Wood Color Classification Based on Color Spatial Features and K-means Algorithm

Le résumé fourni par la source

Wood color classification is used to classify the set of wooden boards with similar colors. It is helpful to improve the appearance of the wooden furniture which is spliced by multiple wooden boards. Due to the similarity of colors among wooden boards, the manual color classification is inaccurate and unstable, thus the supervised learning algorithms can hardly be used in this scenario. Moreover, the wooden board is long and its image has high resolution that may lead to the growth of computation complexity. To overcome these challenges, in this paper, we propose a new mechanism for wood color classification with the support of cloud and edge computing. The wood image is preprocessed to subtract irrelevant colors. Then the feature vector is extracted based on 3-D color histogram to reduce the computation complexity. In the offline clustering, the feature vector sets are partitioned into different clusters through K-means algorithm in the cloud server. The clustering result can be used in the online classification to classify the new wood image by the edge server. The experimental results verify the effectiveness of the proposed mechanism.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.