- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2019
- 2018
- pattern recognition
- image
- partial discharge
- convolutional neural network(CNN)
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- green tide
- Elegant End-to-End Fully Convolutional Network (E3FCN)
- Optoelectronic Information Science and Engineering
- Shanghai Jiao Tong University
- Ocean University of China
- University of Oulu
- Wuhan University
- Central South University
- Hubei University
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Patch-Based Stereo Matching Using 3D Convolutional Neural Networks
摘要： In this paper, we propose patch-based stereo matching using 3D convolutional neural networks (CNN). We extract spatial color and disparity features simultaneously through 3D CNN. We treat stereo matching as multi-class classification that the classes are all possible disparity values. We first generate a large set of patches from stereo images for 3D CNN. Then, we get an initial disparity map through 3D CNN and refine it using color image guided filtering. The color image guided filtering minimizes outliers and refines edges in disparity without texture copying artifacts. Experimental results show that the proposed method successfully estimates disparity in smooth and discontinuity regions while preserving edges as well as outperforms state-of-the-arts in terms of average errors.
关键词： disparity,3D convolutional neural network,Stereo matching,guided filter,patch-based
更新于2025-09-04 15:30:14
-
Optical coherence tomography and computer-aided diagnosis of a murine model of chronic kidney disease
摘要： Chronic kidney disease (CKD) is characterized by a progressive loss of renal function over time. Histopathological analysis of the condition of glomeruli and the proximal convolutional tubules over time can provide valuable insights into the progression of CKD. Optical coherence tomography (OCT) is a technology that can analyze the microscopic structures of a kidney in a nondestructive manner. Recently, we have shown that OCT can provide real-time imaging of kidney microstructures in vivo without administering exogenous contrast agents. A murine model of CKD induced by intravenous Adriamycin (ADR) injection is evaluated by OCT. OCT images of the rat kidneys have been captured every week up to eight weeks. Tubular diameter and hypertrophic tubule population of the kidneys at multiple time points after ADR injection have been evaluated through a fully automated computer-vision system. Results revealed that mean tubular diameter and hypertrophic tubule population increase with time in post-ADR injection period. The results suggest that OCT images of the kidney contain abundant information about kidney histopathology. Fully automated computer-aided diagnosis based on OCT has the potential for clinical evaluation of CKD conditions.
关键词： chronic kidney disease,optical coherence tomography,medical image processing,proximal convolutional tubule
更新于2025-09-04 15:30:14
-
Visualizing Deep Learning Models for the Detection of Referable Diabetic Retinopathy and Glaucoma
摘要： IMPORTANCE Convolutional neural networks have recently been applied to ophthalmic diseases; however, the rationale for the outputs generated by these systems is inscrutable to clinicians. A visualization tool is needed that would enable clinicians to understand important exposure variables in real time. OBJECTIVE To systematically visualize the convolutional neural networks of 2 validated deep learning models for the detection of referable diabetic retinopathy (DR) and glaucomatous optic neuropathy (GON). DESIGN, SETTING, AND PARTICIPANTS The GON and referable DR algorithms were previously developed and validated (holdout method) using 48 116 and 66 790 retinal photographs, respectively, derived from a third-party database (LabelMe) of deidentified photographs from various clinical settings in China. In the present cross-sectional study, a random sample of 100 true-positive photographs and all false-positive cases from each of the GON and DR validation data sets were selected. All data were collected from March to June 2017. The original color fundus images were processed using an adaptive kernel visualization technique. The images were preprocessed by applying a sliding window with a size of 28 × 28 pixels and a stride of 3 pixels to crop images into smaller subimages to produce a feature map. Threshold scales were adjusted to optimal levels for each model to generate heat maps highlighting localized landmarks on the input image. A single optometrist allocated each image to predefined categories based on the generated heat map. MAIN OUTCOMES AND MEASURES Visualization regions of the fundus. RESULTS In the GON data set, 90 of 100 true-positive cases (90%; 95% CI, 82%-95%) and 15 of 22 false-positive cases (68%; 95% CI, 45%-86%) displayed heat map visualization within regions of the optic nerve head only. Lesions typically seen in cases of referable DR (exudate, hemorrhage, or vessel abnormality) were identified as the most important prognostic regions in 96 of 100 true-positive DR cases (96%; 95% CI, 90%-99%). In 39 of 46 false-positive DR cases (85%; 95% CI, 71%-94%), the heat map displayed visualization of nontraditional fundus regions with or without retinal venules. CONCLUSIONS AND RELEVANCE These findings suggest that this visualization method can highlight traditional regions in disease diagnosis, substantiating the validity of the deep learning models investigated. This visualization technique may promote the clinical adoption of these models.
关键词： visualization,convolutional neural networks,deep learning,glaucoma,diabetic retinopathy
更新于2025-09-04 15:30:14
-
Deep Learning in Image Cytometry: A Review
摘要： Artificial intelligence, deep convolutional neural networks, and deep learning are all niche terms that are increasingly appearing in scientific presentations as well as in the general media. In this review, we focus on deep learning and how it is applied to microscopy image data of cells and tissue samples. Starting with an analogy to neuroscience, we aim to give the reader an overview of the key concepts of neural networks, and an understanding of how deep learning differs from more classical approaches for extracting information from image data. We aim to increase the understanding of these methods, while highlighting considerations regarding input data requirements, computational resources, challenges, and limitations. We do not provide a full manual for applying these methods to your own data, but rather review previously published articles on deep learning in image cytometry, and guide the readers toward further reading on specific networks and methods, including new methods not yet applied to cytometry data.
关键词： image cytometry,machine learning,biomedical image analysis,convolutional neural networks,deep learning,cell analysis,microscopy
更新于2025-09-04 15:30:14
-
Deep learning-based automatic volumetric damage quantification using depth camera
摘要： A depth camera or 3-dimensional scanner was used as a sensor for traditional methods to quantify the identified concrete spalling damage in terms of volume. However, to quantify the concrete spalling damage automatically, the first step is to detect (i.e., identify) the concrete spalling. The multiple spots of spalling can be possible within a single structural element or in multiple structural elements. However, there is, as of yet, no method to detect concrete spalling automatically using deep learning methods. Therefore, in this paper, a faster region-based convolutional neural network (Faster R-CNN)-based concrete spalling damage detection method is proposed with an inexpensive depth sensor to quantify multiple instances of spalling simultaneously in the same surface separately and consider multiple surfaces in structural elements. A database composed of 1091 images (with 853 × 1440 pixels) labeled for volumetric damage is developed, and the deep learning network is then modified, trained, and validated using the proposed database. The damage quantification is automatically performed by processing the depth data, identifying surfaces, and isolating the damage after merging the output from the Faster R-CNN with the depth stream of the sensor. The trained Faster R-CNN presented an average precision (AP) of 90.79%. Volume quantifications show a mean precision error (MPE) of 9.45% when considering distances from 100 cm to 250 cm between the element and the sensor. Also, an MPE of 3.24% was obtained for maximum damage depth measurements across the same distance range.
关键词： Convolutional neural network,Deep learning,Concrete spalling,Depth sensor,Volume quantification
更新于2025-09-04 15:30:14
-
[IEEE 2018 - 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON) - Helsinki (2018.6.3-2018.6.5)] 2018 - 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON) - CHANNEL-MISMATCH DETECTION ALGORITHM FOR STEREOSCOPIC VIDEO USING CONVOLUTIONAL NEURAL NETWORK
摘要： Channel mismatch (the result of swapping left and right views) is a 3D-video artifact that can cause major viewer discomfort. This work presents a novel high-accuracy method of channel-mismatch detection. In addition to the features described in our previous work, we introduce a new feature based on a convolutional neural network; it predicts channel-mismatch probability on the basis of the stereoscopic views and corresponding disparity maps. A logistic-regression model trained on the described features makes the ?nal prediction. We tested this model on a set of 900 stereoscopic-video scenes, and it outperformed existing channel-mismatch detection methods that previously served in analyses of full-length stereoscopic movies.
关键词： machine learning,channel mismatch,quality assessment,convolutional neural networks,Stereoscopic video
更新于2025-09-04 15:30:14
-
[IEEE 2018 International Conference on 3D Vision (3DV) - Verona (2018.9.5-2018.9.8)] 2018 International Conference on 3D Vision (3DV) - Learning Material-Aware Local Descriptors for 3D Shapes
摘要： Material understanding is critical for design, geometric modeling, and analysis of functional objects. We enable material-aware 3D shape analysis by employing a projective convolutional neural network architecture to learn material-aware descriptors from view-based representations of 3D points for point-wise material classification or material-aware retrieval. Unfortunately, only a small fraction of shapes in 3D repositories are labeled with physical materials, posing a challenge for learning methods. To address this challenge, we crowdsource a dataset of 3080 3D shapes with part-wise material labels. We focus on furniture models which exhibit interesting structure and material variability. In addition, we also contribute a high-quality expert-labeled benchmark of 115 shapes from Herman-Miller and IKEA for evaluation. We further apply a mesh-aware conditional random field, which incorporates rotational and reflective symmetries, to smooth our local material predictions across neighboring surface patches. We demonstrate the effectiveness of our learned descriptors for automatic texturing, material-aware retrieval, and physical simulation.
关键词： material-aware retrieval,material-aware descriptors,3D shapes,convolutional neural network,material classification
更新于2025-09-04 15:30:14
-
[IEEE 2018 3rd International Conference for Convergence in Technology (I2CT) - Pune (2018.4.6-2018.4.8)] 2018 3rd International Conference for Convergence in Technology (I2CT) - Towards Designing an Adaptive Framework for Facial Image Quality Estimation at Edge
摘要： This paper proposes a framework for facial image quality estimation in order to address the limitation of real-time applicability of facial recognition. This framework determines whether an image is suitable for facial recognition. We ?rst exploit machine learning algorithms to map the relationship between image quality features and performance of facial recog- nition. We extract a variety of features (like focus measure, brightness, obscured face) and study their in?uence on the accuracy of face recognition. After examining the results of this approach, we then used deep learning to build a binary classi?er which accepts or rejects images before sending them for actual facial recognition. This decision is taken based on the probability of the facial recognition framework correctly matching a face from the image. We used images from the Chokepoint dataset, and OpenFace- an open source facial recognition software, for building our framework.
关键词： Classi?cation,Deep Learning,Edge Computing,Convolutional Neural Networks,Machine Learning
更新于2025-09-04 15:30:14
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Sea Ice Classification with Convolutional Neural Networks Using Sentinel-L Scansar Images
摘要： In this paper, the Sentinel-1 ScanSAR IR GRD products are used for sea ice mapping using convolutional neural networks (CNN). The sea and ice are classified as 2 types and 4 types respectively according to their SAR image textures. They are smooth sea, rough sea, granular ice, massive ice, smooth ice and striped ice. The Sentinel-1 SAR images are firstly pre-processed using ESA SNAP software. Then the classes are interpreted manually for chip preparation and annotations. Chips with 3 spatial scales (32x32, 64x64, 128x128) are used for training input of the CNN. The trained CNN is then used for generation of sea ice map from the ScanSAR image. The results are promising. Further work is still going on.
关键词： sea ice,classification,convolutional neural networks,deep learning,SAR
更新于2025-09-04 15:30:14
-
Efficient Variable Rate Image Compression with Multi-scale Decomposition Network
摘要： While deep learning image compression methods have shown impressive coding performance, most of them output a single optimized compression rate using a trained specific network. However, in practical it is essential to support variable rate compression or meet a target rate with high coding performance. This paper proposes a novel image compression method, making it possible for a single CNN model to generate variable rate efficiently with optimized rate-distortion (RD) performance. The method consists of CNN based multi-scale decomposition transform and content adaptive rate allocation. Specifically, the transform network is learned to decompose the input image into several scales of representations while optimizing the RD performance for all scales. Rate allocation algorithms for two typical scenarios are provided to determine the optimal scale of each image block for a given target rate or quality-factor. For a target rate, the allocation is adaptive based on content complexity. And for a target quality-factor which indicates a trade-off between rate and quality, the optimal scale is determined by minimizing the RD cost. Experimental results have shown that our method has outperformed JPEG2000 and BPG standards with high efficiency and state-of-the-art RD performance as measured by MS-SSIM. Moreover, our method can strictly control the rate to generate the target compression result.
关键词： Convolutional neural network,Multi-scale decomposition transform,Content adaptive rate allocation,Lossy image compression,Variable rate image compression
更新于2025-09-04 15:30:14