Improved signature recognition system based on statistical features and fuzzy logic

Abstract

Signature recognition system knows significant attention due to its undeniable importance. For this purpose, a wide-ranged techniques including both statistical and structural approaches, have been introduced. They are both subfields of machine learning that focus on identifying patterns in data. Statistical methodologies are extensively used within diverse domains, providing accurate features and deep understanding of data characteristics. In the proposed system, a statistical framework is adopted, which encompasses three crucial phases: preprocessing, feature extraction, and classification. In the initial stage, a variety of image preprocessing algorithms are employed to segregate signature pixels from background and noise pixels. The second phase consists of extracting the discriminant information based on statistical characteristics, this includes calculating white-black transitions horizontally, vertically, as well as diagonally and antidiagonally. The resulting features are employed as input for the fuzzy min-max classifier (FMMC), which involves iteratively creating hyperboxes. Each iteration comprises three phases: expansion, overlap, and contraction. The primary advantage of applying FMMC lies in its proficiency to handle noisy data and data with overlapping distributions, factors commonly observed in signature images. The proposed method is evaluated with various systems utilizing histogram of oriented gradient, profile projection, convolutional neural network, and Loci as feature extraction techniques, as well as K-nearest neighbors and multilayer perceptron as classification methods. The experimental findings confirm the effectiveness of the proposed framework, demonstrating its ability to achieve a notable accuracy of 99.16%, along with remarkable average precision, recall, and F1-score values of 99.17%, 99.24%, and 99.16% respectively.