Video Mining using LIM Based Clustering and Self Organizing Maps

Devasena, C. Lakshmi; Hemalatha, M.

doi:10.1016/j.proeng.2012.01.945

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outcomes obtained after simulating the proposed technique conveyed its superiority as compared to other image mining schemes. In the study of Devasena and Hemalatha [41], a novel approach for video analytics has been introduced. The technique integrated with a unique LIM based clustering paradigm which uses self-organizing maps to discover unique patterns from video frames and also distinguish novelty in the frames belongs to a video sequence.…”

Section: Review Of Literaturesmentioning

confidence: 99%

A Systematic Review of Existing Data Mining Approaches Envisioned for Knowledge Discovery from Multimedia

S¹,

N²

2018

IJECE

View full text Add to dashboard Cite

<p>The extensive use of multimedia technologies extended the applicability of information technology to a large extent which results enormous generation of complex multimedia contents over the internet. Therefore the number of multimedia contents available to the user is also exponentially increasing. In this digital era of the cloud-enabled Internet of Things (IoT), analysis of complex video and image data plays a crucial role.It aims to extract meaningful information as the distributed storages and processing elements within a bandwidth constraint network seek optimal solutions to increase the throughput along with an optimal trade-off between computational complexity and power consumption. However, due to complex characteristics of visual patterns and variations in video frames, it is not a trivial task to discover meaningful information and correlation. Hence, data mining has emerged as a field which has diverse aspects presently in extracting meaningful hidden patterns from the complex image and video data considering different pattern classification approach. The study mostly investigates the existing data-mining tools and their performance metric for the purpose of reviewing this research track.It also highlights the relationship between frequent patterns and discriminativefeatures associated with a video object. Finally, the study addresses the existing research issues to strengthen up the future direction of research towards video analytics and pattern recognition.</p>

show abstract

Section: Review Of Literaturesmentioning

confidence: 99%

A Systematic Review of Existing Data Mining Approaches Envisioned for Knowledge Discovery from Multimedia

S¹,

N²

2018

IJECE

View full text Add to dashboard Cite

show abstract

“…The technique uses an unsupervised learning-based approach using multiple facial expression factors. Devasena and Hemalatha [54] have presented a unique mining technique for videos which is based on clustering process. The technique also uses self organizing map for further training process.…”

Section: Existing Techniques Of Vamentioning

confidence: 99%

Insights to Video Analytic Modelling Approach with Future Line of Research

Chandra¹,

Reddy²

2016

IJCA

View full text Add to dashboard Cite

The area of Video analytics has made some significant improvement due to advancement in image processing and datamining techniques. However, the inclination is still towards image contents and less to mined contents owing to many unsolved issues. Although concept of mining is more than 2 decade old, but mining approaches are yet to be standardized in the area of video surveillance system. With evolution of newer set of challenges in video capturing, existing mining models finds itself less applicable due to unstructured format of dynamic frames. Hence, this paper discusses about video analytics and presents a brief discussion of frequently used mining approaches in video as well as discussed some recent studies in this direction in order to scale the degree of effectiveness in existing system. The paper also presents research gap and provided solution as future line of research as a possible way to overcome the research gap.

show abstract

Video Mining using LIM Based Clustering and Self Organizing Maps

Cited by 2 publications

References 21 publications

A Systematic Review of Existing Data Mining Approaches Envisioned for Knowledge Discovery from Multimedia

A Systematic Review of Existing Data Mining Approaches Envisioned for Knowledge Discovery from Multimedia

Insights to Video Analytic Modelling Approach with Future Line of Research

Contact Info

Product

Resources

About