基於局部二值模式與模板配對之指拼法辨識設計

Abstract

指拼法辨識是近年來被廣泛應用於人機互動的一種辨識系統。本論文提出一個以色彩深度影像為基礎的指拼法辨識系統，分為手掌區域偵測、特徵擷取及指拼法辨識三個部分。首先利用深度資訊切割手部範圍與背景，將切割完的手部資訊做進一步的手掌區域擷取；接著提出以局部二質化模式處理手掌區域之灰階影像，產生手勢紋理特徵，其後再搭配主成分分析把資料從原本的大維度降維到小維度，降維的目的為有利於資料分析和減少計算時間。最後，先利用間隙統計決定各個手勢的模板數量以及利用K值平均分類方法產生模板，再使用模板配對的方式做為系統分類器。從實驗結果可知，本論文所提出的搭配簡單的特徵擷取方式與非監督式分類器所達到的辨識率可達九成八以上之辨識率。

Finger spelling recognition is a popular communication way for Human-Computer Interaction (HCI). This thesis proposes a finger spelling recognition system with high accuracy rate based on RGB-D image. The system is divided into three main parts, including hand region detection, feature extraction, and finger spelling recognition. For the hand region detection, first, utilize depth information to distinguish the hand region and background and then extract the palm region. Further, use texture operator Local Binary Pattern to extract image feature. After getting the feature, use Principal Component Analysis to reduce data dimension and decrease computational time. Finally, decide the number of templates by Gap Statistic, find the template using K-means Clustering, and classify data with Template Matching Method. The experimental results show that the combination of simple feature extraction method and unsupervised classifier has the accuracy higher than 98% in finger spelling recognition.