Due to the variations among the birds, bird breed classification is still a challenging task. In this paper, we
propose a saliency based graphical model (GMS), which can precisely annotate the object on the pixel
level. In the proposed method, we first over-segment the image into several regions. Then, GMS extracts
the object and classifies the image based on the local context, global context and saliency of each region.
In order to achieve a high precision of classification, we use SVM to classify the image based on the features
of the annotated bird. Finally, we employ posterior probability distribution obtained by GMS and
SVM to perform the image classification. Experiments on the Caltech-UCSD Birds dataset show that
the proposed model can achieve better results compared with existing bird breed classification methods
based on graphical model.
Due to the variations among the birds, bird breed classification is still a challenging task. In this paper, wepropose a saliency based graphical model (GMS), which can precisely annotate the object on the pixellevel. In the proposed method, we first over-segment the image into several regions. Then, GMS extractsthe object and classifies the image based on the local context, global context and saliency of each region.In order to achieve a high precision of classification, we use SVM to classify the image based on the featuresof the annotated bird. Finally, we employ posterior probability distribution obtained by GMS andSVM to perform the image classification. Experiments on the Caltech-UCSD Birds dataset show thatthe proposed model can achieve better results compared with existing bird breed classification methodsbased on graphical model.
การแปล กรุณารอสักครู่..
