Intelligent and Secure Content-Based Image Retrieval for Mobile Users

In the recent years, with the rapid development of technologies production, digital images tend to grow in exponential order. This makes the challenge in retrieving image. Image retrieval plays a vital role in various fields such as Medical, Tourism promotion, Forensics Lab etc. In order to handle these rapid growth efficient images retrieval methods need to be developed. This paper is presented with the survey of different Image retrieval techniques which used various techniques from visual features to the latest deep learning with Convolutional Neural Network(CNN) which become the best approach for image retrieval with number of layers applicable for large database. This survey concretes the way to understand the processing methods of Content Based Image Retrieval (CBIR).

show abstract

“…For mobile users, Content based retrieval methods Run time cost and communication cost are reduced. [6]…”

Section: Discussionmentioning

confidence: 99%

“…Fei Liu et al [6] proposed a method to overcome the security concern of mobile users in retrieving images. Images from the cloud were retrieved without the user's constant interaction.…”

Section: Literature Survey A)mentioning

confidence: 99%

A Survey on Image Retrieval Techniques

Lalitha

Murugavalli²

2020

Intelligent Systems and Computer Technology

View full text Add to dashboard Cite

show abstract

“…These models were selected for their outstanding performance when classified the plant disease images from the ImageNet dataset [20]. The VGG16, as illustrated in Figure 3 [21], used a recommended default input image size of 224×224×3 and 13 convolutional layers with a rectified linear unit (ReLU) activation function. The convolutional layers were fed into a max pooling, three fully connected (FC) layers and a Softmax function at the end of the architecture.…”

Section: Pretrained Dcnn Model and Parametersmentioning

confidence: 99%

Efficacy of chili plant diseases classification using deep learning: a preliminary study

Rozlan

Hanafi

2022

IJEECS

View full text Add to dashboard Cite

<span>Plant disease classification using deep learning techniques is a popular research area due to the numerous opportunities for introducing advance and robust classifiers. Nevertheless, classifying chilli plant diseases accurately from images under uncontrolled environment and various imaging conditions remains unsolved due to the lack of chilli disease image datasets. In this study, the efficacy of three high-performance deep learning algorithms, namely VGG16, InceptionV3, and EfficientNetB0, in classifying three types of chilli leaves diseases, namely upward curling, mosaic/mottling, and the bacterial spot, is demonstrated. These methods are popularly used for other plant disease classifications due to their effectiveness. The experiments were performed on the 3,000 chilli plant disease images collected from three different field environments in Selangor, Malaysia. The images were captured with a complex background and various illuminations, angles, and distances to reflect the real-life scenarios. The complexity of the collected images was created based on the taxonomic information of chilli leaves diseases and the unavailability of chilli disease images under various imaging conditions in the publicly available plant disease databases. Experimented using appropriate specifications, the models demonstrated outstanding performance with more than 95% accuracy with the highest accuracy of 98.83% by InceptionV3.</span>

show abstract

“…However, these schemes are still too time-consuming rather than practice. In recent work, Liu et al [33] try to extract encrypted features based on a pre-trained CNN model (e.g., VGG16). The better feature extractor brings much higher accuracy.…”

Section: Schemes Based On Typical Featurementioning

confidence: 99%

“…There are two main strategies to cope with this problem: one type of schemes [34] tries to use SMC technology, such as garbled circuit [35], to assist nonlinear operations; the others [36] attempt to seek approximate algorithms to replace them. Actually [33] can be seen as the utilization of [34]. However, these schemes not only cause plenty of time consumption but also need to convert ciphertext to an integer (or bits), which will cause extra precision loss.…”

Section: Schemes Based On Typical Featurementioning

confidence: 99%

Privacy-Preserving Image Retrieval Based on Additive Secret Sharing

Xia¹,

Gu²,

Xiong³

et al. 2020

Preprint

View full text Add to dashboard Cite

The rapid growth of digital images motivates individuals and organizations to upload their images to the cloud server. To preserve the privacy, image owners would prefer to encrypt the images before uploading, but it would strongly limit the efficient usage of images. Plenty of existing schemes on privacy-preserving Content-Based Image Retrieval (PPCBIR) try to seek the balance between security and retrieval ability. However, compared to the advanced technologies in CBIR like Convolutional Neural Network (CNN), the existing PPCBIR schemes are far deficient in both accuracy and efficiency. With more cloud service providers, the collaborative secure image retrieval service provided by multiple cloud servers becomes possible. In this paper, inspired by additive secret sharing technology, we propose a series of additive secure computing protocols on numbers and matrices with better efficiency, and then show their application in PPCBIR. Specifically, we extract CNN features, decrease the dimension of features and build the index securely with the help of our protocols, which include the full process of image retrieval in plaintext domain. The experiments and security analysis demonstrate the efficiency, accuracy and security of our scheme.

show abstract

Intelligent and Secure Content-Based Image Retrieval for Mobile Users

Cited by 40 publications

References 36 publications

A Survey on Image Retrieval Techniques

A Survey on Image Retrieval Techniques

Efficacy of chili plant diseases classification using deep learning: a preliminary study

Privacy-Preserving Image Retrieval Based on Additive Secret Sharing

Contact Info

Product

Resources

About