This paper proposes a new descriptor for texture classification that is robust to image blurring. The method, called Local Phase Quantization (LPQ), uses phase information computed locally in a window for every image position. The phases of the four low-frequency coefficients are decorrelated and uniformly quantized in an eight-dimensional space. A histogram of the resulting code words is created and used as a feature in texture classification. The method is highly insensitive to blur, especially centrally symmetric blur, and is also invariant to uniform illumination changes. Experiments show that the LPQ method achieves higher classification accuracy for blurred texture images compared to well-known methods like LBP and Gabor filter banks. Interestingly, it also performs slightly better for non-blurred textures. The LPQ method is based on the Fourier phase spectrum and is designed to be invariant to blur by using local phase information. The method involves computing the Fourier transform over a local window, extracting phase information, decorrelating the coefficients, and quantizing them. The resulting code words are then used to create a histogram that serves as a feature for texture classification. The method is shown to be robust to blur, even with finite-sized image windows, and is effective in both blurred and non-blurred texture classification. The results demonstrate that the LPQ method outperforms other methods in texture classification, particularly in the presence of blur.This paper proposes a new descriptor for texture classification that is robust to image blurring. The method, called Local Phase Quantization (LPQ), uses phase information computed locally in a window for every image position. The phases of the four low-frequency coefficients are decorrelated and uniformly quantized in an eight-dimensional space. A histogram of the resulting code words is created and used as a feature in texture classification. The method is highly insensitive to blur, especially centrally symmetric blur, and is also invariant to uniform illumination changes. Experiments show that the LPQ method achieves higher classification accuracy for blurred texture images compared to well-known methods like LBP and Gabor filter banks. Interestingly, it also performs slightly better for non-blurred textures. The LPQ method is based on the Fourier phase spectrum and is designed to be invariant to blur by using local phase information. The method involves computing the Fourier transform over a local window, extracting phase information, decorrelating the coefficients, and quantizing them. The resulting code words are then used to create a histogram that serves as a feature for texture classification. The method is shown to be robust to blur, even with finite-sized image windows, and is effective in both blurred and non-blurred texture classification. The results demonstrate that the LPQ method outperforms other methods in texture classification, particularly in the presence of blur.