Secure Content Based Image Retrieval Scheme Based on Deep Hashing and Searchable Encryption

To solve the problem that the existing ciphertext domain image retrieval system is challenging to balance security,retrieval efficiency,and retrieval accuracy.This research suggests a searchable encryption and deep hashing-based secure image retrieval technique that extracts more expressive image features and constructs a secure,searchable encryption scheme.First,a deep learning framework based on residual network and transfer learn-ing model is designed to extract more representative image deep features.Secondly,the central similarity is used to quantify and construct the deep hash sequence of features.The Paillier homomorphic encryption encrypts the deep hash sequence to build a high-security and low-complexity searchable index.Finally,according to the additive homomorphic property of Paillier homomorphic encryption,a similarity measurement method suitable for com-puting in the retrieval system’s security is ensured by the encrypted domain.The experimental results,which were obtained on Web Image Database from the National University of Singapore(NUS-WIDE),Microsoft Common Objects in Context(MS COCO),and ImageNet data sets,demonstrate the system’s robust security and precise retrieval,the proposed scheme can achieve efficient image retrieval without revealing user privacy.The retrieval accuracy is improved by at least 37%compared to traditional hashing schemes.At the same time,the retrieval time is saved by at least 9.7%compared to the latest deep hashing schemes.

Hierarchical deep hashing for image retrieval

We present a new method to generate efficient multi-level hashing codes for image retrieval based on the deep siamese conv01utional neural network （DSCNN）. Con- ventional deep hashing methods trade off the capability of capturing highly complex and nonlinear semantic informa- tion of images against very compact hash codes, usually lead- ing to high retrieval efficiency but with deteriorated accuracy. We alleviate the restrictive compactness requirement of hash codes by extending them to a two-level hierarchical coding scheme, in which the first level aims to capture the high-level semantic information extracted by the deep network using a rich encoding strategy, while the subsequent level squeezes them to more global and compact codes. At running time, we adopt an attention-based mechanism to select some of its most essential bits specific to each query image for retrieval instead of using the full hash codes of the first level. The attention-based mechanism is based on the guides of hash codes generated by the second level, taking advantage of both local and global properties of deep features. Experimental re- suits on various popular datasets demonstrate the advantages of the proposed method compared to several state-of-the-art methods.

Asymmetric Deep Hashing for Person Re-Identifications

The person re-identification(re-ID)community has witnessed an explosion in the scale of data that it has to handle.On one hand,it is important for large-scale re-ID to provide constant or sublinear search time and dramatically reduce the storage cost for data points from the viewpoint of efficiency.On the other hand,the semantic affinity existing in the original space should be preserved because it greatly boosts the accuracy of re-ID.To this end,we use the deep hashing method,which utilizes the pairwise similarity and classification label to learn deep hash mapping functions,in order to provide discriminative representations.More importantly,considering the great advantage of asymmetric hashing over the existing symmetric one,we finally propose an asymmetric deep hashing(ADH)method for large-scale re-ID.Specifically,a two-stream asymmetric convolutional neural network is constructed to learn the similarity between image pairs.Another asymmetric pairwise loss is formulated to capture the similarity between the binary hashing codes and real-value representations derived from the deep hash mapping functions,so as to constrain the binary hash codes in the Hamming space to preserve the semantic structure existing in the original space.Then,the image labels are further explored to have a direct impact on the hash function learning through a classification loss.Furthermore,an efficient alternating algorithm is elaborately designed to jointly optimize the asymmetric deep hash functions and high-quality binary codes,by optimizing one parameter with the other parameters fixed.Experiments on the four benchmarks,i.e.,DukeMTMC-reID,Market-1501,Market-1501+500 k,and CUHK03 substantiate the competitive accuracy and superior efficiency of the proposed ADH over the compared state-of-the-art methods for large-scale re-ID.

Enhanced Disease Identification Model for Tea Plant Using Deep Learning

Tea plant cultivation plays a significant role in the Indian economy.The Tea board of India supports tea farmers to increase tea production by preventing various diseases in Tea Plant.Various climatic factors and other parameters cause these diseases.In this paper,the image retrieval model is developed to identify whether the given input tea leaf image has a disease or is healthy.Automation in image retrieval is a hot topic in the industry as it doesn’t require any form of metadata related to the images for storing or retrieval.Deep Hashing with Integrated Autoencoders is our proposed method for image retrieval in Tea Leaf images.It is an efficient andflexible way of retrieving Tea Leaf images.It has an integrated autoencoder which makes it better than the state-of-the-art methods giving better results for the MAP(mean average precision)scores,which is used as a parameter to judge the efficiency of the model.The autoencoders used with skip connections increase the weightage of the prominent features present in the previous tensor.This constitutes a hybrid model for hashing and retrieving images from a tea leaf data set.The proposed model will examine the input tea leaf image and identify the type of tea leaf disease.The relevant image will be retrieved based on the resulting type of disease.This model is only trained on scarce data as a real-life scenario,making it practical for many applications.

An Efficient Encrypted Speech Retrieval Based on Unsupervised Hashing and B+ Tree Dynamic Index

Existing speech retrieval systems are frequently confronted with expanding volumes of speech data.The dynamic updating strategy applied to construct the index can timely process to add or remove unnecessary speech data to meet users’real-time retrieval requirements.This study proposes an efficient method for retrieving encryption speech,using unsupervised deep hashing and B+ tree dynamic index,which avoid privacy leak-age of speech data and enhance the accuracy and efficiency of retrieval.The cloud’s encryption speech library is constructed by using the multi-threaded Dijk-Gentry-Halevi-Vaikuntanathan(DGHV)Fully Homomorphic Encryption(FHE)technique,which encrypts the original speech.In addition,this research employs Residual Neural Network18-Gated Recurrent Unit(ResNet18-GRU),which is used to learn the compact binary hash codes,store binary hash codes in the designed B+tree index table,and create a mapping relation of one to one between the binary hash codes and the corresponding encrypted speech.External B+tree index technology is applied to achieve dynamic index updating of the B+tree index table,thereby satisfying users’needs for real-time retrieval.The experimental results on THCHS-30 and TIMIT showed that the retrieval accuracy of the proposed method is more than 95.84%compared to the existing unsupervised hashing methods.The retrieval efficiency is greatly improved.Compared to the method of using hash index tables,and the speech data’s security is effectively guaranteed.

基于Vision Transformer Hashing的民族布艺图案哈希检索算法研究

针对民族布艺图案复杂多样、语义提取、图像识别与检索困难等问题,以蜡染图案和织锦图案为例,提出一种图像检索算法,以提高匹配和检索民族布艺图案的准确度。结合民族布艺图案领域知识将民族布艺图案图像进行预处理,使用VIT为主干网络在哈希检索算法框架下进行图像检索。该方法优化了深度哈希检索算法,通过自身的自注意力机制提升了提取图案深层语义特征的能力,提高了深度哈希算法检索民族布艺图案的速度和精度。实验结果表明:提出的方法最佳检索精度可以达到95.32%。

Cross-Modal Hashing Retrieval Based on Deep Residual Network

In the era of big data rich inWe Media,the single mode retrieval system has been unable to meet people’s demand for information retrieval.This paper proposes a new solution to the problem of feature extraction and unified mapping of different modes:A Cross-Modal Hashing retrieval algorithm based on Deep Residual Network(CMHR-DRN).The model construction is divided into two stages:The first stage is the feature extraction of different modal data,including the use of Deep Residual Network(DRN)to extract the image features,using the method of combining TF-IDF with the full connection network to extract the text features,and the obtained image and text features used as the input of the second stage.In the second stage,the image and text features are mapped into Hash functions by supervised learning,and the image and text features are mapped to the common binary Hamming space.In the process of mapping,the distance measurement of the original distance measurement and the common feature space are kept unchanged as far as possible to improve the accuracy of Cross-Modal Retrieval.In training the model,adaptive moment estimation(Adam)is used to calculate the adaptive learning rate of each parameter,and the stochastic gradient descent(SGD)is calculated to obtain the minimum loss function.The whole training process is completed on Caffe deep learning framework.Experiments show that the proposed algorithm CMHR-DRN based on Deep Residual Network has better retrieval performance and stronger advantages than other Cross-Modal algorithms CMFH,CMDN and CMSSH.

散列记忆网络增强的自编码器异常检测方法

深度自编码器是异常检测的重要工具,通过异常样本由于分布的差异,无法在编码器中进行重构这一假设实现对异常的检测.而实际应用中,由于深度自编码器的泛化性较强,异常输入后也能实现较好重构,导致漏检情况发生.本文在改进注意力机制基础上,构建了一个散列记忆网络增强的自编码器异常检测方法,较好解决了这一问题.首先,模型将输入编码为编码信息,根据编码信息获取子查询向量,然后通过子查询向量获取子注意力权重及对应子索引,再将子权重交叉求和获得散列权重及索引并从记忆网络单元检索出解码信息,最后利用解码信息进行重构输出.重构的输出总是与正常数据相似,使得异常输入与重构输出之间的重构误差将被放大,从而让异常更容易被识别.仿真实验表明,本文提出方法在图像、视频监控、通用异常检测任务中,均取得了较好的检测效果.

基于增强视觉Transformer的哈希食品图像检索

作为食品计算的一个主要任务,食品图像检索近年来受到了广泛的关注。然而,食品图像检索面临着两个主要的挑战。首先,食品图像具有细粒度的特点,这意味着不同食品类别之间的视觉差异可能很小,这些差异只能在图像的局部区域中观察到。其次,食品图像包含丰富的语义信息,如食材、烹饪方式等,这些信息的提取和利用对于提高检索性能至关重要。为解决这些问题,本实验基于预训练的视觉Transformer(Vision Transformer,ViT)模型提出了一种增强ViT的哈希网络(enhanced ViT hash network,EVHNet)。针对食品图像的细粒度特点,EVHNet中设计了一个基于卷积结构的局部特征增强模块,使网络能够学习到更具有代表性的特征。为更好地利用食品图像的语义信息,EVHNet中还设计了一个聚合语义特征模块,根据类令牌特征来聚合食品图像中的语义信息。本实验提出的EVHNet模型在贪婪哈希、中心相似量化和深度极化网络3种流行的哈希图像检索框架下进行评估,并与AlexNet,ResNet50、ViT-B_32和ViT-B_164种主流网络模型进行比较,在Food-101、Vireo Food-172、UEC Food-2563个食品数据集上的实验结果表明,EVHNet模型在检索精度上的综合性能优于其他模型。

基于word-hashing的DGA僵尸网络深度检测模型

针对使用域名生成算法(DGA)僵尸网络隐蔽性强,传统检测算法特征提取复杂的问题,提出一种无需提取具体特征的深度学习模型DGA域名检测方法.首先基于word-hashing将所有域名转用二元语法字符串表示,利用词袋模型把域名映射到高维向量空间.然后利用5层深度神经网络对转换为高维向量的域名进行训练分类检测.通过深度模型,能够从训练数据中发现不同层次抽象的隐藏模式和特征,而这些模式和特征使用传统的统计方法大多是无法发现的.实验中使用了10万条DGA域名和10万条合法域名作为样本,与基于自然语言特征分类算法进行对比实验.实验结果表明该深度模型对DGA域名检测准确率达到97.23%,比基于自然语言特征分类算法得到的检测准确率高3.7%.

基于图卷积的云制造服务编码算法

随着云制造模式及相关技术的发展,越来越多的服务提供者在云平台上发布并提供云服务业务。客户如何在大量功能相似、服务质量相近的云制造服务中检索并选择合适的云服务,已成为云平台运行过程中的难题。将服务关系与服务特征相结合,将制造过程中的协作关系引入服务哈希编码,对制造服务生成二进制编码,提出一种基于图卷积的云制造服务编码检索算法,通过采用汉明距离等方法度量服务间相似性,筛选服务候选集,提高算法效率。实验结果表明:该算法能够准确、有效地为服务平台上的客户提供良好的制造服务候选集。

基于深度哈希与注意力机制的花卉图像检索

针对当前的花卉识别方法在真实场景下容易受背景、光照等因素干扰导致识别准确率低、识别速度慢的问题,提出一种基于深度哈希与注意力机制相结合的图像检索方法用于花卉识别。上述方法在神经网络中融合了注意力机制用于降低背景干扰提升特征质量,并增加一个哈希层降低特征维度以提升检索效率,在图像预处理阶段采用自适应直方图均衡化降低光照干扰影响。实验结果表明,在更接近真实场景的自制花卉数据集True Flowers上,所提方法与传统神经网络方法相比平均检索精度提升了1.3%,检索速度提升了156倍,在公共数据集Oxford 17 Flowers上新方法的准确率要高于其它文献方法,由此证明了新方法的有效性和先进性。

基于深度哈希算法的学生画像个性化推荐系统的设计与实现

为了提升学生画像个性化推荐的效果,研究设计了一种基于深度哈希算法的学生画像个性化推荐系统。通过使用深度哈希算法结合经过处理的学生信息,进行了学生信息特征标签的提取,并构建了学生画像标签维度模型,从而提升了学生画像的生动性。根据学生画像标注的学生特征,在学校课程资源特征数据集中进行搜索匹配,并根据排序后的检索结果生成推荐结果。实验结果表明,该系统能够有效地采集和预处理学生信息,并成功构建学生画像,完成学生画像的个性化推荐。

多模态检索研究综述

多模态数据的日益增长使得多模态检索技术也相继受到了不少关注。随着汽车、医学等行业引入计算机与大数据技术,大量的行业数据其本身都是以多模态形式呈现出来的,行业的快速发展使人们对信息的需求不断增加,单一模态数据检索已经无法满足人们对信息的需求。为了解决这些问题,满足一种模态的数据检索其他模态数据的需求,通过文献的查阅对多模态检索的方法进行研究,分析了公共子空间、深度学习、多模态哈希算法等不同的研究方法,梳理了近年来提出的解决这些问题的多模态检索技术。最后,对近几年来提出的多模态检索方法根据检索的准确性、检索的效率以及特点等多方面进行评价对比;对多模态检索所遇到的挑战进行分析,并展望多模态检索未来的应用前景。

基于层次聚类的图文检索模型研究

图文检索在工业中的用途和作用是多方面的,可以帮助提高研发和生产效率,促进科技创新,提高产品的质量和竞争力;目前,图文检索模型的重点是提高检索的精度;随着技术和数据的快速发展,深度学习和大模型技术的不断应用,图文检索的速度问题逐渐凸显,为解决当前图文检索速度受限、计算量大的问题,提出了一种基于层次聚类的图文检索模型;该方法选择了检索效果明显的跨模态哈希方法,并运用深度聚类算法对待检索的数据进行分类,从而缩小检索范围,提高了检索速度;实验结果表明,基于层次聚类的图文检索模型在保持检索精度的同时,显著提高了检索速度,使得工程人员能够更快地获取到满意的检索结果。

一种基于Bilinear-HashNet网络的车型识别方法

车型识别对于智能交通系统具有重要的意义.目前基于深度学习的车型识别技术通常采用卷积神经网络来进行图像分类,这一类方法对于已训练的车型类别具有较好的识别效果,但是对于未训练数据类型就无能为力了.针对这一缺点,本文设计了Bilinear-HashNet网络,该网络以Hash Net为基础,使用双线性模块替换Hash Net中的AlexNet部分,使网络具有提取精细粒度特征的能力;并根据提取到的特征生成哈希码,再通过哈希码的匹配实现车型识别.实验证明,基于Bilinear-HashNet的车型识别方法对已训练和未训练的车辆类型都能取得较好的效果.

基于CLIP与注意力机制的跨模态哈希检索算法

针对传统无监督跨模态检索算法提取样本内部与样本之间的关联语义不充分,导致检索准确率低的问题,提出一种基于CLIP与注意力融合机制的无监督跨模态哈希检索算法CAFM_Net。将多模态预训练模型CLIP运用到样本特征提取阶段,从不同维度挖掘数据的相似信息;使用注意力融合机制对提取的特征进行处理,加强显著区域的权重;引入对抗学习的思想设计模态分类器,生成更趋于语义一致性的跨模态数据哈希编码。与现有的代表性哈希方法相比,CAFM_Net在多模态检索任务上准确率提升至少11%与9%。

基于类相似特征扩充与中心三元组损失的哈希图像检索

现有的深度哈希图像检索方法主要采用卷积神经网络,提取的深度特征的相似性表征能力不足.此外,三元组深度哈希主要从小批量数据中构建局部三元组样本,样本数量较少,数据分布缺失全局性,使网络训练不够充分且收敛困难.针对上述问题,文中提出基于类相似特征扩充与中心三元组损失的哈希图像检索模型(Hash Image Retrieval Based on Category Similarity Feature Expansion and Center Triplet Loss,HRFT-Net).设计基于Vision Transformer的哈希特征提取模块(Hash Feature Extraction Module Based on Vision Transformer,HViT),利用Vision Transformer提取表征能力更强的全局特征信息.为了扩充小批量训练样本的数据量,提出基于类约束的相似特征扩充模块(Similar Feature Expansion Based on Category Constraint,SFEC),利用同类样本间的相似性生成新特征,丰富三元组训练样本.为了增强三元组损失的全局性,提出基于Hadamard的中心三元组损失函数(Central Triplet Loss Function Based on Hadamard,CTLH),利用Hadamard为每个类建立全局哈希中心约束,通过增添局部约束与全局中心约束的中心三元组加速网络的学习和收敛,提高图像检索的精度.在CIFAR10、NUS-WIDE数据集上的实验表明,HRFT-Net在不同长度比特位哈希码检索上的平均精度均值较优,由此验证HRFT-Net的有效性.

基于图卷积网络的无监督跨模态哈希检索算法

针对无监督跨模态检索任务中不能充分利用单个模态内的语义关联信息的问题,提出了一种基于图卷积网络的无监督跨模态哈希检索方法。通过图像和文本编码器分别获得两个模态的特征,输入到图卷积网络中挖掘单个模态的内部语义信息,将结果通过哈希编码层进行二值化操作后,与模态间的深度语义关联相似度矩阵进行对比计算损失,不断重构优化生成的二进制编码,直到生成样本对应的健壮哈希表达。实验结果表明,与经典的浅层方法和深度学习方法对比,该方法在多个数据集上的跨模态检索准确率均有明显提升。证明通过图卷积网络能够进一步挖掘模态内的语义信息,所提模型具有更高的准确性和鲁棒性。

注意力增强的视觉Transformer图像检索算法

基于深度哈希的图像检索方法往往利用卷积和池化技术去提取图像局部信息,并且需要不断加深网络层次来获得全局长依赖关系,这些方法一般具有较高的复杂度和计算量。本文提出了一种注意力增强的视觉Transformer图像检索算法,算法使用预训练的视觉Transformer作为基准模型,提升模型收敛速度,通过对骨干网络的改进和哈希函数的设计,实现了高效的图像检索。一方面,本文设计了一个注意力增强模块,来捕获输入特征图的局部显著信息和视觉细节,学习相应的权重以突出重要特征,并增强输入到Transformer编码器的图像特征的表征力。另一方面,为了提高图像检索的效率,设计了一种对比哈希损失函数,生成具有判别力的二进制哈希码,从而降低了内存需求与计算复杂度。在CIFAR-10和NUS-WIDE数据集上的实验结果表明,本文提出的方法,在两个不同数据集上使用不同哈希码长度的平均精度均值达到了96.8%和86.8%,性能超过多种经典的深度哈希算法和其他两种基于Transformer架构的图像检索算法。