易於辨識的手勢之分析

Good Hand-Gestures to Recognize

鄧麒宏(Qi-Hong Deng)

指導教授 ： 陳煥宗

國立清華大學/電機資訊學院/資訊工程學系/碩士(2014年)

摘要

本論文研究的主題是人機互動中的手勢設計與分析。我們試圖去探討常用的手勢為何特別有效，並且嘗試找出其他也可能適合人機互動的手勢，這些較不常見的手勢，或許對於電腦來說，也能夠達到很高的辨識度。我們所採用的研究方法與步驟，是先發展出一套基於視覺化特徵的手勢辨識系統。利用這套手勢辨識系統，我們可以去判別哪些手勢對於電腦來說較容易辨識。我們採用合成的方式，透過調整手勢模型的關節參數，衍生出各種類型的手勢變化，並產生大量手勢影像作為訓練資料。經過訓練之後，能夠達到很高的辨識率的手勢，應該就是較適合被用來當作人機互動的手勢。此外，我們也將手勢的難易度納入考量，希望挑出對人來說比較好做的手勢。在實驗結果中，我們依序列出了一系列手勢，這些手勢不但有利於電腦進行辨識，對於使用者來說也可以輕易呈現，整體而言，應當是人機互動手勢的優先選擇。

關鍵字

手勢 ； 辨識

並列摘要

This thesis presents a line of study on finding good hand gestures for human-computer interaction. We aim to know why the frequently used hand gestures are effective and whether there are other good choices of hand gestures that might not be so obvious but actually are easy to recognize for the computers. Our approach is based on building a system for hand gesture classification. We generate a lot of training samples of synthesized hand gestures, and train a multiclass classifier to distinguish different gestures by their visual features. The gestures that are of high recognition accuracy can be considered as good candidates for the use in human-computer interaction. We also take into account the easiness of performing the gestures using a regression-based evaluation procedure. In the experimental results we show a ranking list of good gestures that are easy to recognize and easy to perform.

並列關鍵字

hand gestures ； recognize ； gestures

參考文獻

[1] Piotr Dollar, Ron Appel, Serge Belongie, and Pietro Perona. Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell., 36(8):1532–1545, 2014.

[4] Brendan J. Frey and Delbert Dueck. Clustering by passing messages between data points. Science, 315:2007, 2007.

[2] Piotr Dollar, Zhuowen Tu, Pietro Perona, and Serge Belongie. Integral channel features. In British Machine Vision Conference, BMVC 2009, London, UK, September 7-10, 2009. Proceedings, pages 1–11, 2009.

[3] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9:1871–1874, 2008.

[5] Marin Saric. Libhand: A library for hand articulation, 2011. Version 0.9.