Privacy preserving in CBIR using color and texture features

Majhi, Mukul; Maheshkar, Sushila

doi:10.1109/pdgc.2016.7913159

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results illustrate that the method preserve private information of the content and retrieve relevant images effectively and efficiently. [14] Sawet Somnugpong (2016)et al presents about -A good content-based image retrieval must provide a robustness to the spatial changing problem of an image which causes from dissimilar acquisition, like, zooming image, similar image but dissimilar color, etc. These mentioned troubles is major cause to humiliate the retrieval presentation.…”

Section: Color Momentmentioning

confidence: 99%

Image Retrieval by using histogram equalization and DBTCF using SVZ

Godiya¹

2018

IJRASET

View full text Add to dashboard Cite

Retrieving images as of from vast quantity of database which is based on to their content are being recognized content based image retrieval. Efficiency of any CBIR system is depend on features mined to stand for an image. As a outcome feature extraction is crucial step in design and the development of some CBIR. Most normally used features to signify images are Color, texture and shape. Here the Block truncation coding feature known as (BTCF) is used so as to compress the image. Further it give thought of Support Vector Machine also known (SVM) classifier. In paper the block of data is also divided into different chunks, so that image of single instance can be stored in these chunks. So replication will be enhanced with the aid of compression techniques which is discussed in detail. Here basic CBIR system is being developed by the combine features like color correlogram , color moments and Gabor wavelet transform all along by way of histogram descriptor. Further outcome is being obtained are then compared through CBIR system is using the SVM classifier.

show abstract

Section: Color Momentmentioning

confidence: 99%

Image Retrieval by using histogram equalization and DBTCF using SVZ

Godiya¹

2018

IJRASET

View full text Add to dashboard Cite

show abstract

“…Consequently, the selection of image features greatly influences the retrieval accuracy of PPCBIR. Certain researchers employ global features (e.g., color, texture, and shape) as image features [3][4] [5]. These features possess low computational complexity but exhibit diminished accuracy when handling images with intricate backgrounds.…”

Section: Introductionmentioning

confidence: 99%

Privacy-preserving image retrieval based on additive secret sharing in cloud environment

Zhang,

Xu,

Yan

et al. 2024

Cluster Comput

View full text Add to dashboard Cite

With the growth of cloud computing, an increasing number of resourceconstrained data owners tend to store their images on the cloud, and cloud servers provide image retrieval services for users. However, this poses significant privacy leakage risks. Privacy-preserving image retrieval can prevent privacy leakage during retrieval, but existing schemes have the problem of low search accuracy. Additionally, existing solutions usually utilize a single cloud server to provide retrieval services, which suffer from problems such as a single point of failure and a greater risk of privacy leakage. This is because the cloud server is honest but curious, and it may peek at users' data out of curiosity or interest. With the proliferation of cloud service providers, image retrieval services can be supported collaboratively by multiple cloud servers. However, complex encryption techniques and frequent interactions between servers significantly degrade the performance of the overall search process. This paper proposes a lightweight three-party computation (3-PC) image retrieval strategy based on additive secret sharing in a cloud environment. Specifically, the data owner extracts the features of images using a pre-trained CNN model and constructs an index for the features using the K-means hierarchical index tree. After splitting and outsourcing the images, CNN model, and index tree to three cloud servers, the data owner remains offline. The three cloud servers process the user's query request and utilize a secure computation protocol based on secret Article Title sharing. This protocol ensures that the parameters of the neural network and the extracted query image features are hidden from the cloud servers and other attackers. Additionally, a secure feature similarity computation and distance ranking protocol is designed to avoid privacy leakage during the search process. Security analysis and experimental results demonstrate the security and retrieval performance of the scheme.

show abstract

Image Inpainting for Irregular Holes Using Extreme Learning Machine

Kanhar¹,

Chandak²

2020

Studies in Computational Intelligence

View full text Add to dashboard Cite

Privacy preserving in CBIR using color and texture features

Cited by 5 publications

References 16 publications

Image Retrieval by using histogram equalization and DBTCF using SVZ

Image Retrieval by using histogram equalization and DBTCF using SVZ

Privacy-preserving image retrieval based on additive secret sharing in cloud environment

Image Inpainting for Irregular Holes Using Extreme Learning Machine

Contact Info

Product

Resources

About