TY - JOUR
AU - Wang, Hai
AB - In order to solve the problems of time-consuming and low classification accuracy of feature extraction in traditional painting feature classification methods, a new method based on stochastic forest algorithm is proposed. The colour feature of painting is converted into HSV component, and the original LBP value of the painting image is converted into 59-dimension feature vector by uniform mode to extract the painting texture feature. The wavelet transform method is used to obtain the high and low frequency band signal of painting features, and the noise reduction of painting features is completed. The similarity coefficient is determined by stochastic forest algorithm, and the similarity matrix of painting features is obtained to complete the classification of painting features. The experimental results show that the accuracy of the classification method can reach 98% and the time is less than 2 s.
TI - Research on classification method of painting features based on stochastic forest algorithm
JF - International Journal of Information and Communication Technology
DO - 10.1504/ijict.2023.132167
DA - 2023-01-01
UR - https://www.deepdyve.com/lp/inderscience-publishers/research-on-classification-method-of-painting-features-based-on-oTMMyrPsj8
SP - 91
EP - 105
VL - 23
IS - 1
DP - DeepDyve
ER -