A5017842484- Advanced Image Fusion Techniques
- Industrial Vision Systems and Defect Detection
- Medical Image Segmentation Techniques
- Image Processing Techniques and Applications
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Face and Expression Recognition
- Advanced Neural Network Applications
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Image and Object Detection Techniques
- Face recognition and analysis
- Image and Video Stabilization
- Infrared Target Detection Methodologies
- Advanced Image Processing Techniques
- AI in cancer detection
- Image Enhancement Techniques
- Medical Imaging Techniques and Applications
- Brain Tumor Detection and Classification
- Phonocardiography and Auscultation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Infrared Thermography in Medicine
- Biometric Identification and Security
- Textile materials and evaluations
Zhongyuan University of Technology
2017-2025
Zhengzhou University
2019-2022
Ministry of Education of the People's Republic of China
2015
Southeast University
2014-2015
Southeast University
2015
Tiangong University
2011
Related studies have revealed that the phonological features of depressed patients are different from those healthy individuals. With increasing prevalence depression, objective and convenient early screening is necessary. To this end, we propose an automatic depression detection method based on hybrid speech extracted by deep learning, dubbed as TTFNet. Firstly, to effectively excavate intrinsic relationship among multidimensional dynamic in frequency domain, Mel spectrogram raw its related...
Seed purity directly affects the quality of seed breeding and subsequent processing products. sorting based on machine vision provides an effective solution to this problem. The deep learning technology, particularly convolutional neural networks (CNNs), have exhibited impressive performance in image recognition classification, been proven applicable sorting. However huge computational complexity massive storage requirements make it a great challenge deploy them real-time applications,...
In order to effectively detect the defects for fabric image with complex texture, this paper proposed a novel detection algorithm based on an end-to-end convolutional neural network. First, proposal regions are generated by RPN (regional Network). Then, Fast Region-based Convolutional Network method (Fast R-CNN) is adopted determine whether extracted defect or not. Finally, Soft-NMS (non-maximum suppression) and data augmentation strategies utilized improve precision. Experimental results...
Arrhythmia is a common cardiovascular disease that can threaten human life. In order to assist doctors in accurately diagnosing arrhythmia, an intelligent heartbeat classification system based on the selected optimal feature sets and AdaBoost + Random Forest model developed. This acquire ECG signals through Holter transmit them cloud platform for preprocessing extraction, features are input into classification. The analysis results output form of reports. this system, by comparing analyzing...
Reducing the radiation in computerized tomography is today a major concern radiology. Low dose (LDCT) offers sound way to deal with this problem. However, more severe noise reconstructed CT images observed under low scan protocols (e.g. lowered tube current or voltage values). In paper we propose Gamma regularization based algorithm for LDCT image reconstruction. This solution flexible and provides good balance between regularizations on l0-norm l1-norm. We evaluate proposed approach using...
Arrhythmia is one of the most common abnormal symptoms that can threaten human life. In order to distinguish arrhythmia more accurately, classification strategy multifeature combination and Stacking-DWKNN algorithm proposed in this paper. The method consists four modules. preprocessing module, signal denoised segmented. Then, multiple different features are extracted based on single heartbeat morphology, P length, QRS T PR interval, ST segment, QT RR R amplitude, amplitude. Subsequently,...
To accurately detect the fabric defects in textile quality control process, this paper proposed a novel detection method based on convolution neural network(CNN) and low-rank representation(LRR). First, characteristics of multiple nonlinear transformations multi-level abstraction ability images deep learning are used to characterize multi-layer features using CNN, then extracted concentrated into feature matrix. Second, representation model is adopted divide matrix sparse matrices, which...