Semantic modelling of unshaped object: An efficient approach in content based image retrieval

Shamsujjoha, Md.; Ahmed, Marya; Hossain, Fahmida; Jabid, Taskeed

doi:10.1109/iccitechn.2014.7073070

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They tend not to focus upon real-life complex imagery. The experiments for these studies were also conducted on only a small and very specific number of images [13][14][15]. In addition, image retrieval accuracy decreases dramatically with an increasing number of images [16,17].…”

Section: Object Recognitionmentioning

confidence: 99%

The Design of a Multimedia-Forensic Analysis Tool (M-FAT)

Mashhadani¹,

Al-Kawaz²,

Clarke³

et al. 2018

IJMIP

View full text Add to dashboard Cite

Digital forensics has become a fundamental requirement for law enforcement due to the growing volume of cyber and computer-assisted crime. Whilst existing commercial tools have traditionally focused upon string-based analyses (e.g., regular expressions, keywords), less effort has been placed towards the development of multimedia-based analyses. Within the research community, more focus has been attributed to the analysis of multimedia content; they tend to focus upon highly specialised specific scenarios such as tattoo identification, number plate recognition, suspect face recognition and manual annotation of images. Given the everincreasing volume of multimedia content, it is essential that a holistic Multimedia-Forensic Analysis Tool (M-FAT) is developed to extract, index, analyse the recovered images and provide an investigator with an environment with which to ask more abstract and cognitively challenging questions of the data. This paper proposes such a system, focusing upon a combination of object and facial recognition to provide a robust system. This system will enable investigators to perform a variety of forensic analyses that aid in reducing the time, effort and cognitive load being placed on the investigator to identify relevant evidence.

show abstract

Section: Object Recognitionmentioning

confidence: 99%

The Design of a Multimedia-Forensic Analysis Tool (M-FAT)

Mashhadani¹,

Al-Kawaz²,

Clarke³

et al. 2018

IJMIP

View full text Add to dashboard Cite

show abstract

“…Rough set theory is different from the basic theory of fuzzy set and the probability theory, it does not need to advance the number of a given certain characteristics or attributes, but directly from the set of a given problem description, the use of collection, lower approximation and describe the concept of uncertainty through indiscernibility relation and indiscernibility classes to determine the approximation of a given problem domain to find out the implicit knowledge and reveal the potential regularity. In short, the main ideas of the rough set theory is through the indiscernibility relation between attributes, on the premise of ability of classification unchanged, contracted through knowledge to export problem of the decision making and classification rules [5].…”

Section: The Rough Set Theorymentioning

confidence: 99%

Research on the Multiple Feature Fusion Image Retrieval Algorithm based on Texture Feature and Rough Set Theory

Shi¹,

Shao²

2016

Proceedings of the 2016 5th International Conference on Advanced Materials and Computer Science

View full text Add to dashboard Cite

Abstract. Recently, we have witnessed the explosive growth of images with complex information and content. In order to effectively and precisely retrieve desired images from a large-scale image database with low time-consuming, we propose the multiple feature fusion image retrieval algorithm based on the texture feature and rough set theory in this paper. In contrast to the conventional approaches that only use the single feature or standard, we fuse the different features with operation of normalization. The rough set theory will assist us to enhance the robustness of retrieval system when facing with incomplete data warehouse. To enhance the texture extraction paradigm, we use the wavelet Gabor function that holds better robustness. In addition, from the perspectives of the internal and external normalization, we re-organize extracted feature with the better combination. The numerical experiment has verified general feasibility of our methodology. We enhance the overall accuracy compared with the other state-of-the-art algorithms.

show abstract