Lung Nodule Image Retrieval Based on Convolutional Neural Networks and Hashing

Lung medical image retrieval based on content similarity plays an important role in computer-aided diagnosis of lung cancer.In recent years,binary hashing has become a hot topic in this field due to its compressed storage and fast query speed.Traditional hashing methods often rely on highdimensional features based hand-crafted methods,which might not be optimally compatible with lung nodule images.Also,different hashing bits contribute to the image retrieval differently,and therefore treating the hashing bits equally affects the retrieval accuracy.Hence,an image retrieval method of lung nodule images is proposed with the basis on convolutional neural networks and hashing.First,apre-trained and fine-tuned convolutional neural network is employed to learn multilevel semantic features of the lung nodules.Principal components analysis is utilized to remove redundant information and preserve informative semantic features of the lung nodules.Second,the proposed method relies on nine sign labels of lung nodules for the training set,and the semantic feature is combined to construct hashing functions.Finally,returned lung nodule images can be easily ranked with the query-adaptive search method based on weighted Hamming distance.Extensive experiments and evaluations on the dataset demonstrate that the proposed method can significantly improve the expression ability of lung nodule images,which further validates the effectiveness of the proposed method.

Image Retrieval Based on Deep Feature Extraction and Reduction with Improved CNN and PCA

With the rapid development of information technology,the speed and efficiency of image retrieval are increasingly required in many fields,and a compelling image retrieval method is critical for the development of information.Feature extraction based on deep learning has become dominant in image retrieval due to their discrimination more complete,information more complementary and higher precision.However,the high-dimension deep features extracted by CNNs(convolutional neural networks)limits the retrieval efficiency and makes it difficult to satisfy the requirements of existing image retrieval.To solving this problem,the high-dimension feature reduction technology is proposed with improved CNN and PCA quadratic dimensionality reduction.Firstly,in the last layer of the classical networks,this study makes a well-designed DR-Module(dimensionality reduction module)to compress the number of channels of the feature map as much as possible,and ensures the amount of information.Secondly,the deep features are compressed again with PCA(Principal Components Analysis),and the compression ratios of the two dimensionality reductions are reduced,respectively.Therefore,the retrieval efficiency is dramatically improved.Finally,it is proved on the Cifar100 and Caltech101 datasets that the novel method not only improves the retrieval accuracy but also enhances the retrieval efficiency.Experimental results strongly demonstrate that the proposed method performs well in small and medium-sized datasets.

An Efficient Deep Learning-based Content-based Image Retrieval Framework

The use of massive image databases has increased drastically over the few years due to evolution of multimedia technology.Image retrieval has become one of the vital tools in image processing applications.Content-Based Image Retrieval(CBIR)has been widely used in varied applications.But,the results produced by the usage of a single image feature are not satisfactory.So,multiple image features are used very often for attaining better results.But,fast and effective searching for relevant images from a database becomes a challenging task.In the previous existing system,the CBIR has used the combined feature extraction technique using color auto-correlogram,Rotation-Invariant Uniform Local Binary Patterns(RULBP)and local energy.However,the existing system does not provide significant results in terms of recall and precision.Also,the computational complexity is higher for the existing CBIR systems.In order to handle the above mentioned issues,the Gray Level Co-occurrence Matrix(GLCM)with Deep Learning based Enhanced Convolution Neural Network(DLECNN)is proposed in this work.The proposed system framework includes noise reduction using histogram equalization,feature extraction using GLCM,similarity matching computation using Hierarchal and Fuzzy c-Means(HFCM)algorithm and the image retrieval using DLECNN algorithm.The histogram equalization has been used for computing the image enhancement.This enhanced image has a uniform histogram.Then,the GLCM method has been used to extract the features such as shape,texture,colour,annotations and keywords.The HFCM similarity measure is used for computing the query image vector's similarity index with every database images.For enhancing the performance of this image retrieval approach,the DLECNN algorithm is proposed to retrieve more accurate features of the image.The proposed GLCM+DLECNN algorithm provides better results associated with high accuracy,precision,recall,f-measure and lesser complexity.From the experimental results,it is clearly observed that the proposed system provides efficient image retrieval for the given query image.

IDSH: An Improved Deep Supervised Hashing Method for Image Retrieval

Image retrieval has become more and more important because of the explosive growth of images on the Internet.Traditional image retrieval methods have limited image retrieval performance due to the poor image expression abhility of visual feature and high dimension of feature.Hashing is a widely-used method for Approximate Nearest Neighbor(ANN)search due to its rapidity and timeliness.Meanwhile,Convolutional Neural Networks(CNNs)have strong discriminative characteristics which are used for image classification.In this paper,we propose a CNN architecture based on improved deep supervised hashing(IDSH)method,by which the binary compact codes can be generated directly.The main contributions of this paper are as follows:first,we add a Batch Normalization(BN)layer before each activation layer to prevent the gradient from vanishing and improve the training speed;secondly,we use Divide-and-Encode Module to map image features to approximate hash codes;finally,we adopt center loss to optimize training.Extensive experimental results on four large-scale datasets:MNIST,CIFAR-10,NUS-WIDE and SVHN demonstrate the effectiveness of the proposed method compared with other state-of-the-art hashing methods.

A Novel Feature Aggregation Approach for Image Retrieval Using Local and Global Features

The current deep convolution features based on retrievalmethods cannot fully use the characteristics of the salient image regions.Also,they cannot effectively suppress the background noises,so it is a challenging task to retrieve objects in cluttered scenarios.To solve the problem,we propose a new image retrieval method that employs a novel feature aggregation approach with an attention mechanism and utilizes a combination of local and global features.The method first extracts global and local features of the input image and then selects keypoints from local features by using the attention mechanism.After that,the feature aggregation mechanism aggregates the keypoints to a compact vector representation according to the scores evaluated by the attention mechanism.The core of the aggregation mechanism is to allow features with high scores to participate in residual operations of all cluster centers.Finally,we get the improved image representation by fusing aggregated feature descriptor and global feature of the input image.To effectively evaluate the proposedmethod,we have carried out a series of experiments on large-scale image datasets and compared them with other state-of-the-art methods.Experiments show that this method greatly improves the precision of image retrieval and computational efficiency.

Content-Based Image Retrieval with Feature Extraction and Rotation Invariance

Over recent years, Convolutional Neural Networks (CNN) has improved performance on practically every image-based task, including Content-Based Image Retrieval (CBIR). Nevertheless, since features of CNN have altered orientation, training a CBIR system to detect and correct the angle is complex. While it is possible to construct rotation-invariant features by hand, retrieval accuracy will be low because hand engineering only creates low-level features, while deep learning methods build high-level and low-level features simultaneously. This paper presents a novel approach that combines a deep learning orientation angle detection model with the CBIR feature extraction model to correct the rotation angle of any image. This offers a unique construction of a rotation-invariant CBIR system that handles the CNN features that are not rotation invariant. This research also proposes a further study on how a rotation-invariant deep CBIR can recover images from the dataset in real-time. The final results of this system show significant improvement as compared to a default CNN feature extraction model without the OAD.

基于CNN-CBIR的遥感图像分类检索方法

遥感图像海量性、复杂性与多样性特征导致现有方法出现查全率、查准率低的问题,无法满足现今遥感图像应用的需求,故提出基于卷积神经网络-图像检索(Convolutional Neural Networks-ContentBased Image Retrieval,CNN-CBIR)的遥感图像分类检索方法研究。为了精确分类遥感图像,基于卷积神经网络-深度卷积神经网络-16 (Convolutional Neural Networks-Visual Geometry Group Net-16,CNN-VGGNet-16)模型提取遥感图像卷积特征与池化特征,通过有效融合得到遥感图像高层聚合特征,以此为基础,采用模糊分类算法分类处理遥感图像,依据遥感图像分类结果,利用基于内容的图像检索(Content-Based Image Retrieval,CBIR)技术制定遥感图像分类检索程序,实现了遥感图像的分类检索。选取数据集图像遥感数据集(UC-Merced)与武大遥感数据集(WHU-RS)作为实验数据集,确定最佳池化区域尺寸与最佳输入尺寸,采用MATLAB软件进行仿真实验。仿真实验数据显示:与标准数值相比较,提出方法的查全率与查准率较高,充分说明提出方法具备更好的检索性能。

基于注意力机制和软匹配的多标签遥感图像检索方法

针对卷积神经网络对于多标签遥感图像特征提取能力弱、不能准确反映遥感图像多标签复杂性的问题,提出基于注意力机制和软匹配的多标签遥感图像检索方法。在特征提取阶段,以密集卷积神经网络模型为基础,在每个密集块(Dense Block)后添加CBAM(Convolutional Block Attention Module)层,实现对多标签图像区域特征提取。在模型训练时,利用区分硬匹配与软匹配的联合损失函数,学习图像的哈希编码表示。通过评估遥感图像哈希编码间的汉明距离,实现相似图像的检索。实验结果表明,所提方法在数据集NUS-WIDE和多标签遥感图像数据集DLRSD上与其他基于全局特征的深度哈希方法相比,明显提升了检索准确率。

基于深度哈希与VP-Tree的快速图像检索方法

针对高维特征图像检索中的精度和速度挑战,提出了一种结合深度哈希技术和VP-Tree索引的快速图像检索方法.该方法首先设计了一个轻量级的深度卷积编码网络,并在网络中引入了卷积块注意力模块和空间金字塔池化技术,以增强特征提取能力;然后通过该网络模型将图像数据集中每幅图像的高维特征转化为二进制哈希编码,并与其对应的图像编号组成一个哈希表;接着使用所有图像的哈希编码来构建一个VP-Tree,在执行图像检索时将使用待查询图像的哈希编码从VP-Tree中快速找到与其距离最近的节点;最后根据这些节点的哈希值从哈希表中取出对应的结果图像.实验结果表明,所提方法在保持高检索精度的同时显著提升了检索速度(在MNIST、FASHION-MNIST和CIFAR-10上的检索速度分别提高了24.17、8.61和4.01倍).

基于印刷体监督的手写维文识别方法

手写维吾尔文字图像数据集匮乏及手写文本难于分割识别问题,提出了一种基于印刷体监督的手写维文识别模型模型将文字和印刷体文字图片同时作为标签,在训练时将两种文字图像并行输入到CNN中提取特征,而后将特征分别输入至识别分支进行识别任务、输入至匹配分支进行图片匹配任务,预测时将特征输入到BiLSTM编码器中得到序列特征,最后通过CTC得到识别结果。所提方法可生成充裕有效的手写文字图像,且在真实手写维文测试集上相较于基准模型CER降低5.03%,在IAM上也证明了模型迁移性。实验结果表明,提出的方法能够有效缓解手写维文文字图像数据集匮乏问题,模型能充分挖掘印刷体文字图像的特征作为手写体文字识别的监督信息来提高识别效果。

融合注意力机制的深度哈希图像检索方法

传统的基于深度哈希图像检索方法在获取图像的特征信息时,会关注到部分冗余信息,影响最终的图像检索精度。针对上述问题,提出一种应用于卷积神经网络中的融合跨维度交互注意力机制模块,该模块可以提高网络的性能,学习到更多有利于图像检索的特征信息。在深度哈希图像检索任务中,选用VGG16与ResNet18两种经典模型作为图像检索的基础模型,加入注意力模块并且重新设计哈希码目标损失函数后,在CIFAR-10和NUS-WIDE数据集上进行了对比实验,实验结果表明添加了注意力机制后的图像检索精度有较大提高,验证了所提出方法的有效性。

Construction of apricot variety search engine based on deep learning

Apricot has a long history of cultivation and has many varieties and types. The traditional variety identification methods are timeconsuming and labor-consuming, posing grand challenges to apricot resource management. Tool development in this regard will help researchers quickly identify variety information. This study photographed apricot fruits outdoors and indoors and constructed a dataset that can precisely classify the fruits using a U-net model (F-score:99%), which helps to obtain the fruit's size, shape, and color features. Meanwhile, a variety search engine was constructed, which can search and identify variety from the database according to the above features. Besides, a mobile and web application (ApricotView) was developed, and the construction mode can be also applied to other varieties of fruit trees.Additionally, we have collected four difficult-to-identify seed datasets and used the VGG16 model for training, with an accuracy of 97%, which provided an important basis for ApricotView. To address the difficulties in data collection bottlenecking apricot phenomics research, we developed the first apricot database platform of its kind (ApricotDIAP, http://apricotdiap.com/) to accumulate, manage, and publicize scientific data of apricot.

基于卷积神经网络的高相似度图像识别方法

考虑到部分图像中的相似度较高,会造成错误的图像分类或图像混淆。为了满足对高相似度图像的识别需求,提出一种基于卷积神经网络的高相似度图像识别方法。根据高相似度图像的预处理,计算图像特征的相似度加权和,通过构建高相似度图像特征的频数直方图,检索高相似度图像特征的相似度。基于神经元中图像特征之间的灵敏度,建立误差函数,结合采样层中图像特征的灵敏度,更新卷积神经网络的权值。利用迭代分析法,确定图像的中心点,以中心点为判定条件,实现高相似度图像的识别。实验结果表明,文中方法能够识别出具有较高相似度的图像,并提高图像的识别效率。

基于ImageNet预训练卷积神经网络的遥感图像检索

高分辨率遥感图像内容复杂,细节信息丰富,传统的浅层特征在描述这类图像上存在一定难度,容易导致检索中存在较大的语义鸿沟。本文将大规模数据集ImageNet上预训练的4种不同卷积神经网络用于遥感图像检索,首先分别提取4种网络中不同层次的输出值作为高层特征,再对高层特征进行高斯归一化,然后采用欧氏距离作为相似性度量进行检索。在UC-Merced和WHU-RS数据集上的一系列实验结果表明,4种卷积神经网络的高层特征中,以CNN-M特征的检索性能最好;与视觉词袋和全局形态纹理描述子这两种浅层特征相比,高层特征的检索平均准确率提高了15.7%~25.6%,平均归一化修改检索等级减少了17%~22.1%。因此将ImageNet上预训练的卷积神经网络用于遥感图像检索是一种有效的方法。

基于卷积神经网络的织物图像特征提取与检索研究进展

为实现织物图像的快速自动识别与检索,从织物图像浅层视觉特征提取、深度语义特征学习以及检索模型构建3个方面综述了该领域的研究进展,分析了现有研究中存在的问题。发现织物图像浅层视觉特征在小样本数据集的检索中具有较好的适用性,且多特征融合应用可有效提升检索精度,但在大样本数据集及高层语义识别检索问题中的应用存在局限性,深度卷积神经网络是克服这一问题的有效途径;织物语义属性的优化设计、卷积神经网络结构优化以及距离尺度学习是目前提升深度检索模型语义识别精度的3个有效途径;认为未来织物图像识别检索精度的提升主要依赖于标准化的语义系统设计、精准的图像分割与识别技术以及多模态的信息融合检索。

基于t-SNE卷积编码的图像检索方法

为了提高基于内容图像检索系统的速度和精度,提出了一种基于t-SNE卷积编码的图像检索方法。该方法首先采用一个高精度卷积神经网络模型提取图像特征,然后通过定量分析模型不同层特征的检索性能,选择出最佳特征。其次将选择出的最佳特征使用t-SNE方法进行编码,降低特征维度的同时进一步减少图像特征中的噪声。最后,利用降维后的编码特征,实现基于内容的图像检索系统。实验结果表明:随着特征维度的降低,卷积编码方法不但不会降低检索精度,反而在某些情况下会提高检索精度。采用16维卷积编码特征,就可以超过传统方法 128维编码特征的检索精度。而一旦特征维度降低8倍,可以使得特征的存储空间缩小8倍,图像检索效率大幅提高。因此,该方法可以有效提高基于内容图像检索系统的速度和精度。

聚合CNN特征的遥感图像检索

针对高分辨率遥感图像检索中手工特征难以准确描述图像的问题,提出聚合卷积神经网络(convolutional neural network,CNN)特征的方法来改进特征表达。首先,将预训练的CNN参数迁移到遥感图像,并针对不同尺寸的输入图像,提取表达局部信息的CNN特征;然后,对该CNN特征采用池化区域尺寸不同的均值池化和视觉词袋(bag of visual words,Bo VW) 2种聚合方法,分别得到池化特征和Bo VW特征;最后,将2种聚合特征用于遥感图像检索。实验结果表明:合理的输入图像尺寸能提高聚合特征的表达能力;当池化区域为特征图的60%～80%时,绝大多数池化特征的结果优于传统均值池化方法的结果;池化特征和Bo VW特征的最优平均归一化修改检索等级值比手工特征分别降低了27. 31%和21. 51%,因此,均值池化和Bo VW方法都能有效提高遥感图像的检索性能。

基于卷积神经网络和重排序的农业遥感图像检索

卷积神经网络具有很强的分类能力,并在图像分类等应用中取得显著成效,但遥感图像检索应用中还较少利用该分类能力。为了提高农业遥感图像检索性能,该文提出一种利用卷积神经网络分类能力的遥感图像检索方法。首先利用微调的卷积神经网络模型提取查询图像的检索特征和估计查询图像的每个类别权重,然后利用根据CNN模型判断的检索图像类别和初始排序结果计算类别查准率,根据查询图像的类别权重和类别查准率计算加权类别查准率,最后根据加权类别查准率对图像类别进行排序,并根据排序结果对初始检索结果进行重排序,从而得到最终的检索结果。试验结果表明:该检索方法在PatternNet数据集中平均查准率达到97.56%,平均归一化调整后的检索秩达到0.020 1;在UCM_LandUse数据集中平均查准率达到93.67%,平均归一化调整后的检索秩达到0.049 2,较之其他遥感图像检索方法下降0.2358,降幅超过82.7%;平均每张检索图像重排序时间大约是初始排序时间的1%。该文提出的重排序方法可以得到更好的遥感图像检索结果,提高了遥感图像检索性能,将有助于农业信息领域信息化和智能化。

融合多层卷积神经网络特征的快速图像检索方法

基于卷积神经网络在图像特征表示方面的良好表现,以及深度哈希可以满足大规模图像检索对检索时间的要求,提出了一种结合卷积神经网络和深度哈希的图像检索方法.针对当前典型图像检索方法仅仅使用全连接层作为图像特征进行检索时,存在有些样本的检索准确率为零的问题,提出融合神经网络不同层的信息作为图像的特征表示;针对直接使用图像特征进行检索时响应时间过长的问题,使用深度哈希的方法将图像特征映射为二进制的哈希码,这样哈希码中既包含底层的边缘信息又包含高层的语义信息;同时,提出了一种相似性度量函数进行相似性匹配.实验结果表明,与已有的图像检索方法相比,该方法在检索准确率上有一定程度的提高.

基于条件生成对抗网络的手绘图像检索

传统的手绘图像检索方法将自然图像通过边缘检测算法转换成"类手绘图",不能很好地减小自然图像与手绘图像之间的视觉差异.针对此问题,提出一种基于条件生成对抗网络的手绘图像检索方法.首先训练条件生成对抗网络,其中生成器由边缘图至自然图像的映射网络构成;然后通过生成器将手绘图转换为自然图像,以消除二者的视觉差异;最后使用深度卷积神经网络提取深度特征进行相似度度量,达到检索的目的.在基准数据库上进行实验的结果显示,该方法的检索精度有明显提高.