In this paper, we suggest and implement a flower image recognition system using Difference Image Entropy (hereinafter, DIE), image rotation, contour and color information of the object. Conventional studies on flower or leaf recognition have restrictions and limitations that include a sharp drop of recognition rate due to the varying positions and number of objects in the original object image. Hence, this paper focuses on 1) contour feature extraction technology by drawing and designating flower region of the user's interest, 2) image rotation and color feature extraction technology by drawing and designating flower region of the user's interest, and 3) a distributed processing-based flower image recognition technology using DIE, for robust flower image recognition from the given original flower image with multi-flower objects. The suggested system was evaluated using fourteen species of flowers with each ten samples. Experimental results achieved an average recognition rate of 93.6%.