We present an improved sketch-based image search technique through which users can search their target images from the images in database. This technique can be used in constructing an efficient game development framework. Our basic approach is to search the database by comparing the user-created sketch with the graph extracted from the images in the database and estimating the similarity. The images of high similarities are suggested as the candidates that match the target image. To improve the accuracy of the matching process, we substitute the graph-based representation of images with vectorized coherent lines, which are known as one of the most precise schemes in extracting and describing important features in an image. By the experiments on 820 images of 32 categories, we prove that our scheme shows higher matching accuracy than the existing schemes.

ABSTRACT
 1. 서론
 2. 관련 연구
 3. 연구 개요
 4. 알고리즘
  4.1 Cohernet Line Drawing
  4.2 Indexable Oriented Chamfer Matching
  4.3 Two-way matching
 5. 실험결과
  5.1 실험 파라미터
  5.2 실험 결과 비교
  5.3 실험 결과 영상
 6. 결론 및 향후 연구
 감사의 글
 참고문헌

• 이정준(Department of Media Software) | Jungjun Lee
• 양희경(Department of Computer Science, Graduate School Sangmyung University) | Heekyung Yang
• 민경하(Department of Media Software) | Kyungha Min