Resource Type

Journal Article 128

Year

2023 12

2022 16

2021 10

2020 12

2019 16

2018 14

2017 12

2016 9

2015 1

2014 2

2013 1

2012 1

2011 1

2010 1

2008 2

2007 3

2006 4

2005 2

2004 2

2003 2

open ︾

Keywords

Deep learning 5

Classification 3

Ensemble learning 3

Feature extraction 3

Compressive sensing 2

Data hiding 2

Dictionary learning 2

Feature selection 2

High-speed railway 2

Hypervelocity impact 2

Image segmentation 2

Semi-supervised learning 2

AF/PSTM 1

Accumulated settlement 1

Active learning 1

Adaptive patch based processing 1

Adaptive watermarking 1

Adversarial samples 1

Alternating direction method of multipliers (ADMM) 1

open ︾

Search scope:

排序： Display mode:

Representation learning via a semi-supervised stacked distance autoencoder for image classification Research Articles

Liang Hou, Xiao-yi Luo, Zi-yang Wang, Jun Liang,jliang@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7,   Pages 963-1118 doi: 10.1631/FITEE.1900116

Abstract: is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An is a special type of , often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional , incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance . Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance method is compared with the traditional , sparse , and supervised . Experimental results verify the effectiveness of the proposed model.

Keywords： 自动编码器；图像分类；半监督学习；神经网络    

HTML PDF Collect

Two-level hierarchical feature learning for image classification Article

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 9,   Pages 897-906 doi: 10.1631/FITEE.1500346

Abstract: In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.

Keywords： Transfer learning     Feature learning     Deep convolutional neural network     Hierarchical classification     Spectral clustering    

HTML PDF Collect

Deep Learning in Medical Ultrasound Analysis: A Review Review

Shengfeng Liu, Yi Wang, Xin Yang, Baiying Lei, Li Liu, Shawn Xiang Li, Dong Ni, Tianfu Wang

Engineering 2019, Volume 5, Issue 2,   Pages 261-275 doi: 10.1016/j.eng.2018.11.020

Abstract:

Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed.

Keywords： Deep learning     Medical ultrasound analysis     Classification     Segmentation     Detection    

HTML PDF Collect

Automatic Visual Leakage Detection and Localization from Pipelines in Chemical Process Plants Using Machine Vision Techniques Reiew

Mina Fahimipirehgalin, Emanuel Trunzer, Matthias Odenweller, Birgit Vogel-Heuser

Engineering 2021, Volume 7, Issue 6,   Pages 758-776 doi: 10.1016/j.eng.2020.08.026

Abstract:

Liquid leakage from pipelines is a critical issue in large-scale process plants. Damage in pipelines affects the normal operation of the plant and increases maintenance costs. Furthermore, it causes unsafe and hazardous situations for operators. Therefore, the detection and localization of leakages is a crucial task for maintenance and condition monitoring. Recently, the use of infrared (IR) cameras was found to be a promising approach for leakage detection in large-scale plants. IR cameras can capture leaking liquid if it has a higher (or lower) temperature than its surroundings. In this paper, a method based on IR video data and machine vision techniques is proposed to detect and localize liquid leakages in a chemical process plant. Since the proposed method is a vision-based method and does not consider the physical properties of the leaking liquid, it is applicable for any type of liquid leakage (i.e., water, oil, etc.). In this method, subsequent frames are subtracted and divided into blocks. Then, principle component analysis is performed in each block to extract features from the blocks. All subtracted frames within the blocks are individually transferred to feature vectors, which are used as a basis for classifying the blocks. The k-nearest neighbor algorithm is used to classify the blocks as normal (without leakage) or anomalous (with leakage). Finally, the positions of the leakages are determined in each anomalous block. In order to evaluate the approach, two datasets with two different formats, consisting of video footage of a laboratory demonstrator plant captured by an IR camera, are considered. The results show that the proposed method is a promising approach to detect and localize leakages from pipelines using IR videos. The proposed method has high accuracy and a reasonable detection time for leakage detection. The possibility of extending the proposed method to a real industrial plant and the limitations of this method are discussed at the end.

Keywords： Leakage detection and localization     Image analysis     Image pre-processing     Principle component analysis     k-nearest neighbor classification    

HTML PDF Collect

Laplacian sparse dictionary learning for image classification based on sparse representation Article

Fang LI, Jia SHENG, San-yuan ZHANG

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11,   Pages 1795-1805 doi: 10.1631/FITEE.1600039

Abstract: Sparse representation is a mathematical model for data representation that has proved to be a powerful tool for solving problems in various fields such as pattern recognition, machine learning, and computer vision. As one of the building blocks of the sparse representation method, dictionary learning plays an important role in the minimization of the reconstruction error between the original signal and its sparse representation in the space of the learned dictionary. Although using training samples directly as dictionary bases can achieve good performance, the main drawback of this method is that it may result in a very large and inefficient dictionary due to noisy training instances. To obtain a smaller and more representative dictionary, in this paper, we propose an approach called Laplacian sparse dictionary (LSD) learning. Our method is based on manifold learning and double sparsity. We incorporate the Laplacian weighted graph in the sparse representation model and impose the l1-norm sparsity on the dictionary. An LSD is a sparse overcomplete dictionary that can preserve the intrinsic structure of the data and learn a smaller dictionary for each class. The learned LSD can be easily integrated into a classification framework based on sparse representation. We compare the proposed method with other methods using three benchmark-controlled face image databases, Extended Yale B, ORL, and AR, and one uncontrolled person image dataset, i-LIDS-MA. Results show the advantages of the proposed LSD algorithm over state-of-the-art sparse representation based classification methods.

Keywords： Sparse representation     Laplacian regularizer     Dictionary learning     Double sparsity     Manifold    

HTML PDF Collect

Astatistical distribution texton feature for synthetic aperture radar image classification Article

Chu HE, Ya-ping YE, Ling TIAN, Guo-peng YANG, Dong CHEN

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 10,   Pages 1614-1623 doi: 10.1631/FITEE.1601051

Abstract: We propose a novel statistical distribution texton (s-texton) feature for synthetic aperture radar (SAR) image classification. Motivated by the traditional texton feature, the framework of texture analysis, and the importance of statistical distribution in SAR images, the s-texton feature is developed based on the idea that parameter estimation of the statistical distribution can replace the filtering operation in the traditional texture analysis of SAR images. In the process of extracting the s-texton feature, several strategies are adopted, including pre-processing, spatial gridding, parameter estimation, texton clustering, and histogram

Keywords： Synthetic aperture radar     Statistical distribution     Parameter estimation     Image classification    

HTML PDF Collect

Web page classification based on heterogeneous features and a combination of multiple classifiers Research Articles

Li Deng, Xin Du, Ji-zhong Shen,jzshen@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7,   Pages 963-1118 doi: 10.1631/FITEE.1900240

Abstract: Precise can be achieved by evaluating features of web pages, and the structural features of web pages are effective complements to their textual features. Various classifiers have different characteristics, and multiple classifiers can be combined to allow classifiers to complement one another. In this study, a method based on heterogeneous features and a combination of multiple classifiers is proposed. Different from computing the frequency of HTML tags, we exploit the tree-like structure of HTML tags to characterize the structural features of a web page. Heterogeneous textual features and the proposed tree-like structural features are converted into vectors and fused. Confidence is proposed here as a criterion to compare the classification results of different classifiers by calculating the classification accuracy of a set of samples. Multiple classifiers are combined based on confidence with different decision strategies, such as voting, confidence comparison, and direct output, to give the final classification results. Experimental results demonstrate that on the Amazon dataset, 7-web-genres dataset, and DMOZ dataset, the accuracies are increased to 94.2%, 95.4%, and 95.7%, respectively. The fusion of the textual features with the proposed structural features is a comprehensive approach, and the accuracy is higher than that when using only textual features. At the same time, the accuracy of the is improved by combining multiple classifiers, and is higher than those of the related algorithms.

Keywords： 网页分类；网页特征；分类器组合    

HTML PDF Collect

Intertidal area classification with generalized extreme value distribution and Markov random field in quad-polarimetric synthetic aperture radar imagery None

Ting-ting JIN, Xiao-qiang SHE, Xiao-lan QIU, Bin LEI

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 2,   Pages 253-264 doi: 10.1631/FITEE.1700462

Abstract:

Classification of intertidal area in synthetic aperture radar (SAR) images is an important yet challenging issue when considering the complicatedly and dramatically changing features of tidal fluctuation. The difficulty of intertidal area classification is compounded because a high proportion of this area is frequently flooded by water, making statistical modeling methods with spatial contextual information often ineffective. Because polarimetric entropy and anisotropy play significant roles in characterizing intertidal areas, in this paper we propose a novel unsupervised contextual classification algorithm. The key point of the method is to combine the generalized extreme value (GEV) statistical model of the polarization features and the Markov random field (MRF) for contextual smoothing. A goodness-of-fit test is added to determine the significance of the components of the statistical model. The final classification results are obtained by effectively combining the results of polarimetric entropy and anisotropy. Experimental results of the polarimetric data obtained by the Chinese Gaofen-3 SAR satellite demonstrate the feasibility and superiority of the proposed classification algorithm.

Keywords： Intertidal classification     Polarimetric synthetic aperture radar     Finite mixture model     Markov random field     Generalized extreme value model    

HTML PDF Collect

Image Engineering and Its Research Status in China

Zhang Yujin

Strategic Study of CAE 2000, Volume 2, Issue 8,   Pages 91-94

Abstract:

This paper provides a well-regulated explanation of the definition as well as contents of image engineering, a classification of the theories of image engineering and the applications of image technology. In addition, a comprehensive survey on important Chinese publications about image engineering in the past five years is carried out. An analysis and a discussion of the statistics made on the classification results are also presented. This work shows a general and up-to-date picture of the current status, progress trends and application areas of image engineering in China. It also supplies useful information for readers doing research and/or application works in this field, and provides a helpful reference for editors of journals and potential authors of papers.

Keywords： image engineering     publication     survey    

HTML PDF Collect

High-payload completely reversible data hiding in encrypted images by an interpolation technique Article

Di XIAO, Ying WANG, Tao XIANG, Sen BAI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11,   Pages 1732-1743 doi: 10.1631/FITEE.1601067

Abstract: We present a new high-payload joint reversible data-hiding scheme for encrypted images. Instead of embedding data in the encrypted image directly, the content owner first uses an interpolation technique to estimate whether the location can be used for embedding and generates a location map before encryption. Next, the data hider embeds the additional data through flipping the most significant bits (MSBs) of the encrypted image according to the location map. At the receiver side, before extracting the additional data and reconstructing the image, the receiver decrypts the image first. Experimental results demonstrate that the proposed method can achieve real reversibility, which means data extraction and image recovery are free of error. Moreover, our scheme can embed more payloads than most existing reversible data hiding schemes in encrypted images.

Keywords： Encrypted image     Data hiding     Image recovery     Real reversibility     Interpolation    

HTML PDF Collect

A Rough Fuzzy Neural Classifier

Zeng Huanglin,Wang Xiao

Strategic Study of CAE 2003, Volume 5, Issue 12,   Pages 60-65

Abstract:

In this paper, the concepts of rough sets are used to define equivalence classes encoding input data sets, and eliminate redundant or insignificant attributes in data sets so that to reduce the complexity of system construction. In order to deal with ill-defined or real experimental data, an input object is represented as a fuzzy variable by fuzzy membership function, and the significant factor of the input feature corresponding to output pattern classification is incorporated to constitute a fuzzy inference so that to enhance nonlinear mapping classification. A new kind of rough fuzzy neural classifier and a learning algorithm with LSE are proposed in this paper. A integration of the merits of fuzzy and neural network technologies can not only accommodate overlapping classification and therefore increase the performance of nonlinear mapping classification, but ensure more efficiently to handle real life ambiguous and changing situations and to achieve tractability, robustness, and low-cost solutions.

Keywords： fuzzy sets     rough sets     neural networks     pattern classification    

HTML PDF Collect

Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis Article

Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao

Engineering 2021, Volume 7, Issue 7,   Pages 1002-1010 doi: 10.1016/j.eng.2020.04.012

Abstract:

Infectious keratitis is the most common condition of corneal diseases in which a pathogen grows in the cornea leading to inflammation and destruction of the corneal tissues. Infectious keratitis is a medical emergency for which a rapid and accurate diagnosis is needed to ensure prompt and precise treatment to halt the disease progression and to limit the extent of corneal damage; otherwise, it may develop a sight threatening and even eye-globe-threatening condition. In this paper, we propose a sequentiallevel deep model to effectively discriminate infectious corneal disease via the classification of clinical images. In this approach, we devise an appropriate mechanism to preserve the spatial structures of clinical images and disentangle the informative features for clinical image classification of infectious keratitis. In a comparison, the performance of the proposed sequential-level deep model achieved 80% diagnostic accuracy, far better than the 49.27% ± 11.5% diagnostic accuracy achieved by 421 ophthalmologists over 120 test images.

Keywords： Deep learning     Corneal disease     Sequential features     Machine learning     Long short-term memory    

HTML PDF Collect

Public key based bidirectional shadow image authentication without pixel expansion in image secret sharing Research Article

Xuehu YAN, Longlong LI, Jia CHEN, Lei SUN,publictiger@126.com

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 1,   Pages 88-103 doi: 10.1631/FITEE.2200118

Abstract: (ISS) is gaining popularity due to the importance of digital images and its wide application to cloud-based distributed storage and multiparty secure computing. generally includes shadow image detection and identification, and plays an important role in ISS. However, traditional dealer-participatory methods, which suffer from significant or storing auxiliary information, authenticate the shadow image mainly during the decoding phase, also known as unidirectional authentication. The authentication of the shadow image in the distributing (encoding) phase is also important for the participant. In this study, we introduce a based bidirectional method in ISS without for a (k,n) threshold. When the dealer distributes each shadow image to a corresponding participant, the participant can authenticate the received shadow image with his/her private key. In the decoding phase, the dealer can authenticate each received shadow image with a secret key; in addition, the dealer can losslessly decode the secret image with any k or more shadow images. The proposed method is validated using theoretical analyses, illustrations, and comparisons.

Keywords： Image secret sharing     Shadow image authentication     Public key     Pixel expansion     Lossless decoding    

HTML PDF Collect

Recent Advances in Passive Digital Image Security Forensics: A Brief Review Review

Xiang Lin, Jian-Hua Li, Shi-Lin Wang, Alan-Wee-Chung Liew, Feng Cheng, Xiao-Sa Huang

Engineering 2018, Volume 4, Issue 1,   Pages 29-39 doi: 10.1016/j.eng.2018.02.008

Abstract:

With the development of sophisticated image editing and manipulation tools, the originality and authenticity of a digital image is usually hard to determine visually. In order to detect digital image forgeries, various kinds of digital image forensics techniques have been proposed in the last decade. Compared with active forensics approaches that require embedding additional information, passive forensics approaches are more popular due to their wider application scenario, and have attracted increasing academic and industrial research interests. Generally speaking, passive digital image forensics detects image forgeries based on the fact that there are certain intrinsic patterns in the original image left during image acquisition or storage, or specific patterns in image forgeries left during the image storage or editing. By analyzing the above patterns, the originality of an image can be authenticated. In this paper, a brief review on passive digital image forensic methods is presented in order to provide a comprehensive introduction on recent advances in this rapidly developing research area. These forensics approaches are divided into three categories based on the various kinds of traces they can be used to track—that is, traces left in image acquisition, traces left in image storage, and traces left in image editing. For each category, the forensics scenario, the underlying rationale, and state-of-the-art methodologies are elaborated. Moreover, the major limitations of the current image forensics approaches are discussed in order to point out some possible research directions or focuses in these areas.

Keywords： Digital image forensics     Image-tampering detection     Multimedia security    

HTML PDF Collect

Dual-constraint burst image denoising method Research Articles

Dan ZHANG, Lei ZHAO, Duanqing XU, Dongming LU,cszhd@zju.edu.cn,cszhl@zju.edu.cn,xdq@zju.edu.cn,ldm@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 2,   Pages 220-233 doi: 10.1631/FITEE.2000353

Abstract: has proven to be an effective mechanism for computer vision tasks, especially for and burst . In this paper, we focus on solving the burst problem and aim to generate a single clean image from a burst of noisy images. We propose to combine the power of block matching and 3D filtering (BM3D) and a convolutional neural network (CNN) for burst . In particular, we design a CNN with a divide-and-conquer strategy. First, we employ BM3D to preprocess the noisy burst images. Then, the preprocessed images and noisy images are fed separately into two parallel CNN branches. The two branches produce somewhat different results. Finally, we use a light CNN block to combine the two outputs. In addition, we improve the performance by optimizing the two branches using two different constraints: a signal constraint and a noise constraint. One maps a clean signal, and the other maps the noise distribution. In addition, we adopt block matching in the network to avoid frame misalignment. Experimental results on synthetic and real noisy images show that our algorithm is competitive with other algorithms.

Keywords： Image denoising     Burst image denoising     Deep learning    

HTML PDF Collect

Title Author Date Type Operation

Representation learning via a semi-supervised stacked distance autoencoder for image classification

Liang Hou, Xiao-yi Luo, Zi-yang Wang, Jun Liang,jliang@zju.edu.cn

Journal Article

Two-level hierarchical feature learning for image classification

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Journal Article

Deep Learning in Medical Ultrasound Analysis: A Review

Shengfeng Liu, Yi Wang, Xin Yang, Baiying Lei, Li Liu, Shawn Xiang Li, Dong Ni, Tianfu Wang

Journal Article

Automatic Visual Leakage Detection and Localization from Pipelines in Chemical Process Plants Using Machine Vision Techniques

Mina Fahimipirehgalin, Emanuel Trunzer, Matthias Odenweller, Birgit Vogel-Heuser

Journal Article

Laplacian sparse dictionary learning for image classification based on sparse representation

Fang LI, Jia SHENG, San-yuan ZHANG

Journal Article

Astatistical distribution texton feature for synthetic aperture radar image classification

Chu HE, Ya-ping YE, Ling TIAN, Guo-peng YANG, Dong CHEN

Journal Article

Web page classification based on heterogeneous features and a combination of multiple classifiers

Li Deng, Xin Du, Ji-zhong Shen,jzshen@zju.edu.cn

Journal Article

Intertidal area classification with generalized extreme value distribution and Markov random field in quad-polarimetric synthetic aperture radar imagery

Ting-ting JIN, Xiao-qiang SHE, Xiao-lan QIU, Bin LEI

Journal Article

Image Engineering and Its Research Status in China

Zhang Yujin

Journal Article

High-payload completely reversible data hiding in encrypted images by an interpolation technique

Di XIAO, Ying WANG, Tao XIANG, Sen BAI

Journal Article

A Rough Fuzzy Neural Classifier

Zeng Huanglin,Wang Xiao

Journal Article

Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis

Yesheng Xu, Ming Kong, Wenjia Xie, Runping Duan, Zhengqing Fang, Yuxiao Lin, Qiang Zhu, Siliang Tang, Fei Wu, Yu-Feng Yao

Journal Article

Public key based bidirectional shadow image authentication without pixel expansion in image secret sharing

Xuehu YAN, Longlong LI, Jia CHEN, Lei SUN,publictiger@126.com

Journal Article

Recent Advances in Passive Digital Image Security Forensics: A Brief Review

Xiang Lin, Jian-Hua Li, Shi-Lin Wang, Alan-Wee-Chung Liew, Feng Cheng, Xiao-Sa Huang

Journal Article

Dual-constraint burst image denoising method

Dan ZHANG, Lei ZHAO, Duanqing XU, Dongming LU,cszhd@zju.edu.cn,cszhl@zju.edu.cn,xdq@zju.edu.cn,ldm@zju.edu.cn

Journal Article