Edge-Based Feature Extraction Method for Image Retrieval(Sessions5 Image Processing)(IWAIT2002)

Gosuke OHASHI, Keita MOCHIZUKI, Yasutake NAGASHIMA, Yoshifumi SHIMODAIRA
2002 ITE Technical Report  
Slk) propose a new feature extraction method for contentbased irnage retrieval using a graphical rough sketch, The proposal image feature is based on the shape and the texture of the object This edge-based feature extraction method is to represent the relative positional relationship between edge pixels, This proposed feature has adyantage of shift-invariant, scale-invariant, and rotate-invariant. Tb verify the effectiveness ofthis method, we have carried out two experiments. First, in order to
more » ... assess the extracted feature value, a comparison of subjective evaluation was performed using Multi-Dimensional Scaling. The result is ln good agreement with human perceptual judgrnents. Then, as a result of applying the method to 3,20e images from COREL photo gallery, we found that the proposal feature is effective for image retrieval.
doi:10.11485/itetr.26.4.0_1 fatcat:ejrvfpc2r5dkxg57dcggiepy7e