文字辨識為常見的電腦視覺應用之一，隨著正確率逐漸的上升，許多新的服務相繼出現，本論文改善了筆記管理軟體最主要的問題－文字切割，並提出兩種新的中文印刷體及手寫體的分類方法。我們將筆記文件中較常見的重點標記過濾後，再使用新核心的文字結構濾波取得筆記文件中的文字區塊，新的核心數據大幅降低原始核心的計算時間。本論文也使用文字結構濾波作為分辨印刷體、手寫體的特徵值，由於文字結構濾波會依據筆畫結構給予能量回饋，使得較工整的印刷體與手寫體能有所區別，此外也使用Sobel搭配不同角度範圍進行字體辨識，實驗結果證實了本論文所提出的文字切割及字體分類方法對於筆記文件資訊的處理是有效的。 / Character recognition is an important and practical application of computer vision. With the advance of this technology, more and more services embedding text recognition functionality have become available. However, segmentation is still the central issue in many situations. In this thesis, we tackle the character segmentation problem in note taking and management applications. We propose novel methods for the discrimination of handwritten and machine-printed Chinese characters. First, we perform noise removal using heuristics and apply a stroke filter with modified kernels to efficiently compute the bounding box for the text area. The responses of the stroke filter also serve as clues for differentiating machine-printed and handwritten texts. They are further enhanced using a SVM-based classifier that employs aggregated directional responses of edge detectors as input. Experiment results have validated the efficacy of the proposed approaches in terms of text localization and style recognition.

本文以賓組的卜旬卜辭作為論題。先就卜辭的字體與句式兩部份做分類與整理，接著討論其驗辭的內容與所載貞人之關係，最後綜合討論以上成果。 　　第一章「緒論」說明研究動機與方法，以及目前學者和卜辭字體類型相關及卜旬卜辭驗辭內容相關的研究成果。第二章整理賓組卜旬卜辭的句式與字體，並嘗試透過整理成果來回應前輩學者的分期之說。第三章至第四章討論賓組卜旬卜辭的驗辭內容，並與字體整理成果對照研究。第五章主要整理於賓組中曾參與卜旬貞問的貞人，並觀察與之配合的字體類型，藉此排列出貞人間的相對時序。第六章則概述前述四章的研究成果，並說明本文透過賓組卜旬卜辭研究所得的結論。 / The purpose of this thesis is to study the content of Oracle Bone Script, constrained in Bu-Xun(卜旬),the record of the ancient psychic augury every half-decade, of Collection Bin(賓組). We carefully assorted all the pieces available by its ways of writing and its exterior forms in this range. Later, we present the connection between Zen-Ren(貞人) the ancient official psychics and Yen-Tzu(驗辭) of certain augury of Bu-Xun of Oracle Bone Scripts which note whether the prediction was found to be true or false. In chapter one we explain the research methods used and the context of the study. In the second chapter, text of Bu-Xun in the Oracle Bone Scripts assorted by its form and font will respond to predecessors’ assortments which have been a controversy between the researchers. In chapter three and four we further study the retained Yen-Tzu, the proven and disproven notes engraved on, of the text on Bu-Xun in Collection Bin, and then figuring out the correlation between the content of it and our assortment. In the fifth chapter, in the study of known psychics, we further discover a new chronological order by pointing out the relations between the specific font and the names of these official psychics The final chapter summarizes the four chapters above, and concluded the result of our research on Bu-xun Oracle Bone scripts in the large Collection Bin and explained how this study develop the field of research.