检索结果-南通市图书馆

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4863-4882页

作者： Tao Zhou Yujie Guo Caiyue Peng Yuxia Niu Yunfeng Pan Huiling Lu School of Computer Science and Engineering North Minzu UniversityYinchuan750021China School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China Key Laboratory of image and Graphics Intelligent processing of State Ethnic Affairs Commission North Minzu UniversityYinchuan750021China

Computer-aided diagnosis of pneumonia based on deep learning is a research ***,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this *** main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale *** MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features ***,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature ***,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different *** verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried *** the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,*** the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,*** model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

关键词： Pneumonia X-ray image ResNet multi-scale feature direction feature transformer

Natural color image segmentation using integrated mechanism

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2003年第11期1卷 645-647页

作者：徐杰施鹏飞 institute of image processing and pattern recognition Shanghai Jiao Tong University Shanghai 200030

A new method for natural color image segmentation using integrated mechanism is proposed in this paper. Edges are first detected in term of the high phase congruency in the gray-level image. K-mean cluster is used to label long edge lines based on the global color information to estimate roughly the distribution of objects in the image, while short ones are merged based on their positions and local color differences to eliminate the negative affection caused by texture or other trivial features in image. Region growing technique is employed to achieve final segmentation results. The proposed method unifies edges, whole and local color distributions, as well as spatial information to solve the natural image segmentation problem. The feasibility and effectiveness of this method have been demonstrated by various experiments.

关键词： image processing

A novel enhancement method for low illumination images based on microarray camera

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics(A Journal of Chinese Universities) 2017年第3期32卷 313-322页

作者： ZOU Jian-cheng ZHENG Wen-qi YANG Zhi-hui institute of image processing and pattern recognition North China University of Technology Beijing 100144 China.

It is difficult but important to get clear information from the low illumination images. In recent years the research of the low illumination image enhancement has become a hot topic in image processing and computer vision. The Retinex algorithm is one of the most popular methods in the field and uniform illumination is necessary to enhance low illumination image quality by using this algorithm. However, for the different areas of an image with contrast brightness differences, the illumination image is not smooth and causes halo artifacts so that it cannot retain the detail information of the original images. To solve the problem, we generalize the multi-scale Retinex algorithm and propose a new enhancement method for the low illumination images based on the microarray camera. The proposed method can well make up for the deficiency of imbalanced illumination and significantly inhibit the halo artifacts as well. Experimental results show that the proposed method can get better image enhancement effect compared to the multi-scale Retinex algorithm of a single image enhancement. Advantages of the method also include that it can significantly inhibit the halo artifacts and thus retain the details of the original images, it can improve the brightness and contrast of the image as well. The newly developed method in this paper has application potential to the images captured by pad and cell phone in the low illumination environment.

关键词： low illumination microarray camera multi-scale Retinex image sharpening

在线全文

学校读者我要写书评

暂无评论

Chinese Optics Letters 2003年第11期1卷 637-640页

作者：杜培军方涛唐宏施鹏飞 institute of image processing and pattern recognition Shanghai Jiaotong University Shanghai 200030 Department of Spatial Informatics China University of Mining and Technology Xuzhou 221008 institute of image processing and pattern recognition Shanghai Jiaotong University Shanghai 200030

In this paper, two new similarity measure methods based on set theory were proposed. Firstly, similarity measure of two sets based on set theory and set operation was discussed. This principle was used to spectral vectors, and two approaches were proposed. The first method was to create a spectral polygon corresponding to spectral curve, and similarity of two spectral vectors can be replaced by that of two polygons. Area of spectral polygon was used as quantification function and some effective indexes for similarity and dissimilarity were computed. The second method was to transform the original spectral vector to encoding vector according to absorption or reflectance feature bands, and similarity measure was conducted to encoding vectors. It proved that the spectral polygon-based approach was effective 'and can be used to hyperspectral RS image retrieval.

关键词： image processing Set theory

High Performance of a TOA-TDOA Hybrid GSM Location System for Intelligent Transportation Systems

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2003年第3期20卷 84-87页

作者：徐志扬施鹏飞 The institute of image processing and pattern recognition Shanghai Jiaotong UniversityShanghai 200030

This paper illustrates the performance of a mobile positioning technique applicable to a GSM *** experimental system of a network-based GSM positioning for ITS has been proposed, and the hybrid TOA-TDOA method based on GSM signaling has been analyzed and used. The performance of the proposed system is showed through simulations in urban and suburban environments. The accuracy for 67% mobile stations is 70 m in urban and 120 m in suburban. The accuracy, coverage and network load of positioning system are also analyzed.

关键词： wireless location Time difference of arrival Angle of arrival Time of arrival GSM Intelligent transportation system

Active Appearance Model Based Hand Gesture recognition

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2005年第4期22卷 67-71页

作者：滕晓龙于威威刘重庆 institute of image processing and pattern recognition Shanghai Jiaotong University Shanghai 200030

This paper addresses the application of hand gesture recognition in monocular image sequences using Active Appearance Model （AAM）, For this work, the proposed algorithm is composed of constricting AAMs and fitting the models to the interest region. In training stage, according to the manual labeled feature points, the relative AAM is constructed and the corresponding average feature is obtained. In recognition stage, the interesting hand gesture region is firstly segmented by skin and movement cues. Secondly, the models are fitted to the image that includes the hand gesture, and the relative features are extracted. Thirdly, the classification is done by comparing the extracted features and average features. 30 different gestures of Chinese sign language are applied for testing the effectiveness of the method. The Experimental results are given indicating good performance of the algorithm.

关键词： human-machine interaction hand gesture recognition AAM sign language.

Global motion estimation with Gabor wavelet transform

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第3期16卷 645-650页

作者：王朋刘重庆 inst .of I mage processing &pattern recognition Shanghai Jiaotong Univ

A novel algorithm of global motion estimation is proposed. First, through Gabor wavelet transform （GWT）, a kind of energy distribution of image is obtained and checkpoints are selected according to a probability decision approach proposed. Then, the initialized motion vectors are obtained via a hierarcbal block-matching based on these checkpoints. Finally, by employing a 3-parameter motion model, precise parameters of global motion are found. From the experiment, the algorithm is reliable and robust.

关键词： global motion estimation Gabor wavelet transform probability decision block-matching.

Modulation classification based on spectrogram

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第3期16卷 475-488页

作者：杨杰叶晨洲周越 inst .of I mage processing &pattern recognition Shanghai Jiaotong Univ

The aim of modulation classification （MC） is to identify the modulation type of a commtmication signal. It plays an important role in many cooperative or noncooperative communication applications. Three spectrogram-based modulation classification methods are proposed. Their recognition scope and performance are investigated or evaluated by theoretical analysis and extensive simulation studies. The method taking moment-like features is robust to frequency offset while the other two, which make use of principal component analysis （PCA） with different transformation inputs, can achieve satisfactory accuracy even at low SNR （as low as 2 dB）. Due to the properties of spectrogram, the statistical pattern recognition techniques, and the image preprocessing steps, all of our methods are insensitive to unknown phase and frequency offsets, timing errors, and the arriving sequence of symbols.

关键词： modulation classification spectrcgram image processing principal component analysis support vector machine.

Probabilistic data association algorithm based on ensemble Kalman filter with observation iterated update

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2015年第3期21卷 301-308页

作者：胡振涛 Fu Chunling Li Junwei institute of image processing and pattern recognition Henan University College of Physics and Electronics Henan University

Aiming at improving the observation uncertainty caused by limited accuracy of sensors,and the uncertainty of observation source in clutters,through the dynamic combination of ensemble Kalman filter(EnKF) and probabilistic data association(PDA),a novel probabilistic data association algorithm based on ensemble Kalman filter with observation iterated update is ***,combining with the advantages of data assimilation handling observation uncertainty in EnKF,an observation iterated update strategy is used to realize optimization of EnKF in *** the object is to further improve state estimation precision of nonlinear ***,the above algorithm is introduced to the framework of PDA,and the object is to increase reliability and stability of candidate echo *** addition,in order to decrease computation complexity in the combination of improved EnKF and PDA,the maximum observation iterated update mechanism is applied to the iteration of ***,simulation results verify the feasibility and effectiveness of the proposed algorithm by a typical target tracking scene in clutters.

关键词： nonlinear filter observation iterated update ensemble Kalman filter (EnKF) probabilistic data association (PDA)