Handwriting Recognition Accuracy Improvement by Author Identification
In this paper, two level handwriting recognition concept is presented, where writer identification is used in order to increase handwriting recognition accuracy. On the upper level, author identification is performed. Lower level consists of a classifiers set trained on samples coming from individual writers. Recognition from upper level is used on the lower level for selecting or combining classifiers trained for identified writers. The feature set used on the upper level contains directional features as well as the features characteristic for general writing style as line spacing, tendency to line skewing and proportions of text line elements, which are usually lost in typical process of handwritten text normalization. The proposed method can be used in applications, where texts subject to recognizing come form relatively small set of known writers.
KeywordsWord Recognition Recognition Accuracy Character Recognition Multi Layer Perceptron Handwriting Recognition
Unable to display preview. Download preview PDF.
- 3.Cha, S.H., Srihari, S.N.: Multiple Feature Integration for Writer Integration. In: Proc. of Seventh International Workshop on Frontiers in Handwriting Recognition, pp. 333–342 (2000)Google Scholar
- 8.Schomaker, L., Bulacu, M., van Erp, M.: Sparse-parametric writer identification using heterogeneous feature groups. In: Proc. of Int. Conf. on Image Processing ICIP, vol. 1, pp. 545–548 (2003)Google Scholar
- 9.Bulacu, M., Schomaker, L., Vuurpijl, V.: Writer identification using edge-based directional features. In: Proc. of Seventh International Conference on Document Analysis and Recognition, vol. 2, pp. 937–941 (2003)Google Scholar
- 12.Schlapbach, A., Bunke, H.: Off-line handwriting identification using HMM based recognizers. In: Proc. 17th Int. Conf. on Pattern Recognition, vol. 2, pp. 654–658 (2004)Google Scholar
- 13.Schomaker, L., Bulacu, M., Franke, K.: Automatic writer identification using fragmented connected-component contours. In: Proc. of 9th IWFHR, pp. 185–190. IEEE Computer Society, Los Alamitos (2004)Google Scholar
- 14.Sas, J., Luzyna, M.: Combining character classifier using member classifiers assessment. In: Proc. of 5th Int. Conf. on Intelligent Systems Design and Applications, ISDA 2005, pp. 400–405. IEEE Press, Los Alamitos (2005)Google Scholar
- 15.Kurzynski, M., Sas, J.: Combining character level classifier and probabilistic lexicons in handprinted word recognition - comparative analysis of methods. In: Proc. XI Int. Conference on Computer Analysis and Image Processing. LNCS, pp. 330–337. Springer, Heidelberg (2005)Google Scholar