In this article, we propose a lexicon-free, script-dependent approach to segment online handwritten isolated Tamil words into its constituent symbols. Our proposed segmentation strategy comprises two modules, namely the (1) Dominant Overlap Criterion Segmentation (DOCS) module and (2) Attention Feedback Segmentation (AFS) module. Based on a bounding box overlap criterion in the DOCS module, the input word is first segmented into stroke groups. A stroke group may at times correspond to a part of a valid symbol (over-segmentation) or a merger of valid symbols (under-segmentation). Attention on specific features in the AFS module serve in detecting possibly over-segmented or under-segmented stroke groups. Thereafter, feedbacks from the SVM classifier likelihoods and stroke-group based features are considered in modifying the suspected stroke groups to form valid symbols.The proposed scheme is tested on a set of 10000 isolated handwritten words (containing 53,246 Tamil symbols). The results show that the DOCS module achieves a symbol-level segmentation accuracy of 98.1p, which improves to as high as 99.7p after the AFS strategy. This in turn entails a symbol recognition rate of 83.9p (at the DOCS module) and 88.4p (after the AFS module). The resulting word recognition rates at the DOCS and AFS modules are found to be, 50.9p and 64.9p respectively, without any postprocessing.

Attention-Feedback Based Robust Segmentation of Online Handwritten Isolated Tamil Words

http://tudr.thapar.edu:8080/jspui/bitstream/10266/1780/3/1780.pdf

Use of Dominant Point Detection Feature for Recognition of Online Handwritten Devanagari Script

Among the biometric characteristic, signature forgery is the easiest way to do. Possibility of signature forgery similarity might be reached perfectly. This paper introduced a new technique to improve dominant point feature system based on its location for online signature verification. Dynamic Time Warping is used to match two signature features vector. The performance of system is tested by using 50 participants. Based on simulation result, system accuracy without presence of the simple and trained impostors is 99.65% with rejection error is 0% and acceptance error is 0.35%. While the current systems are faced with the simple and trained impostors, system accuracy became 91.04% with rejection error is 1.6% and an average of acceptance error is 7.36% with details as follows; acceptance error is 0.08%, acceptance error of simple impostors is 4.4%, and acceptance error of trained impostors is 17.6%.The improved feature within fusion is produce better accuracy significantly than dominant point feature. Accuracy of the improved feature within fusion is 91.04%, whereas system accuracy with just use the dominant point feature is 70.96%.

http://www.sersc.org/journals/IJSIA/vol8_no1_2014/6.pdf

An Improved Dominant Point Feature for Online Signature Verification

Among the biometric characteristic, signature forgery is the easiest way to do. Possibility
of signature forgery similarity might be reached perfectly. This paper introduced a new
technique to improve dominant point feature system based on its location for online signature
verification. Dynamic Time Warping is used to match two signature features vector. The
performance of system is tested by using 50 participants. Based on simulation result, system
accuracy without presence of the simple and trained impostors is 99.65% with rejection error
is 0% and acceptance error is 0.35%. While the current systems are faced with the simple and
trained impostors, system accuracy became 91.04% with rejection error is 1.6% and an
average of acceptance error is 7.36% with details as follows; acceptance error is 0.08%,
acceptance error of simple impostors is 4.4%, and acceptance error of trained impostors is
17.6%.The improved feature within fusion is produce better accuracy significantly than
dominant point feature. Accuracy of the improved feature within fusion is 91.04%, whereas
system accuracy with just use the dominant point feature is 70.96%.

Peer Review Karya Ilmiah Jurnal dengan judul: An Improved Dominant Point Feature for Online Signature Verification

Driven by new applications running on Tablet PC, a new pattern descriptor was proposed for retrieval of on-line Chinese scripts. The descriptor is based on Attributed Relational Graph (ARG). Fuzzy description is employed to enhance the adaptability of this model. To simplify the matching, the graph model is transformed to statistical features. Another improvement is that the descriptor is rotation-invariant. The experimental results show that this descriptor is effective for rotation-invariant retrieval of characters in regular style.

Retrieving On-line Chinese Scripts with an Invariant Structural Descriptor

We proposed a new dominant point detection method which has the following advantages: robust, computational efficient, and real-time response to pen movement. We construct a variable which is the ratio of the height to the width of an imagined rectangle whose bottom coincides with the polygon enclosed by the pen movement trace, and the area is equal to the polygonal area. While online watching whether the value of this variable exceeds a given threshold, one can find dominant points in real-time. Only when the fluctuation comparing to the scale of a curve is big enough, value of this variable can exceed the given threshold. By this way, pseudo turning points can be rejected. As a new point comes in, only a small number of computations are needed to update the value of this variable. Effectiveness of this method was confirmed by experiments.

Su Yang

Papers

Detecting dominant points on online scripts with a simple approach