Spiral architecture based hybrid fractal image compression

Ismail, B. Mohammed; Reddy, T. Bhaskara; Reddy, B. Eswara

doi:10.1109/iceeccot.2016.7955179

Cited by 11 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evolution of SBIR has closely paralleled advancements in image processing [5,6], computer vision, and machine learning. Originating in the late 1990s as an offshoot of CBIR, early SBIR systems focused on basic shape matching using simple feature extraction techniques [7].…”

Section: Introductionmentioning

confidence: 99%

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks

Gopu,

Dunna

2024

J. Imaging

View full text Add to dashboard Cite

Sketch-based image retrieval (SBIR) refers to a sub-class of content-based image retrieval problems where the input queries are ambiguous sketches and the retrieval repository is a database of natural images. In the zero-shot setup of SBIR, the query sketches are drawn from classes that do not match any of those that were used in model building. The SBIR task is extremely challenging as it is a cross-domain retrieval problem, unlike content-based image retrieval problems because sketches and images have a huge domain gap. In this work, we propose an elegant retrieval methodology, StyleGen, for generating fake candidate images that match the domain of the repository images, thus reducing the domain gap for retrieval tasks. The retrieval methodology makes use of a two-stage neural network architecture known as the stacked Siamese network, which is known to provide outstanding retrieval performance without losing the generalizability of the approach. Experimental studies on the image sketch datasets TU-Berlin Extended and Sketchy Extended, evaluated using the mean average precision (mAP) metric, demonstrate a marked performance improvement compared to the current state-of-the-art approaches in the domain.

show abstract

Section: Introductionmentioning

confidence: 99%

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks

Gopu,

Dunna

2024

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Image compression, as a specialist topic of electronic engineering, has gotten a lot of interest recently due to its wide range of applications. Compressed picture transmission saves bandwidth and, as a result, assures cost-effective transmission [1]. Today's uses for such compressions span from mobile phones to high-definition television transmission among many others, towards applications that require very high quality, including professional digital video recording (DVD), and digital cinema, including large-screen digital imaging (LCD).…”

Section: Introductionmentioning

confidence: 99%

“…Today's uses for such compressions span from mobile phones to high-definition television transmission among many others, towards applications that require very high quality, including professional digital video recording (DVD), and digital cinema, including large-screen digital imaging (LCD). The development of tools and techniques for ultralow-bit-rate image coding as a consequence of this has seen a significant increase in demand [1]. The human visual system processes a two-dimensional (2-D) signal into a picture.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Fractal Image Compression Techniques

Dwivedi

Mishra

2022

2022 IEEE International Conference on Current Development in Engineering and Technology (CCET)

View full text Add to dashboard Cite

Computed tomography (CT) scans have great medical value since it helps clinicians determine clinical staging and surgical range. In offline storage and remote diagnosis, a significant number of CT scan pictures necessitate a huge quantity of storage space and transmission capacity in the Picture Archiving and Communication System (PACS). As a result, in high-quality MRI images, compression is research-oriented. Present compression techniques for CT-scanned images with an increased compression ratio result in data loss on lesions, which may lead to misdiagnosis; compression approaches for CTscanned images and also MRI images with a low compression ratio do not realize the desired effect. As a result, rapid fractalbased image compression in a variety of areas like DWT, DCT, etc. has been reviewed in this paper and its applications in further domains have been discussed.

show abstract

Method to Enhance Classification of Skin Cancer Using Back Propagated Artificial Neural Network

Nyemeesha

Ismail

2021

Applied Intelligence and Informatics

View full text Add to dashboard Cite

Spiral architecture based hybrid fractal image compression

Cited by 11 publications

References 5 publications

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks

Zero-Shot Sketch-Based Image Retrieval Using StyleGen and Stacked Siamese Neural Networks

Comparison of Fractal Image Compression Techniques

Method to Enhance Classification of Skin Cancer Using Back Propagated Artificial Neural Network

Contact Info

Product

Resources

About