부산대학교 도서관

Orchid is a kind of terrestrial herb and it has elegant fower posture, quiet fower fragrance, rich colors and noble moral, therefore it has high ornamental value and is deeply loved by people. There are many kinds of orchids, and some of them are similar in shape, texture and color, which make people difcult to quickly and correctly distinguish them. As the existing classifcation model of orchid species have the problems of low accuracy rate and long classifcation time because of the inter species similarities and intra species diferences in orchid species, thus infuencing its wide application. In order to solve the problem above, in this paper, an improved classifcation model based on feature fusion is proposed for orchid species. The achievement of the paper lies in the fact that we successfully developed a classifcation model based on feature fusion to realize the high-efcient classifcation for orchid species. Specifcally, in our scheme, frstly we obtained 12 orchid image sets with number of 12,227 images by network and feld photography; Secondly we analyzed and studied the semantic relationship of diferent scale features from acquired orchid images above; Thirdly we designed an improved classifcation model based on feature fusion on the basis of the semantic relationship above; At last, we used the classifcation model above to realize the high-efcient classifcation for 12 orchid species. The experimental results showed that our proposed classifcation model based on feature fusion in this paper can realize 92.98% classifcation accuracy rate compared with classifcation models without using feature fusion technology, which can greatly improve the classifcation efciency for orchid species.