指尖手寫軌跡的字形辨識

Alphanumeric Shape Recognition of Fingertip Writing Trajectory

林瑞堂(Ruei-Tang Lin)

指導教授 ： 吳明芳

崑山科技大學/工程學院/電機工程研究所/碩士(2009年)

https://doi.org/10.6828/KSU.2009.00011

摘要

摘要:本論文目的在發展一套手寫文字辨識系統。此系統以網路攝影機為輸入裝置，以偵測指尖手寫軌跡並進行軌跡識別。本文中提出一種新的指尖辨識方法，針對指尖位置通常於手部區塊外框之特性，進行指尖搜尋，再配合設定條件以進行指尖位置判定。
本文的辨識系統分為兩階段，第一階段為指尖軌跡紀錄，流程為當畫面輸入系統之後，會先進行前處理、手部位置辨識，再進行指尖位置辨識以利指尖軌跡追蹤及記錄，並於紀錄指尖軌跡之後進入字形辨識階段，此階段會先對軌跡進行前處理，並擷取特徵以進行文字辨識。實驗結果顯示系統可以順利的對指尖進行追蹤，對於文字辨識方面亦有滿高的成功率。

關鍵字

指尖 ； 追蹤 ； 軌跡 ； 字形 ； 辨識

並列摘要

Abstract:The purpose of this thesis is to develop a recognition system of handwriting letter. This system uses web camera as the input device, and discriminates the alphanumeric shape after detecting out the trajectory of handwriting. This research presents a new method of fingertip identification. In the method, the fingertip is found out by the characteristic that the position of fingertip is usually on the external frame of hand block, and the position of fingertip can be determined according to the established conditions in this thesis.
The identification system of this article divides into two stages. The first stage is the fingertip trajectory record. In this stage, after video frames input the system, the image processing of each frame and the identification of hand position are proceeded, and then the position of fingertip is determined so that we can track and record the trajectory of fingertip. The second stage is the recognition of alphanumeric shape. In this stage, we do the front disposal of trajectory and then extract features of the trajectory for the recognition of alphanumeric shape. The outcome of the experiment shows that the system can track on the fingertip smoothly, and it also has high success rate on the identification of alphanumeric shape.

並列關鍵字

fingertip ； tracking ； trajectory ； alphanumeric shape ； recognition

參考文獻

[1] 洪兆欣，以軌跡辨識為基礎之手勢辨識系統，國立中央大學資訊工程研究所碩士論文，民國95年。

[2] K. Oka, Y. Sato, and H. Koike,“Real-time fingertip tracking and gesture recognition,”Computer Graphics and Applications, IEEE, Vol. 22, Issue 6, pp. 64-71, 2002,.

[5] K.Oka, Y. Sato, H. Koike, “Real-time Tracking of Multiple Fingertips and Gesture Recognition for Augmented Desk Interface Systems”, Automatic Face and Gesture Recognition, IEEE, pp.429-434, May 2002.

[6] L .Rabiner, B .Juang, “An introduction to hidden markov models,” ASSP Magazine of the IEEE, Vol. 3, Issue 1, pp. 4-16, 1986.

[7] L .R .Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition", Proceedings of the IEEE, Vol. 77, Issue 2, pp.257-286, Feb. 1989.