,<mml:math...
The identification of images irrespective their location, size and orientation is one the important tasks in pattern analysis. use global moment features has been most popular techniques for this purpose. We present a simple effective method gray-level image representation which utilizes fuzzy radial moments segments (local moments) as opposed to features. A multilayer perceptron neural network employed classification. Fuzzy entropy measure applied optimize parameters membership function....
This paper defines a new image feature called Harris vector, which is able to describe the gradient distribution in an effective way. By computing mean and standard deviation of vector local region, novel descriptors are constructed for matching invariable rigid transformation linear intensity change. Experimental evidence suggests that descriptor point has good adaptability slight view changing, JPEG compression nonlinear changing intensity, besides, line performs well too.
Breast cancer investigation is of great significance, and developing tumor detection methodologies a critical need. However, it challenging task for breast ultrasound due to the complicated structure poor quality images. In this paper, we propose novel saliency estimation model guided by enriched anatomy knowledge localize tumor. Firstly, layers are generated deep neural network. Then refine integrating non-semantic solve problems incomplete mammary layers. Meanwhile, new background map...