Gastroscopic Image Retrieval Based on PCA

Herein we describe a system for gastroscopic image retrieval which based on PCA algorithm. First quantize and cluster in HSV color space, make use of spatial partitioning-weighted method to calculate each block’s main color, and then combine with color correlogram to carry out integrate retrieval. A PCA algorithm is adopted to reduce the dimension since the dimension of feature vector which including color and spatial information is high. A prototype system which supports query by example is designed and implemented. The experimental results according to the prototype show that the approach proposed in the paper is effective to gastroscopic images.