检索结果-内蒙古大学图书馆

Spatially Variant convolutional autoencoder Based on Patch Division for Pill Defect Detection

IEEE ACCESS 2020年 8卷 216781-216792页

作者： Kim, Sora Jo, Youngjae Cho, Jungchan Song, Jiwoo Lee, Younyoung Lee, Minsik Hanyang Univ Dept Elect & Elect Engn Ansan 15588 South Korea Hyundai Mobis Co Ltd ADAS Platform Cell Team Yongin 16891 South Korea Gachon Univ Coll Informat Technol Seongnam 13120 South Korea Daekhon Corp Adv Technol Ctr Seoul 08381 South Korea

Detecting pill defection remains challenging, despite recent extensive studies, because of the lack of defective data. In this paper, we propose a pipeline composed of a pill detection module and an autoencoder-based defect detection module to detect defective pills in pill packages. Furthermore, we created a new dataset to test our model. The pill detection module segments pills in an aluminum-plastic package into individual pills. To segment pills, we used a shallow segmentation network that is then divided into individual pills using the watershed algorithm. The defect detection module identifies defects in individual pills. It is trained only on the normal data. Thus, it is expected that the module will be unable to reconstruct defective data correctly. However, in reality, the conventional autoencoder reconstructs defective data better than expected, even if the network is trained only on normal data. Hence, we introduce a patch division method to prevent this problem. The patch division involves dividing the output of the convolutional encoder network into patch-wise features, and then applying patch-wise encoder layer. In this process, each latent patch has its independent weight and bias. This can be interpreted as reconstructing the input image using multiple local autoencoders. The patch division makes the network concentrate only on reconstructing local regions, thereby reducing the overall capacity. This prohibits the proposed network reconstructing unseen data well. Experiments show that the proposed patch division technique indeed improves the defect detection performance and outperforms existing deep learning based anomaly detection methods. The ablation study shows the efficacy of patch division and compression following the concatenation of patch-wise features.

关键词： Image reconstruction Anomaly detection Pipelines Mathematical model Generative adversarial networks Feature extraction Licenses Pill defect detection deep neural network convolutional autoencoder unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

ScCAEs: deep clustering of single-cell RNA-seq via convolutional autoencoder embedding and soft K-means

引用

BRIEFINGS IN BIOINFORMATICS 2022年第1期23卷 bbab321-bbab321页

作者： Hu, Hang Li, Zhong Li, Xiangjie Yu, Minzhe Pan, Xiutao Zhejiang Sci Tech Univ Hangzhou Peoples R China Chinese Acad Med Sci Beijing Peoples R China Peking Union Med Coll Beijing Peoples R China Nankai Univ Sch Stat & Data Sci Tianjin Peoples R China

Clustering and cell type classification are a vital step of analyzing scRNA-seq data to reveal the complexity of the tissue (e.g. the number of cell types and the transcription characteristics of the respective cell type). Recently, deep learning-based single-cell clustering algorithms become popular since they integrate the dimensionality reduction with clustering. But these methods still have unstable clustering effects for the scRNA-seq datasets with high dropouts or noise. In this study, a novel single-cell RNA-seq deep embedding clustering via convolutional autoencoder embedding and soft K-means (scCAEs) is proposed by simultaneously learning the feature representation and clustering. It integrates the deep learning with convolutional autoencoder to characterize scRNA-seq data and proposes a regularized soft K-means algorithm to cluster cell populations in a learned latent space. Next, a novel constraint is introduced to the clustering objective function to iteratively optimize the clustering results, and more importantly, it is theoretically proved that this objective function optimization ensures the convergence. Moreover, it adds the reconstruction loss to the objective function combining the dimensionality reduction with clustering to find a more suitable embedding space for clustering. The proposed method is validated on a variety of datasets, in which the number of clusters in the mentioned datasets ranges from 4 to 46, and the number of cells ranges from 90 to 30 302. The experimental results show that scCAEs is superior to other state-of-the-art methods on the mentioned datasets, and it also keeps the satisfying compatibility and robustness. In addition, for single-cell datasets with the batch effects, scCAEs can ensure the cell separation while removing batch effects.

关键词： single-cell RNA-seq deep clustering convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

One-Class Classification in Images and Videos Using a convolutional autoencoder With Compact Embedding

引用

IEEE ACCESS 2020年 8卷 86520-86535页

作者： Ribeiro, Manasses Gutoski, Matheus Lazzaretti, Andre E. Lopes, Heitor S. Catarinense Fed Inst Educ Sci & Technol IFC BR-89560000 Videira Brazil Fed Univ Technol Parana UTFPR BR-3165 Curitiba Parana Brazil

In One-Class Classification (OCC) problems, the classifier is trained with samples of a class considered normal, such that exceptional patterns can be identified as anomalies. Indeed, for real-world problems, the representation of the normal class in the feature space is an important issue, considering that one or more clusters can describe different aspects of the normality. For classification purposes, it is important that these clusters be as compact (dense) as possible, for better discriminating anomalous patterns, which is a recurrent problem in OCC tasks. This work introduces a hybrid approach using deep learning and One-Class Support Vector Machine (OC-SVM) methods, named convolutional autoencoder with Compact Embedding (CAE-CE), for enhancing the compactness of clusters in the feature space. Such an approach is still underexplored in the literature, being restricted to models within the context of metric learning. Additionally, the absence of anomalous samples during training makes it difficult to determine when to interrupt the learning process, so as to avoid over-compression of the normal examples, thus resulting in overfitting of the model. In this work, we propose a novel sensitivity-based stop criterion, and its suitability for OCC problems was assessed. Using an OC-SVM for the classification task, several experiments were done using publicly available image and video datasets. We also introduce other two new benchmarks, specifically designed for video anomaly detection in highways. The final performance of the proposed method was compared with a baseline convolutional autoencoder (CAE). Overall results suggest that the enhanced compactness introduced by the CAE-CE improved the classification performance for most datasets. Also, the qualitative analysis of frames at the visual level indicated that features learned by CAE-CE are closely correlated to the anomalous events.

关键词： Anomaly detection compact embedding convolutional autoencoder deep learning feature extraction one-class classification

来源：评论

学校读者我要写书评

暂无评论

Energy Compaction-Based Image Compression Using convolutional autoencoder

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2020年第4期22卷 860-873页

作者： Cheng, Zhengxue Sun, Heming Takeuchi, Masaru Katto, Jiro Waseda Univ Grad Sch Fundamental Sci & Engn Dept Comp Sci & Commun Engn Tokyo 1698555 Japan Waseda Res Inst Sci & Engn Tokyo 1698555 Japan JST PRESTO 4-1-8 Honcho Kawaguchi Saitama 3320012 Japan

Image compression has been an important research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and its use in image compression has gradually been increasing. In this paper, we present an energy compaction-based image compression architecture using a convolutional autoencoder (CAE) to achieve high coding efficiency. Our main contributions include three aspects: 1) we propose a CAE architecture for image compression by decomposing it into several down(up)sampling operations;2) for our CAE architecture, we offer a mathematical analysis on the energy compaction property and we are the first work to propose a normalized coding gain metric in neural networks, which can act as a measurement of compression capability;3) based on the coding gain metric, we propose an energy compaction-based bit allocation method, which adds a regularizer to the loss function during the training stage to help the CAE maximize the coding gain and achieve high compression efficiency. The experimental results demonstrate our proposed method outperforms BPG (HEVC-intra), in terms of the MS-SSIM quality metric. Additionally, we achieve better performance in comparison with existing bit allocation methods, and provide higher coding efficiency compared with state-of-the-art learning compression methods at high bit rates.

关键词： Image compression convolutional autoencoder optimum bit allocation energy compaction

来源：评论

学校读者我要写书评

暂无评论

Image denoising using deep convolutional autoencoder with feature pyramids

引用

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES 2020年第4期28卷 2096-2109页

作者： Cetinkaya, Ekrem Kirac, M. Furkan Ozyegin Univ Dept Engn Fac Comp Sci Istanbul Turkey Alpen Adria Univ Klagenfurt ITEC Inst Informat Technol Klagenfurt Austria

Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted natural images are used during training to improve robustness against various noise levels. Experimental results show that the proposed method can achieve competitive performance in blind Gaussian denoising with significantly less training time required compared to state of the art methods. Extensive experiments showed the proposed method gives promising performance in a wide range of noise levels with a single network.

关键词： Image denoising convolutional autoencoder feature pyramid image processing

来源：评论

学校读者我要写书评

暂无评论

Vector Quantized convolutional autoencoder for Low-Dose CT Image Reconstruction with Perceptual and Bias Reducing Loss

Journal of Uncertain Systems

引用

Journal of Uncertain Systems 2023年第4期16卷

作者： Ramanathan, Shalini Ramasundaram, Mohan National Institute of Technology Tiruchirappalli Tamil Nadu India

In medical imaging, Computed Tomography (CT) is one of the most often utilized imaging modalities for diagnosing different disorders. Deep learning has become significant in the field of medical imaging, specifically investigated for low-dose CT. In recently available CT Scanners, Low Dose CT (LDCT) reconstruction is presented with a post-processing approach, which uses deep learning-based methods to reduce the noise level. Applying low radiation dosage can decrease damage to patients but the projected image is corrupted with noise due to lower intensity and fewer angle measurements, resulting in excessive noise in the reconstructed CT image. Thus, the presence of noise and artifacts in LDCT images limits their potential use. Here, a vector quantized convolutional encoder network is proposed for the image reconstruction task. The network is trained using the LoDoPaB-CT Dataset and tested on chest CT images. The qualitative and quantitative results produced better quality results when compared with the recent state-of-art deep learning-based methods. The quality of the results is optimized with perceptual and Bias-Reducing loss functions. © 2023 World Scientific Publishing Company.

关键词： convolutional autoencoder deep learning Low-dose computed tomography medical image reconstruction vector quantization

来源：评论

学校读者我要写书评

暂无评论

Learning Unsupervised Visual Representations using 3D convolutional autoencoder with Temporal Contrastive Modeling for Video Retrieval

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGE...

引用

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGEMENT SCIENCES 2022年第2期7卷 272-287页

作者： Kumar, Vidit Tripathi, Vikas Pant, Bhaskar Graph Era Deemed Be Univ Dehradun Dept Comp Sci & Engn Dehra Dun Uttarakhand India

The rapid growth of tag-free user-generated videos (on the Internet), surgical recorded videos, and surveillance videos has necessitated the need for effective content-based video retrieval systems. Earlier methods for video representations are based on hand-crafted, which hardly performed well on the video retrieval tasks. Subsequently, deep learning methods have successfully demonstrated their effectiveness in both image and video-related tasks, but at the cost of creating massively labeled datasets. Thus, the economic solution is to use freely available unlabeled web videos for representation learning. In this regard, most of the recently developed methods are based on solving a single pretext task using 2D or 3D convolutional network. However, this paper designs and studies a 3D convolutional autoencoder (3D-CAE) for video representation learning (since it does not require labels). Further, this paper proposes a new unsupervised video feature learning method based on joint learning of past and future prediction using 3D-CAE with temporal contrastive learning. The experiments are conducted on UCF-101 and HMDB-51 datasets, where the proposed approach achieves better retrieval performance than state-of-the-art. In the ablation study, the action recognition task is performed by fine-tuning the unsupervised pre-trained model where it outperforms other methods, which further confirms the superiority of our method in learning underlying features. Such an unsupervised representation learning approach could also benefit the medical domain, where it is expensive to create large label datasets.

关键词： Contrastive learning convolutional autoencoder Content-based search Deep learning Video retrieval Future prediction Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Robust Place Recognition Using Illumination-compensated Image-based Deep convolutional autoencoder Features

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2020年第10期18卷 2699-2707页

作者： Park, Chansoo Chae, Hee-Won Song, Jae-Bok Korea Univ Sch Mechatron 145 Anam Ro Seoul South Korea Korea Univ Sch Mech Engn 145 Anam Ro Seoul South Korea

Place recognition is a method for determining whether a robot has previously visited the place it currently observes, thus helping the robot correct its accumulated position error. Ultimately, the robot will travel long distances more accurately. Conventional image-based place recognition uses features extracted from a bag-of-visual-words (BoVW) scheme or pre-trained deep neural network. However, the BoVW scheme does not cope well with environmental changes, and the pre-trained deep neural network is disadvantageous in that its computation time is high. Therefore, this paper proposes a novel place recognition scheme using an illumination-compensated image-based deep convolutional autoencoder (ICCAE) feature. Instead of reconstructing the raw image, the autoencoder designed to extract ICCAE features is trained to reconstruct the image, whose illumination component is compensated in the logarithm frequency domain. As a result, we can extract the ICCAE features based on a convolution layer that is robust to illumination and environmental changes. Additionally, ICCAE features can perform faster feature matching than the features extracted from existing deep networks. To evaluate the performance of ICCAE feature-based place recognition, experiments were conducted using a public dataset that includes various conditions.

关键词： convolutional autoencoder frequency image illumination compensation place recognition

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection Based on convolutional Recurrent autoencoder

引用

SENSORS 2022年第12期22卷 4647-4647页

作者： Wang, Bokun Yang, Caiqian Xiangtan Univ Coll Civil Engn & Mech Xiangtan 411100 Peoples R China Southeast Univ Sch Civil Engn Nanjing 210096 Peoples R China

As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a convolutional Recurrent autoencoder (CR-AE), which combines an attention-based convolutional Long-Short-Term Memory (ConvLSTM) network and a convolutional autoencoder. The ConvLSTM network and the convolutional autoencoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively.

关键词： video anomaly detection deep learning convolutional long-short-term memory convolutional autoencoder

来源：评论

学校读者我要写书评

暂无评论

Novel statistical downscaling emulator for precipitation projections using deep convolutional autoencoder over Northern Africa

引用

JOURNAL OF ATMOSPHERIC AND SOLAR-TERRESTRIAL PHYSICS 2021年 218卷 105614-105614页

作者： Babaousmail, Hassen Hou, Rongtao Gnitou, Gnim Tchalim Ayugi, Brian Nanjing Univ Informat Sci & Technol Binjiang Coll Wuxi Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Key Lab Atmospher Environm Monitoring & P Collaborat Innovat Ctr Atmospher Environm & Equip Sch Environm Sci & Engn Nanjing 210044 Peoples R China Org African Acad Doctors OAAD Off Kamiti Rd POB 25305-00100 Nairobi Kenya

This study employed Machine Learning (ML) technique known as convolutional autoencoder to build Statistical Downscaling Model (SDM) emulator. Eight General Circulation Models (GCMs) rainfall datasets were selected under the Representative Concentration Pathway (RCP4.5) emission scenario over Northern Africa. Historical rainfall simulation for the period 1951?2005 from 8 GCMs were applied to train/validate the SDM. To evaluate the SDM performance emulating latest Rossby Centre (RCA4) RCM, SDM results were investigated against RCM projection products (2006?2100). Continuous statistics were employed to examine the SDM performance. The SDM has exhibited positive correlation of 0.75 < R < 0.95 and low RMSE values ranging between 6.9 and 15.8 mm/month. Similarly, the bias ratio scored a low value ranging from -8.94 < bias <8.25. The SDM showed good performance in reproducing the temporal rainfall projections, whereas unsatisfactory simulation was recorded regarding the spatial rainfall projections. In conclusion, the SDM showed better performance reproducing the projections of the mean ensemble rather than the individual RCMs. For future work, the SDM could be employed to downscale the mean ensemble projections of different climate variables.

关键词： GCMs SDM convolutional autoencoder Rossby center (RCA4) Rainfall North Africa

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：