Hyperspectral image classification via parallel multi-input mechanism-based convolutional neural network

In recent years, Convolutional Neural Networks (CNNs) have succeeded in Hyperspectral Image Classification and shown excellent performance. However, the implicit spatial information between features, which significantly affect the classification performance of CNNs, are neglected in most existing CNN models. To address this issue, we propose a parallel multi-input mechanism-based CNN (PMI-CNN) fully exploiting the implicit spectral-spatial information in Hyperspectral Images. PMI-CNN employs four parallel convolution branches to extract spatial features with different levels, feature maps from each branch are spliced, and used as the classifier’s input. The proposed PMI-CNN’s classification performance is examined on three benchmark datasets and compared with six competing models. Experimental results show that PMI-CNN has better classification performance via exploiting spectral-spatial information. Compared with other models, the classification accuracy of PMI-CNN on the Indian Pines dataset is significantly improved, varying between 1.23%-25.36%. Likewise, the PMI-CNN, performed on the other two benchmark datasets, achieves 0.54%-12.26% and 0.96%-8.38% advantages in overall accuracy over the other six models, respectively.

     

ECG signal classification via combining hand-engineered features with deep neural network features

The electrocardiogram (ECG) has been proven to be the most common and effective approach to investigate cardiovascular diseases because that it is simple, noninvasive and inexpensive. However, the differences among ECG signals are difficult to be distinguished. In this paper, hand-engineered ECG features and automatic ECG features extracted with deep neural networks are combined to generate high dimensional features. First, rich hand-engineered features were extracted using some extraction methods for common ECG features. Second, a convolutional neural network model was designed to extract the ECG features automatically. High dimensional feature set is obtained through combing hand-engineered features and automatic features. To get the most informative ECG feature combination, a feature selection method based on mutual information was proposed. An ensemble learning method was then used to build the classification model for abnormal ECG types. Six atrial arrhythmia subtypes’ ECG signals from the Chinese cardiovascular disease database dataset were analyzed through the proposed method. The precision of the classification results reaches 98.41%, which is higher than the results based on other current methods.

     

Quantum convolutional neural network for image classification

Pattern Analysis and Applications - In this paper we propose two scale-inspired local feature extraction methods based on Quantum Convolutional Neural Network (QCNN) in the Tensorflow quantum...     

Kernel-blending connection approximated by a neural network for image classification

Computational Visual Media - This paper proposes a kernel-blending connection approximated by a neural network (KBNN) for image classification. A kernel mapping connection structure, guaranteed by...     

基于KMNF和BP神经网络的高光谱遥感影像分类

为了对高维非线性的高光谱影像进行降维及信息提取,提出了高光谱影像核最小噪声分离变换(kernel minimum noise fraction,KMNF)特征提取后利用BP神经网络分类的方法.以高光谱影像KMNF特征提取后的前几个特征分量作为BP神经网络的输入,进行BP神经网络分类,并与单独的高光谱影像BP神经网络分类进行比较.美国内华达州CUPRITE矿区AVIRIS数据的实验结果表明,基于KMNF和BP神经网络的高光谱影像分类较单独BP神经网络分类总体精度及时间性能均得到提高.     

Strategies and best practice for neural network image classification

This paper examines a number of experimental investigations of neural networks used for the classification of remotely sensed satellite imagery at the Joint Research Centre over a period of five years, and attempts to draw some conclusions about 'best practice' techniques to optimize network training and overall classification performance. The paper examines best practice in such areas as: network architecture selection; use of optimization algorithms; scaling of input data; avoidance of chaos effects; use of enhanced feature sets; and use of hybrid classifier methods. It concludes that a vast body of accumulated experience is now available, and that neural networks can be used reliably and with much confidence for routine operational requirements in remote sensing.     

CT image classification based on convolutional neural network

Neural Computing and Applications - With the rapid development of the Internet, image information is explosively growing. Traditional image classification methods are difficult to deal with huge...     

关键点图对比图像分类方法

深度学习是目前图像分类的主流方法之一,其重视感受野内的局部信息,却忽略了类别的先验拓扑结构信息。本文提出了一种新的图像分类方法,即Key-D-Graph,这是基于关键点的图对比网络方法,在识别图像类别时可以显式地考虑拓扑先验结构。具体地,图像分类需要2个步骤,第一步是基于关键点构建图像的图表达,即采用深度学习方法识别图像中目标类别的可能关键点,并采用关键点坐标生成图像的拓扑图表达;第二步基于关键点的图像图表达建立图对比网络,以估计待识别图与目标类别之间的结构差异,实现类别判断,该步骤利用了物体的拓扑先验结构信息,实现了基于图像全局结构信息的物体识别。特别的,Key-D-Graph的中间输出结果为类别关键点,具有语义可解释性,便于在实际应用中对算法逐步分析调试。实验结果表明,提出的方法可在效率和精度上超过主流方法,且通过消融实验分析验证了拓扑结构在分类中的作用机制和有效性。     

基于小波神经网络的医学图像分类方法

为了提高乳腺癌早期诊断的准确率,将小波理论与神经网络理论相结合提出改进的小波神经网络算法。将经过预处理的医学图像提取特征值,然后利用基于改进的小波神经网络算法的分类器对医学图像进行分类。通过实验表明此分类器具有较高的分类精度,是有效和可行的;与单独使用后向传播神经网络算法相比分类效果也得到了改善。     

Bi-branch deconvolution-based convolutional neural network for image classification

With the rise of deep neural network, convolutional neural networks show superior performances on many different computer vision recognition tasks. The convolution is used as one of the most efficient ways for extracting the details features of an image, while the deconvolution is mostly used for semantic segmentation and significance detection to obtain the contour information of the image and rarely used for image classification. In this paper, we propose a novel network named bi-branch deconvolution-based convolutional neural network (BB-deconvNet), which is constructed by mainly stacking a proposed simple module named Zoom. The Zoom module has two branches to extract multi-scale features from the same feature map. Especially, the deconvolution is borrowed to one of the branches, which can provide distinct features differently from regular convolution through the zoom of learned feature maps. To verify the effectiveness of the proposed network, we conduct several experiments on three object classification benchmarks (CIFAR-10, CIFAR-100, SVHN). The BB-deconvNet shows encouraging performances compared with other state-of-the-art deep CNNs.     

基于非对称双分支交互神经网络的水下生物识别

针对水底环境存在着可见度低、光照条件差、物种间特征差异不明显等问题,基于卷积神经网络,提出了一种新的非对称双分支水下生物分类模型。模型中交互分支利用不同的卷积神经网络中间层提取局部特征并通过交互模块对局部特征进行交互,增强分类模型的局部特征学习能力;卷积神经网络分支可以有效地学习到目标的全局特征,弥补交互分支中忽略的全局信息。在Fish4-Knowledge(F4K)、Eilat、RAMAS三个数据集上取得了98.9%、98.3%、97.9%的准确率,较前人方法有显著提高;视觉解释也验证了该模型可以有效地捕捉到局部特征并消除背景影响。最终显示,该模型在水下环境具有良好的分类性能。     

量型图像分类神经网络改进研究

当前普遍使用的轻量型神经网络仍然存在计算量与参数量过大的问题,导致算力较低的廉价移动设备无法快速完成图像分类任务.针对此问题提出了一种更适合于应用在算力较低的廉价移动设备上的轻量型神经网络,引入了代价较小的线性操作与特征图合并操作用于减少神经网络的计算量与参数量,还引入了改进的残差结构、注意力机制和标签平滑技术用于提高结果判断的准确率.基于PD-38数据集的实验表明,该神经网络相比传统的轻量型神经网络使用较小的计算量与参数量可以达到较高的分类准确率.在公共数据集CIFAR-10上的实验进一步表明该神经网络具有通用性.     

Artificial neural network visual model for image quality enhancement

An artificial neural network visual model is developed, which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate for the coding distortions. This provides a generic postprocessing technique that can be applied to all the main coding methods. Experimental results involving postprocessing of the JPEG and quadtree coding systems show that the proposed artificial neural network visual model significantly enhances the quality of reconstructed images, both in terms of the objective peak signal-to-noise ratio and subjective visual assessment.     

Improved convolutional neural network in remote sensing image classification

Neural Computing and Applications - The classification of land cover is the first step in the analysis and application of remote sensing data in land resources. How to solve the multi-category...     

基于叠层循环神经网络的语义关系分类模型

基于循环神经网络结合句法结构的方法被广泛运用于关系分类,利用神经网络对输入的编码信息自动获取特征并实现关系分类;然而,目前已有的方法主要是基于单一特定句法结构的模型,而特定句法结构的模型不能够迁移到其他句法结构类型上。针对该问题,提出一种融合多句法结构的叠层循环神经网络模型。该叠层循环神经网络分为两层进行网络构建,首先在序列层进行实体预训练,通过Bi-LSTM-CRF融合attention机制,提高模型对文本序列上实体信息的关注度,从而获取更加准确的实体特征信息,促进关系层阶段更好地分类;其次在关系层,将Bi-Tree-LSTM嵌套在序列层之上,并将序列层的隐状态与实体特征信息传入关系层,利用共享参数对三种不同的句法结构进行加权学习,通过端到端的模型训练并实现语义关系分类。实验结果表明,该模型在SemEval-2010 Task8语料库上的marco-◢F◣▼1▽值达到了85.9%,并进一步地提升了模型的鲁棒性。     

基于卷积神经网络和代价敏感的不平衡图像分类方法

针对不平衡图像分类中少数类查全率低、分类结果总代价高,以及人工提取特征主观性强而且费时费力的问题,提出了一种基于Triplet-sampling的卷积神经网络（Triplet-sampling CNN）和代价敏感支持向量机（CSSVM）的不平衡图像分类方法——Triplet-CSSVM。该方法将分类过程分为特征学习和代价敏感分类两部分。首先,利用误差公式为三元损失函数的卷积神经网络端对端地学习将图像映射到欧几里得空间的编码方法;然后,结合采样方法重构数据集,使其分布平衡化;最后,使用CSSVM分类算法给不同类别赋以不同的代价因子,获得最佳代价最小的分类结果。在深度学习框架Caffe上使用人像数据集FaceScrub进行实验。实验结果表明,所提方法在1∶3的不平衡率下,与VGGNet-SVM方法相比,少数类的精确率提高了31个百分点,召回率提高了71个百分点。     

卷积神经网络在图像分类和目标检测应用综述

卷积神经网络具有强大的特征学习能力,随着大数据时代的到来和计算机能力的提升,近年来卷积神经网络在图像识别、目标检测等领域取得了突破性进展,掀起了新的研究热潮。综述卷积神经网络的基本原理,以及其在图像分类、目标检测上的研究进展和典型模型,最后分析了卷积神经网络目前的问题,并展望了未来的发展方向。     

Remote sensing image classification based on neural network ensemble algorithm

The amounts and types of remote sensing data have increased rapidly, and the classification of these datasets has become more and more overwhelming for a single classifier in practical applications. In this paper, an ensemble algorithm based on Diversity Ensemble Creation by Oppositional Relabeling of Artificial Training Examples (DECORATEs) and Rotation Forest is proposed to solve the classification problem of remote sensing image. In this ensemble algorithm, the RBF neural networks are employed as base classifiers. Furthermore, interpolation technology for identical distribution is used to remold the input datasets. These remolded datasets will construct new classifiers besides the initial classifiers constructed by the Rotation Forest algorithm. The change of classification error is used to decide whether to add another new classifier. Therefore, the diversity among these classifiers will be enhanced and the accuracy of classification will be improved. Adaptability of the proposed algorithm is verified in experiments implemented on standard datasets and actual remote sensing dataset.     

基于卷积神经网络的图像分类算法综述

卷积神经网络（CNN）是目前基于深度学习的计算机视觉领域中重要的研究方向之一。它在图像分类和分割、目标检测等的应用中表现出色,其强大的特征学习与特征表达能力越来越受到研究者的推崇。然而,CNN仍存在特征提取不完整、样本训练过拟合等问题。针对这些问题,介绍了CNN的发展、CNN经典的网络模型及其组件,并提供了解决上述问题的方法。通过对CNN模型在图像分类中研究现状的综述,为CNN的进一步发展及研究方向提供了建议。