scholarly journals Multi-Neighborhood Convolutional Networks

2015 ◽  
Vol 1 (1) ◽  
Author(s):  
Elnaz Barshan ◽  
Paul Fieguth ◽  
Alexander Wong
Keyword(s):  
Feature Learning ◽  
Scale Space ◽  
Image Features ◽  
Superior Performance ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Image Characteristics ◽  
Single Scale ◽  
Nonlinear Scale

<p>We explore the role of scale for improved feature learning in convolutional<br />networks. We propose multi-neighborhood convolutional<br />networks, designed to learn image features at different levels of<br />detail. Utilizing nonlinear scale-space models, the proposed multineighborhood<br />model can effectively capture fine-scale image characteristics<br />(i.e., appearance) using a small-size neighborhood, while<br />coarse-scale image structures (i.e., shape) are detected through<br />a larger neighborhood. The experimental results demonstrate the<br />superior performance of the proposed multi-scale multi-neighborhood<br />models over their single-scale counterparts.</p>

scholarly journals STRUCTURALLY ADAPTIVE MATHEMATICAL MORPHOLOGY BASED ON NONLINEAR SCALE-SPACE DECOMPOSITIONS

2011 ◽  
Vol 30 (2) ◽  
pp. 111 ◽  
Author(s):  
Jesús Angulo ◽  
Santiago Velasco-Forero
Keyword(s):  
Mathematical Morphology ◽  
Scale Space ◽  
Local Regularity ◽  
Natural Image ◽  
Translation Invariant ◽  
Morphological Operators ◽  
Multi Scale ◽  
Nonlinear Scale Space ◽  
Local Intensity ◽  
Nonlinear Scale

Standard formulation of morphological operators is translation invariant in the space and in the intensity: the same processing is considered for each point of the image. A current challenging topic in mathematical morphology is the construction of adaptive operators. In previous works, the adaptive operators are based either on spatially variable neighbourhoods according to the local regularity, or on size variable neighbourhoods according to the local intensity. This paper introduces a new framework: the structurally adaptive mathematical morphology. More precisely, the rationale behind the present approach is to work on a nonlinear multi-scale image decomposition, and then to adapt intrinsically the size of the operator to the local scale of the structures. The properties of the derived operators are investigated and their practical performances are compared with respect to standard morphological operators using natural image examples.

scholarly journals An Improved Level Set Method on the Multiscale Edges

Symmetry ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1650
Author(s):  
Yao Su ◽  
Kun He ◽  
Dan Wang ◽  
Tong Peng
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Image Features ◽  
Superior Performance ◽  
Total Variation Regularization ◽  
Multiscale Decomposition ◽  
Multi Scale ◽  
Segmentation Methods ◽  
Edge Based ◽  
Feature Scale

The level set method can segment symmetrical or asymmetrical objects in real images according to image features. However, the segmentation performance varies with feature scale. In order to improve the segmentation effect, we propose an improved level set method on the multiscale edges, which combines the level set method with image multi-scale decomposition to form a unified model. In this model, the segmentation relies on multiscale edges, and the multiscale edges depend on multiscale decomposition. A novel total variation regularization is proposed in multiscale decomposition to preserve edges. The multiscale edges obtained by the multiscale decomposition are integrated into the segmentation process, and the object can be easily extracted from a proper scale. Experimental results indicate that this method has superior performance in precision, recall and F-measure, compared with relative edge-based segmentation methods, and is insensitive to noise and inhomogeneous sub-regions.

MULTISCALE MORPHOLOGICAL WATERSHED SEGMENTATION FOR GRAY LEVEL IMAGE

2006 ◽  
Vol 04 (04) ◽  
pp. 627-641 ◽  
Author(s):  
HAIHUA LIU ◽  
ZHOUHUI CHEN ◽  
CHANGSHENG XIE
Keyword(s):  
Scale Space ◽  
Image Features ◽  
Natural Scenes ◽  
Gray Level ◽  
Morphological Operators ◽  
Morphological Gradient ◽  
Wide Range ◽  
Gray Level Image ◽  
Contrast Information ◽  
Nonlinear Scale

Multiscale image analysis has been used successfully in a number of applications to segment image features according to their relative scale. In this paper, we present a new framework for the hierarchical segmentation of gray level image. The proposed scheme comprises a nonlinear scale-space and morphological gradient watersheds. Our aim is to produce a meaningful hierarchy among the objects in the image. The scale-space is based on morphological anisotropic diffusion that uses reconstruction morphological operators. Furthermore, we introduce the method to reconstruct morphological operators and the principle of the dynamics of contours in scale-space that combines scale and contrast information. The performance of the proposed segmentation scheme is presented via experimental results obtained with a wide range of image including natural scenes.

Fine-Grained 3D-Attention Prototypes for Few-Shot Learning

2020 ◽  
Vol 32 (9) ◽  
pp. 1664-1684
Author(s):  
Xin Hu ◽  
Jun Liu ◽  
Jie Ma ◽  
Yudai Pan ◽  
Lingling Zhang
Keyword(s):  
Image Reconstruction ◽  
Feature Learning ◽  
Local Features ◽  
Image Features ◽  
Superior Performance ◽  
Fine Grained ◽  
Learning Module ◽  
Class Distribution ◽  
Label Distribution ◽  
3D Attention

In the real world, a limited number of labeled finely grained images per class can hardly represent the class distribution effectively. Due to the more subtle visual differences in fine-grained images than simple images with obvious objects, that is, there exist smaller interclass and larger intraclass variations. To solve these issues, we propose an end-to-end attention-based model for fine-grained few-shot image classification (AFG) with the recent episode training strategy. It is composed mainly of a feature learning module, an image reconstruction module, and a label distribution module. The feature learning module mainly devises a 3D-Attention mechanism, which considers both the spatial positions and different channel attentions of the image features, in order to learn more discriminative local features to better represent the class distribution. The image reconstruction module calculates the mappings between local features and the original images. It is constrained by a designed loss function as auxiliary supervised information, so that the learning of each local feature does not need extra annotations. The label distribution module is used to predict the label distribution of a given unlabeled sample, and we use the local features to represent the image features for classification. By conducting comprehensive experiments on Mini-ImageNet and three fine-grained data sets, we demonstrate that the proposed model achieves superior performance over the competitors.

scholarly journals Mathematical Modelling of Glioblastomas Invasion within the Brain: A 3D Multi-Scale Moving-Boundary Approach

Mathematics ◽  
2021 ◽  
Vol 9 (18) ◽  
pp. 2214
Author(s):  
Szabolcs Suveges ◽  
Kismet Hossain-Ibrahim ◽  
J. Douglas Steele ◽  
Raluca Eftimie ◽  
Dumitru Trucu
Keyword(s):  
Moving Boundary ◽  
Diffusion Tensor ◽  
Initial Conditions ◽  
Survival Rates ◽  
Cell Dynamics ◽  
Diffusion Term ◽  
Multi Scale ◽  
Single Scale ◽  
Invasion Patterns

Brain-related experiments are limited by nature, and so biological insights are often limited or absent. This is particularly problematic in the context of brain cancers, which have very poor survival rates. To generate and test new biological hypotheses, researchers have started using mathematical models that can simulate tumour evolution. However, most of these models focus on single-scale 2D cell dynamics, and cannot capture the complex multi-scale tumour invasion patterns in 3D brains. A particular role in these invasion patterns is likely played by the distribution of micro-fibres. To investigate the explicit role of brain micro-fibres in 3D invading tumours, in this study, we extended a previously introduced 2D multi-scale moving-boundary framework to take into account 3D multi-scale tumour dynamics. T1 weighted and DTI scans are used as initial conditions for our model, and to parametrise the diffusion tensor. Numerical results show that including an anisotropic diffusion term may lead in some cases (for specific micro-fibre distributions) to significant changes in tumour morphology, while in other cases, it has no effect. This may be caused by the underlying brain structure and its microscopic fibre representation, which seems to influence cancer-invasion patterns through the underlying cell-adhesion process that overshadows the diffusion process.

scholarly journals Multi-Stage Attention-Enhanced Sparse Graph Convolutional Network for Skeleton-Based Action Recognition

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2198
Author(s):  
Chaoyue Li ◽  
Lian Zou ◽  
Cien Fan ◽  
Hao Jiang ◽  
Yifeng Liu
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Feature Learning ◽  
Superior Performance ◽  
Sparse Graph ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Spatial Graph ◽  
Multi Stage ◽  
The Time Domain

Graph convolutional networks (GCNs), which model human actions as a series of spatial-temporal graphs, have recently achieved superior performance in skeleton-based action recognition. However, the existing methods mostly use the physical connections of joints to construct a spatial graph, resulting in limited topological information of the human skeleton. In addition, the action features in the time domain have not been fully explored. To better extract spatial-temporal features, we propose a multi-stage attention-enhanced sparse graph convolutional network (MS-ASGCN) for skeleton-based action recognition. To capture more abundant joint dependencies, we propose a new strategy for constructing skeleton graphs. This simulates bidirectional information flows between neighboring joints and pays greater attention to the information transmission between sparse joints. In addition, a part attention mechanism is proposed to learn the weight of each part and enhance the part-level feature learning. We introduce multiple streams of different stages and merge them in specific layers of the network to further improve the performance of the model. Our model is finally verified on two large-scale datasets, namely NTU-RGB+D and Skeleton-Kinetics. Experiments demonstrate that the proposed MS-ASGCN outperformed the previous state-of-the-art methods on both datasets.

Multi-Scale and Single-Scale Fully Convolutional Networks for Sound Event Detection

2021 ◽  
Vol 421 ◽  
pp. 51-65
Author(s):  
Yingbin Wang ◽  
Guanghui Zhao ◽  
Kai Xiong ◽  
Guangming Shi ◽  
Yumeng Zhang
Keyword(s):  
Event Detection ◽  
Convolutional Networks ◽  
Multi Scale ◽  
Fully Convolutional Networks ◽  
Single Scale ◽  
Sound Event ◽  
Sound Event Detection

scholarly journals Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Yunong Tian ◽  
En Li ◽  
Zize Liang ◽  
Min Tan ◽  
Xiongkui He
Keyword(s):  
Image Features ◽  
Training Set ◽  
Multi Scale ◽  
Ring Rot ◽  
Image Characteristics ◽  
Different Types ◽  
Precise Diagnosis ◽  
Apple Quality ◽  
Apple Fruits ◽  
Traditional Image

Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level.

scholarly journals Real-time FPGA-based implementation of the AKAZE algorithm with nonlinear scale space generation using image partitioning

2021 ◽  
Author(s):  
Parastoo Soleimani ◽  
David W. Capson ◽  
Kin Fun Li
Keyword(s):  
Real Time ◽  
Memory Management ◽  
Scale Space ◽  
Image Resolution ◽  
Hardware Architecture ◽  
Frame Rate ◽  
Time Sharing ◽  
Scale Invariant ◽  
Nonlinear Scale Space ◽  
Nonlinear Scale

AbstractThe first step in a scale invariant image matching system is scale space generation. Nonlinear scale space generation algorithms such as AKAZE, reduce noise and distortion in different scales while retaining the borders and key-points of the image. An FPGA-based hardware architecture for AKAZE nonlinear scale space generation is proposed to speed up this algorithm for real-time applications. The three contributions of this work are (1) mapping the two passes of the AKAZE algorithm onto a hardware architecture that realizes parallel processing of multiple sections, (2) multi-scale line buffers which can be used for different scales, and (3) a time-sharing mechanism in the memory management unit to process multiple sections of the image in parallel. We propose a time-sharing mechanism for memory management to prevent artifacts as a result of separating the process of image partitioning. We also use approximations in the algorithm to make hardware implementation more efficient while maintaining the repeatability of the detection. A frame rate of 304 frames per second for a $$1280 \times 768$$ 1280 × 768 image resolution is achieved which is favorably faster in comparison with other work.

Void-dynamics in nano-wires and the role of microstructure investigated via a multi-scale physics-based model

2021 ◽  
Vol 129 (12) ◽  
pp. 125102
Author(s):  
A. S. Saleh ◽  
H. Ceric ◽  
H. Zahednamesh
Keyword(s):  
Multi Scale ◽  
Void Dynamics ◽  
Nano Wires
Sign in / Sign up

Export Citation Format

Share Document