본문 바로가기
  • Home

Edge Feature Extract CBIRS for Car Retrieval : CBIRS/EFI

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2010, 15(11), pp.75-82
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Koo Gun Seo 1

1숭의여자대학

Accredited

ABSTRACT

The paper proposed CBIRS/EFI with contents based search technique using edge feature information of the object from image information of the object which is uncertain. In order to search specially efficiently case of partial image information of the object, we used the search technique which extracts outline information and color information in feature information of object. In order to experiment this, we extracted side edge feature information of the vehicle for feature information of the object after capture the car image of the underground garage. This is the system which applies a contents base search by the result which analyzes the image which extracts a feature, an original image to search and a last similar measurement result. This system compared in FE-CBIRS systems which are an existing feature extraction contents base image retrieval system and the function which improves the accuracy and an effectiveness of search rate was complemented. The performance appraisal of CBIRS/EFI systems applied edge extraction feature information and color information of the cars. And we compared a color feature search time, a shape characteristic search time and a search rate from the process which searches area feature information. We extracted the case 91.84% of car edge feature extraction rate. And a average search time of CBIRS/EFI is showing a difference of average 0.4-0.9 seconds than FE-CBIRS from vehicle. color search time, shape characteristic search time and similar search time. So, it was proven with the fact that is excellent

Citation status

* References for papers published after 2023 are currently being built.