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 ha...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.展开更多
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 capabilit...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.展开更多
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 dra...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.展开更多
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 othe...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.展开更多
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 dat...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.展开更多
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 un...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.展开更多
Recently,deep hashing methods play a pivotal role in image retrieval tasks by combining advanced convolutional neural networks(CNNs)with efficient hashing.Meanwhile,second-order representations of deep convolutional a...Recently,deep hashing methods play a pivotal role in image retrieval tasks by combining advanced convolutional neural networks(CNNs)with efficient hashing.Meanwhile,second-order representations of deep convolutional activations have been established to effectively improve network performance in various computer vision applications.In this work,to obtain more compact hash codes,we propose a supervised deep second-order covariance hashing(SDSoCH)method by combining deep hashing with second-order statistic model.SDSoCH utilizes a powerful covariance pooling to model the second-order statistics of convolutional features,which is naturally integrated into the existing point-wise hashing network in an end-to-end manner.The embedded covariance pooling operation well captures the interaction of convolutional features and produces global feature representations with more discriminant capability,leading to the more informative hash codes.Extensive experiments conducted on two benchmarks demonstrate that the proposed SDSoCH outperforms its first-order counterparts and achieves superior retrieval performance.展开更多
基金supported by the National Natural Science Foundation of China(No.61862041).
文摘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.
基金This work was partially supported by the National Natural Science Foundation of China (Grant Nos, 61373060 and 61672280) and Qing Lan Project.
文摘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.
基金supported by the National Natural Science Foundation of China(Nos.61701277 and 61771288)the State Key Development Program in the 13th Five-Year Plan(No.2017YFC0821601)Open Project Fund of the National Engineering Laboratory for Intelligent Video Analysis and Application。
文摘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.
文摘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.
基金supported by the NationalNatural Science Foundation of China(No.61862041).
文摘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.
文摘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.
基金the National Key R&D Program of China(2018YFC0910506)the National Natural Science Foundation of China(61972062)+2 种基金the Natural Science Foundation of Liaoning Province(2019-MS-011)the Key R&D Program of Liaoning Province(2019 JH2/10100030)the Liaoning BaiQianWan Talents Program.
文摘Recently,deep hashing methods play a pivotal role in image retrieval tasks by combining advanced convolutional neural networks(CNNs)with efficient hashing.Meanwhile,second-order representations of deep convolutional activations have been established to effectively improve network performance in various computer vision applications.In this work,to obtain more compact hash codes,we propose a supervised deep second-order covariance hashing(SDSoCH)method by combining deep hashing with second-order statistic model.SDSoCH utilizes a powerful covariance pooling to model the second-order statistics of convolutional features,which is naturally integrated into the existing point-wise hashing network in an end-to-end manner.The embedded covariance pooling operation well captures the interaction of convolutional features and produces global feature representations with more discriminant capability,leading to the more informative hash codes.Extensive experiments conducted on two benchmarks demonstrate that the proposed SDSoCH outperforms its first-order counterparts and achieves superior retrieval performance.