New Content Based Image Retrieval database structure using Query by Approximate Shapes

Deniziak, Stanislaw; Michno, Tomasz

doi:10.15439/2017f457

Cited by 9 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite this, bag-offeature techniques have outperformed standard global descriptors at a high computational cost trade-off. SIFT enforcement is also not the ideal solution owing to the sparse spatial distribution of its detected points and the large dimension of its calculated descriptors [23]. In addition, it is inadequate for large-scale databases.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Image Retrieval Using Convolutional Autoencoder, InfoGAN, and Vision Transformer Unsupervised Models

et al. 2023

View full text Add to dashboard Cite

Query by Image Content (QBIC), subsequently known as Content-Based Image Retrieval (CBIR) systems, may offer a more advantageous solution in a variety of applications, including medical, meteorological, search by image, and others. Such systems primarily use similarity matching algorithms to compare image content to get their relevance from databases. They are essentially measuring the spatial distance between extracted visual features from a query image and their correspondence in the dataset. One of the most challenging query retrieval problems is Facial Sketched-Real Image Retrieval (FSRIR), which is content similarity matching based. These facial retrieving systems are employed in a variety of contexts, including criminal justice. The difficulties of retrieving such sorts come from the composition of the human face and its distinctive parts. In addition, the comparison between these images is made from two different domains. Besides, to our knowledge, there is a rare existence of large-scale facial datasets that can be used to evolve the performance of the retrieving system. The success of the retrieval process is governed by the method used to calculate similarity and the efficient representation of compared images. However, by effectively representing visual features, the main challenge-posing component of such approaches might be resolved. Hence, this paper has several contributions that fill the research gap in content-based similarity matching and retrieving as follows: 1) The first contribution is extending the Chinese University Face Sketch (CUFS) dataset by including augmented images, introducing to the community a novel dataset named Extended Sketched-Real Image Retrieval (ESRIR). The CUFS dataset has been extended from 100 images to include 53,000 facial sketches and 53,000 real facial images. 2) The paper's second contribution is proposing three new algorithms for sketched-real image retrieving based on convolutional autoencoder, Infogan, and Vision Transformer unsupervised models for large datasets. 3) Furthermore, to meet the subjective demands of the users because of the prevalence of multiple query formats. The third contribution of this paper is to train and assess the proposed algorithms across two additional facial datasets of various image sorts. 4) Recently, the majority of people have preferred searching for brand logo images, but it may be tricky to separate certain brand logo features from their alternatives and even from other features in an image. Thus, the fourth contribution is to compare logo image retrieval performance based on visual features derived from each of the three suggested retrieving systems. 5) The paper also proposes cloud-based energysaving and computational complexity approaches in large-scale datasets. Due to the ubiquity of touchscreen devices, users often make drawings based on their fantasies for certain object image searches. Thus, the proposed algorithms were tested and assessed on a tough dataset of doodle-scratched human artworks. They are also studied for a...

show abstract

Section: Related Workmentioning

confidence: 99%

“…Besides, it is incompatible with large-scale datasets. Consequently, the authors of [25] proposed matching based on approximate shapes, with the object represented as a collection of recognized approximate forms termed "primitives." Each primitive has various descriptive parameters as well as information about its kind.…”

Section: Related Workmentioning

confidence: 99%

Image Retrieval Using Convolutional Autoencoder, InfoGAN, and Vision Transformer Unsupervised Models

et al. 2023

View full text Add to dashboard Cite

show abstract

“…ON HSL IMAGE REPRESENTATION In this paper we propose to enhance the shapes extraction algorithm in comparison with the previous version used in [1]. The main idea of the improvement is based on converting an image into a HSL color space.…”

Section: The Image Shapes Extraction Algorithm Basedmentioning

confidence: 99%

“…The tree database structure and operations which may be performed (adding, deleting and querying graphs) were described more detailed in [1].…”

Section: The Database Structurementioning

confidence: 99%

See 1 more Smart Citation

Query by Approximate Shapes Image Retrieval with improved object sketch extraction algorithm

Deniziak¹,

Michno²

2018

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

In this paper a new Content Based Image Retrieval based on a sketch method was proposed. The main idea of the algorithm is based on decomposing an object into predefined set of shapes (primitives): line segments, polylines, polygons, arches, polyarches and arc-sided polygons. All primitives are stored as a graph in order to store the mutual relations between them. Graphs are stored in a tree-based structure which allows fast querying. As an improvement to the algorithm, a conversion to the HSL color space was proposed in order to detect primitives more accurately. Moreover, computing all line slopes in relation to the object oriented bounding box was also proposed. Additionally, in order to better detect objects present in images, the usage of Edge Boxes algorithm was proposed.

show abstract

Graph of Primitives Matching Problem in the World Wide Web CBIR Searching Using Query by Approximate Shapes

Deniziak

Michno

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

New Content Based Image Retrieval database structure using Query by Approximate Shapes

Cited by 9 publications

References 20 publications

Image Retrieval Using Convolutional Autoencoder, InfoGAN, and Vision Transformer Unsupervised Models

Image Retrieval Using Convolutional Autoencoder, InfoGAN, and Vision Transformer Unsupervised Models

Query by Approximate Shapes Image Retrieval with improved object sketch extraction algorithm

Graph of Primitives Matching Problem in the World Wide Web CBIR Searching Using Query by Approximate Shapes

Contact Info

Product

Resources

About