• BALAJI GUGULOTH
• BHOOKIYA NAVEEN

Video resemblance checking is the most time-consuming and cost-effective procedure. Effective and quick manipulations of huge video files are becoming increasingly desirable as the demand for visual information of rich material grows. Several experiments on content-based video retrieval have been conducted. Despite its importance, video subsequence identification, which entails finding information in a long video sequence similar to a short query clip, has received little attention. This paper proposes a graph transformation and matching solution for this problem in order to detect potential changes in ordering. A bipartite graph is employed to express the mapping relationship between the query and database video, which is then used to locate related frames using a unique batch query approach. The closely matching chunks of the long sequence are then recovered using a filter-and-refine search approach, and certain irrelevant subsequences are pruned. During the filtering stage, Maximum Size Matching decreases the number of candidates by producing subgraphs from the query and candidate subsequences. Sub-Maximum Similarity Matching is used during the refinement phase to select the subsequence with the highest aggregate score among all candidates, using a comprehensive video similarity model that takes into account visual content, temporal order, and frame alignment information.

ROBUST TECHNIQUE FOR VIDEO RESEMBLANCE CHECKING

"ROBUST TECHNIQUE FOR VIDEO RESEMBLANCE CHECKING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.182-186, February-2019, Available :http://www.jetir.org/papers/JETIRFE06033.pdf

"ROBUST TECHNIQUE FOR VIDEO RESEMBLANCE CHECKING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp182-186, February-2019, Available at : http://www.jetir.org/papers/JETIRFE06033.pdf