Biometrics is the science and technology of automatically identifying people by their unique physical and behavioural traits. More and more people are being verified by biometric methods. In order to increase signature verification’s classification accuracy, researchers are always looking into new feature representations. As a robust feature extraction method, local binary pattern (LBP) has been proposed to capture the texture. LBP is a texture measure that works in any colour space, as it is based on a neighbourhood-level definition of texture. The LBP operator converts a 3 × 3 area’s grayscale value to binary by using it as a threshold for a binary code. You may describe the texture using the histogram of these labels. To generate a binary code for each pixel in a greyscale image, the LBP approach begins with a basic processing step. Intensity differences between surrounding pixels and the current pixel are encoded by this code. Each subject is given a set of 100 signatures, of which 10 are authentic and 3 are forgeries, to use as training data. The testing process involves determining whether or not a submitted signature is a legitimate copy of the subject’s original. In order to extract features, the LBP operator is used, which is a gray-scale invariant texture measure based on a generic definition of texture in the context of a particular neighbourhood. By thresholding a 33 area by its central grey value, the LBP operator generates a binary code. A texture description is then derived from the histograms of these labels. Tests are conducted on signature photos from the local dataset and the MCYT database. Signature verification systems have used KNN and SVM classifiers. KNN and SVM classifiers’ overall recognition accuracy and FAR are provided.