The scene recognition between indoor and outdoor is one of the basic problems in image processing. A solution to this problem which does not require image segmentation and object recognition is proposed in this paper. First of all

a 5-level wavelet transform was implemented on the image

then the rotation invariant LBP algorithm was used to extract the texture feature from 2-level to 5-level LL sub-images. Afterwards

the mean and variance of the LH

HL

HH sub-images from 2-level to 1-level were computed. Finally

these two low-dimensional eigenvectors were concatenated as the image feature to classify the indoor and outdoor scene images. The experiment results indicate that our algorithm performs well on indoor/outdoor classification

and the overall texture information of the fuzzy image is only needed in the scene recognition between indoor and outdoor

rather than the local detailed information such as object shape.