Keyframe selection of frame similarity to generate scene segmentation based on point operation

Wisnu Widiarto*, Mochamad Hariadi, Eko Mulyanto Yuniarno

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Video segmentation has been done by grouping similar frames according to the threshold. Two-frame similarity calculations have been performed based on several operations on the frame: Point operation, spatial operation, geometric operation and arithmatic operation. In this research, similarity calculations have been applied using point operation: Frame difference, gamma correction and peak signal to noise ratio. Three-point operation has been performed in accordance with the intensity and pixel frame values. Frame differences have been operated based on the pixel value level. Gamma correction has analyzed pixel values and lighting values. The peak signal to noise ratio (PSNR) has been related to the difference value (noise) between the original frame and the next frame. If the distance difference between the two frames was smaller then the two frames were more similar. If two frames had a higher gamma correction factor, then the correction factor would have an increasingly similar effect on the two frames. If the value of PSNR was greater then the comparison of two frames would be more similar. The combination of the three point operation methods would be able to determine several similar frames incorporated in the same segment.

Original languageEnglish
Pages (from-to)2839-2846
Number of pages8
JournalInternational Journal of Electrical and Computer Engineering
Volume8
Issue number5
DOIs
Publication statusPublished - Oct 2018

Keywords

  • Frame difference
  • Gamma correction
  • Peak signal to noise ratio
  • Point operation
  • Similarity

Fingerprint

Dive into the research topics of 'Keyframe selection of frame similarity to generate scene segmentation based on point operation'. Together they form a unique fingerprint.

Cite this