A Novel Approach to Separate Handwritten Connected Digits

05/2004; DOI: 10.1109/ICDAR.2003.1227847
Source: CiteSeer

ABSTRACT This paper presents a novel approach to separate connected digits in handwritten numerals by employing two agents in the process. The first agent decides on candidate cut-point as the closest feature-point to the center of the deepest top-valley, if any. The second agent argues candidate cut-point as the closest feature-point to the center of the highest bottom-hill, if any. Then the actual cut-point is decided by negotiation, which is influenced by a degree of confidence in each candidate cut-point. Experiments conducted so far are promising and successful as well as justified employing multiple agents. The obtained results are very encouraging with a success factor of 97.8%.

  • [Show abstract] [Hide abstract]
    ABSTRACT: This article presents in two modules a new method for segmenting connected handwritten Persian digits using the characteristics of the foreground and utilizing the background skeleton. The first module excavates all the valleys and hills, if there are any, from the upper pixels and lower pixels of the thinned image respectively. Then feature point excavate. For better segmentation the digits, a separability degree is calculated, regarding the height of the hills and valleys close to each feature point considering the characteristic of connected Persian digits. Then the significance degree is calculated to determine of its influence rate in segmentation. Then, using that, one or few points with high significance degree, which are more influence in the segmentation, are selected as the cutting points. Having excavated the background skeleton, the second module begins to identify the priority points in the skeleton in order to connect them to the cutting points The conducted experiments confirm the accuracy of the factors utilized and the results indicates a correct segmentation at a rate of 97.2%.
    11th International Conference on Control, Automation, Robotics and Vision, ICARCV 2010, Singapore, 7-10 December 2010, Proceedings; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Machine recognition of handwritten numerals has practical significance. Segmentation of connected digits is being recognized as a critical task in the field of document image analysis and recognition. Higher recognition rates for isolated digits Vs those obtained for connected numeral strings exemplify the vital role of connected digits segmentation. The present overview describes various segmentation techniques for connected digits in general numeral strings and mathematical expressions, worked out in this decade.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new algorithm for segmentation of touching handwritten digits. The proposal is divided into two parts: the selection of feature points which is made after the application of skeletonization, and the use of Self-Organizing Maps to define the segmentation points. As these two parts are independent from each other, the method is suitable for parallelization, increasing its performance. The algorithm was tested in a set of 42 images of real digits synthetically connected and achieved very promising results.
    IEEE 23rd International Conference on Tools with Artificial Intelligence, ICTAI 2011, Boca Raton, FL, USA, November 7-9, 2011; 01/2011

Full-text (2 Sources)

Available from
May 22, 2014