Bar Image Identification Based on Laplacian Eigenmap and Fuzzy SVM

Abstract

Bar code image recognition is a key technology in modern logistics management. An efficient identification system is built based on manifold learning and fuzzy SVM. By integrating the fractal image segmentation technology, it realizes high automatic classification and identification of bar code image. At first, the authors conduct the preprocessing of the collected code image, including three steps, tilt correction, image binarization based on globally dynamic threshold, and fractal segmentation technology. Then, a graph-based fuzzy support vector machine is proposed to realize the high accuracy classification and identification. Experimental results indicate that the accuracy of the proposed method is higher than other compared methods in both pure and noisy samples, reaching 96.6% and 94.5%. And no huge decrease exists when some noise is added to the pure dataset, and the percentage is only 2.1%, which is much lower than the drop of other methods. It shows that the proposed method can significantly promote the identification accuracy, the generalization, and robustness to noise.