CBIR-CNN: Content-Based Image Retrieval on Celebrity Data Using Deep Convolution Neural Network

Singh, Pushpendra; Hrisheekesha, P.N.; Singh, Vandita

doi:10.2174/2666255813666200129111928

Cited by 21 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Singh et al . propose a similar CNN-Based feature extractor for celebrity facial image retrieval, prioritizing the usage of convolutional layer outputs and max-pooling operations for dimensionality reduction in representing the repeated patterns in facial images [ 106 ]. Sezavar et al .…”

Section: Related Workmentioning

confidence: 99%

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

António,

Valente,

Mora

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

A trademark’s image is usually the first type of indirect contact between a consumer and a product or a service. Companies rely on graphical trademarks as a symbol of quality and instant recognition, seeking to protect them from copyright infringements. A popular defense mechanism is graphical searching, where an image is compared to a large database to find potential conflicts with similar trademarks. Despite not being a new subject, image retrieval state-of-the-art lacks reliable solutions in the Industrial Property (IP) sector, where datasets are practically unrestricted in content, with abstract images for which modeling human perception is a challenging task. Existing Content-based Image Retrieval (CBIR) systems still present several problems, particularly in terms of efficiency and reliability. In this paper, we propose a new CBIR system that overcomes these major limitations. It follows a modular methodology, composed of a set of individual components tasked with the retrieval, maintenance and gradual optimization of trademark image searching, working on large-scale, unlabeled datasets. Its generalization capacity is achieved using multiple feature descriptions, weighted separately, and combined to represent a single similarity score. Images are evaluated for general features, edge maps, and regions of interest, using a method based on Watershedding K-Means segments. We propose an image recovery process that relies on a new similarity measure between all feature descriptions. New trademark images are added every day to ensure up-to-date results. The proposed system showcases a timely retrieval speed, with 95% of searches having a 10 second presentation speed and a mean average precision of 93.7%, supporting its applicability to real-word IP protection scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

António,

Valente,

Mora

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Therefore, it is especially important to define and use appropriate similarity metrics on the defined feature space to effectively complete the image retrieval task. In this paper, we focus on several distance metric functions commonly used in similarity metrics [16], and similarity learning methods based on diffusion processes. The classical histogram similarity metric is used to calculate the normalized correlation coefficient between two histograms, and the idea of this method is simple, which is to judge the similarity by the difference between vectors mathematically.…”

Section: Automatic Generation Based On Plant Image Similaritymentioning

confidence: 99%

Automatic Algorithm for Fractal Plant Art Image Similarity Feature Generation

Liu

Sun

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

With the popularity of smart devices and the Internet, the volume of multimedia data is growing rapidly, and content-based image retrieval (CBIR) can search for similar images from large-scale images to realize the utilization of the data. For data owners, outsourcing the management and maintenance of image data to cloud service providers can effectively reduce costs, but there is a privacy leakage problem. In this paper, we focus on image feature extraction, index design, and image similarity recognition methods under a dual server model with content-based image security similarity recognition as the research topic, the work done such as proposing a BOVW (Bag of Visual Word) feature-based image security similarity recognition scheme. The scheme combines SIFT (scale-invariant feature transform) feature secure extraction and locally sensitive hashing algorithm to achieve secure extraction of BOVW features of images. To protect the BOVW features of images, an inverted index based on word frequency division is designed, the index is stored in chunks, and an image secure similarity recognition scheme based on CNN (convolutional neural networks) features is proposed. The scalable hash index based on dimensional division is designed based on the image CNN features secure extraction algorithm. The security and performance of the proposed scheme are theoretically analyzed and experimentally verified. Based on different image datasets, the impact of different parameters on the performance of the scheme is tested, and optimized parameters are given. The experimental results show that the proposed scheme in this paper can effectively improve the efficiency of analyzing the similarity of plant botanical art images compared to the existing schemes.

show abstract

“…When both are matched with a similarity of the images from the internet and repositories can be derived immediately to improve the latency on the network node computers. The similarity has founded in the images was done by features such as resolution, size, clarity, and type of the images created on the internet sources [4]. The entire process of CBIR has done using a lot of classical approach algorithms but the extraction time and accuracy are still ha challenges and; limitations to access them on a centralized huge cloud server on the network, The internet speed is also a factor for delay and latency problems in CBIR, but it reflects the contents available in the cluster's features [5].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study on Image Retrieval Algorithms of Cloud Storage for Information Extraction in HealthCare System

Vasudeva¹,

S.N²

2022

IJCDS

View full text Add to dashboard Cite

The world is full of digital data disseminated everywhere for creating, accessing, and storing information among the people's communication through media with network devices. The huge volume of data stored as a repository in a remote place where it is accessed in terms of datasets/databases. Such kinds of databases are extracted from the repositories in a short period based on its features and contents available inside the databases. The processing of transformation of data from one form to another using the above-said functions of a database plays a vital role in extracting information on large networks. Information Retrieval (IR) is the normal technique to derive the information from the warehouses through its features and functionalities. Cloud computing is the trending technique to store the accessed information and converted it into meaningful data as a database and stored in a remote place among the nodes of networks. The stored databases are collected and combined as a group of data based on the features present in the database then stored as clusters. Separate clusters are created in the cloud to store text, audio, video, and multimedia supported files remotely from different sources on the internet. From those clusters, extracting the accurate files needed should be processed through various classical algorithms and techniques with the supported tools. Content-Based Image Retrieval (CBIR) is the common popular technique used to get accurate results as an output from the cloud clusters in a short duration of time. The latency and efficiency will be very low to process the huge volume of data on the network. Classical approaches implemented innovative ideas such as query-based approach, features extraction, auto-encoders, and indexing on this CBIR technique and applied them through machine learning algorithms, CNN (Convolution Neural Networks), and deep learning. Since cloud computing is working with the internet as an important phenomenon all the techniques are needed for internet sources. The accuracy and latency of the CBIR technique on cloud storage servers is a challenging mission for people who are needed in different sectors, especially in healthcare. To find better solutions for the above-said problem this survey paper has been written from a technical perspective view, and helpful to the researchers get motivated to do their innovative works, and ideas on the CBIR model to emphasize in the competitive world.

show abstract

CBIR-CNN: Content-Based Image Retrieval on Celebrity Data Using Deep Convolution Neural Network

Cited by 21 publications

References 0 publications

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

Automatic Algorithm for Fractal Plant Art Image Similarity Feature Generation

A Comprehensive Study on Image Retrieval Algorithms of Cloud Storage for Information Extraction in HealthCare System

Contact Info

Product

Resources

About