Just-noticeable difference (JND) is defined as the smallest intensity change in an image that can be noticed by the human vision system (HVS). Any perceptible distortion level must be greater than the JND. Based on this observation, a local binary pattern (LBP) is developed for image quality assessment. First, the JND map of the image is computed. The spatial and relative intensity relationships among pixels in a local neighborhood are employed to generate the proposed LBP based on the JND map. Then, image contrast is used as a weighting factor for the LBP histogram generation to characterize the structural and contrast information of the image. Finally, the contrast and structure changes due to image distortion are measured by calculating the similarity between contrast-weighted histograms of the reference and distorted images. Support vector regression is employed to pool the similarity to predict the quality. Experimental results on benchmark databases demonstrate that the proposed LBP can effectively and accurately measure image quality, which is consistent with the HVS. The proposed method achieves high consistency with subjective perception using 18 reference values and performs better than other state-of-the-art reduced reference image quality assessment methods.