Deep Hashing Based Fusing Index Method for Large-Scale Image Retrieval

Duan, Lijuan; Zhao, Chongyang; Miao, Jun; Qiao, Yuanhua; Su, Xing

doi:10.1155/2017/9635348

Cited by 3 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14], a depth residual hash (DRH) is proposed to learn two phases simultaneously and to reduce quantization errors and improve the quality of the hash coding by using hash-related loss and regularization. Recently, a new hash index method was proposed in [15], which is called deep hash fusion index (DHFI). Its purpose is to generate more compact hash codes with more a expressive ability and distinguishing ability.…”

Section: Hash Methodsmentioning

confidence: 99%

Fully Convolutional-based Dense Network for Lung Nodule Image Retrieval Algorithm

Qin¹

2019

IJPE

View full text Add to dashboard Cite

At present, there are many problems in the existing content-based medical image retrieval (CBMIR) algorithms. The most important problem is the lack of feature extraction, resulting in the imperfect expression of semantic information and the lack of data-based learning ability. Meanwhile, the characteristic dimension is high, which affects the performance of image retrieval. In order to solve these problems, this paper presents a fully convolutional dense network (FCDN) algorithm, which solves the gap between the extracted lowlevel features and high-level semantic features. In order to improve the accuracy and efficiency of retrieval, the concept of Joint distance is proposed in this paper. Since the image information of lung nodules extracted from different layers of the network is different, the minimum Joint distance is selected by comparing the minimum Hamming distances of the layers 4, 17 and 25 of the similar images retrieved. Compared with other methods, the average accuracy of the lung nodule image retrieval can reach 91.17% under the 64-bit hash code length, the average time for retrieving a lung slice is 4.8×10-5 s, The search results not only express the rich semantic features of the image, but also improve the retrieval efficiency. And the retrieval performance is better than other network structures to help doctors assist in diagnosis.

show abstract

Section: Hash Methodsmentioning

confidence: 99%

Fully Convolutional-based Dense Network for Lung Nodule Image Retrieval Algorithm

Qin¹

2019

IJPE

View full text Add to dashboard Cite

show abstract

“…Figure 3 shows an example of a CMR system, where image modality is the input and text/audio modality are the output. The training phase generates a modality-invariant common sub-space, which has an encoding form of information called binary-valued representation or actual information called real-valued representation (Cao et al, 2016;Duan et al, 2017;Wang et al, 2021). The testing phase of the CMR system uses a common sub-space for retrieval.…”

Section: Introductionmentioning

confidence: 99%

Impact of Binary-Valued Representation on the Performance of Cross-Modal Retrieval System

Bhatt

Ganatra

Bhatt

et al. 2022

Int. j. math. eng. manag. sci.

View full text Add to dashboard Cite

The tremendous proliferation of Multi-Modal data and the flexible need of users has drawn attention to the field of Cross-Modal Retrieval (CMR), which can perform image-sketch matching, text-image matching, audio-video matching and near infrared-visual image matching. Such retrieval is useful in many applications like criminal investigation, recommendation systems and person reidentification. The real challenge in CMR is to preserve semantic similarities between various modalities of data. To preserve semantic similarities, existing deep learning-based approaches use pairwise labels and generate binary-valued representation. The generated binary-valued representation provides fast retrieval with low storage requirement. However, the relative similarity between heterogeneous data is ignored. So, the objective of this work is to reduce the modality-gap by preserving relative semantic similarities among various modalities. So, a model named "Deep Cross-Modal Retrieval (DCMR)" is proposed, which takes triplet labels as the input and generates binary-valued representation. The triplet labels locate semantic similar data points nearer and dissimilar points far in the vector space. Extensive experiments are performed and the result is compared with deep learning-based approaches, which shows that the performance of DCMR increases by 2% to 3% for Image→Text retrieval and by 2% to 5% for Text→Image retrieval in mean average precision (mAP) on MSCOCO, XMedia, and NUS-WIDE datasets. So, the binary-valued representation generated from triplet labels preserve better relative semantic similarities than pairwise labels.

show abstract

RTIM Hashing: Robust and Compact Video Hashing With a Rotation- and Translation-Invariant Model

Chen

Shang

2022

The Computer Journal

View full text Add to dashboard Cite

Video hashing is a popular research topic in the fields of multimedia information and security because its fast matching and low-cost storage characteristics are widely used in many applications (video copy detection, video retrieval, video authentication, etc.). This paper describes a compact video hashing method with a rotation- and translation-invariant model (RTIM). The key contribution of this approach is that it innovatively reconstructs an input video into a 3D RTIM by combining ring partition and a pipeline histogram; this is a first in video hashing and helps make video hashes resistant to rotation and translation. Then, the proposed model is decomposed via Tucker decomposition, and the generated core tensor is used to produce a compact hash. As the core tensor is a compressed version of the original tensor, hash construction with the core tensor makes RTIM hashing compact and achieves desirable discrimination ability. Different from existing video hashing algorithms, RTIM hashing can not only resist many commonly used digital operations, especially video rotation and cyclic frame shifting, but also achieve good discrimination ability. Various experiments demonstrate the effectiveness of our algorithm. Receiver operating characteristic curve comparisons show that compared with the state-of-the-art video hashing algorithms, RTIM hashing is more robust and compact.

show abstract

Deep Hashing Based Fusing Index Method for Large-Scale Image Retrieval

Cited by 3 publications

References 27 publications

Fully Convolutional-based Dense Network for Lung Nodule Image Retrieval Algorithm

Fully Convolutional-based Dense Network for Lung Nodule Image Retrieval Algorithm

Impact of Binary-Valued Representation on the Performance of Cross-Modal Retrieval System

RTIM Hashing: Robust and Compact Video Hashing With a Rotation- and Translation-Invariant Model

Contact Info

Product

Resources

About