In this paper, a graph regularized adaptive joint collaborative representation algorithm is proposed to overcome a low classification accuracy problem caused by insufficient utilization of spatial information for hyperspectral image classification. Firstly, the bilateral filter is adopted to extract spatial information for hyperspectral image to fully explore the spatial information of each pixel. Then, a graph regularized term is introduced into the objective function of joint collaborative representation to maintain the local manifold structure of hyperspectral image(HSI) data. On one hand, the image segmentation is used to adjust the shape of the spatial neighborhood; on the other hand, an adaptive space-spectral feature fusion strategy is proposed by assigning different weights to the spatial neighbors of the central pixels. Finally, the label of each testing sample is determined by utilizing the least errors criterion. Experimental results on Indian Pines and Pavia University datasets show that overall accuracies of the proposed algorithm can achieve 98.50% and 97.30% respectively.