在資訊科技爆炸的時代，所有的資料都要求能數位化，以便利用資訊科技對數位資料進行分析、整理與應用。對於都市規劃而言，建立數位城市模型即成為目前的重要課題之一。 建立數位城市模型中間最困難的步驟之一，在於處理並數位化古老的紙本地籍資料與建築物平面圖或手繪建築物之地圖，然後進行資訊整合，以建立基本的城市三度空間模型，進而利用更精準的測量技術，來建立精確的數位城市模型。然而要以人工處理並將上述資料數位化來製作基本的三度空間模型，秏時費工且成本太高。有鑑於此，本篇論文提出一套自動化的處理方法，針對附有樓層高度的紙本建築地圖或手繪地圖進行自動化處理，從而建立基本的三度空間模型，作為建立數位城市模型的初步處理。 我們先利用文字辨識的技術對建築物進行分析、擷取並判斷地圖中屬於建築物高度的文字資料。其次利用不同的演算法，對地圖進行細化及骨架粹取，並找出地圖上組成建築物的關鍵節點，然後對節點分群，以區分並判斷不同的建築物，進而建立地圖上各個建築物的平面模型圖。最後將每棟建築物的高度資料及其相對應的平面模型圖加以整合，自動產生該地圖的三度空間模型。 我們隨機選取一張台北地區之建築平面圖以及學校平面圖來檢驗我們提出的方法，測試的結果顯示，我們的方法都能成功的將這些平面圖，自動建立出原圖基本的三度空間模型，可以作為未來建立城市數位模型之參考。 / In the era of information explosion, digital archiving every piece of information becomes a must in order to organize, process, and analyze this information and make further use of the information. Hence, constructing a cyber city model is one of the major issues in urban planning. One of the most difficult steps in constructing a cyber city model is to process and digitize the ancient cadastral information as well as the architecture sketches or the hand drawing maps. By combining this information, we could construct an early stage three dimensional model for the city that would help us in constructing the final model for the cyber city. However, manually processing this information is not cost effectively and automatic processing them might reduce the construction cost dramatically. In this paper, we propose an automatic processing mechanism that could digitize the architecture sketches or the hand drawing maps automatically. Our mechanism will produce an early stage three dimensional model for the specified area that will eventually lead to the construction of a more accurate three dimensional model for the entire city. After the sketches or the maps were scanned, as bitmap images, into the computer, we start with analyzing the architecture sketches and extract the elevation information using traditional methods of character recognition. Then, we use various algorithms to thinning and to extract the skeleton of the image. The critical nodes of each building in the images were identified, isolated, and used to construct the base of each building in a planar diagram. Finally, the elevation information is used along with the planar diagram just constructed to generate an early stage three dimension model for the specified area. We randomly choose an architecture sketch of Taipei City and our campus map to verify our mechanism. The results show that our method could produce the corresponding three dimensional models successfully. These models could be used and help us to construct a more accurate three dimensional model for the entire city.

智慧型手機的用途已從語音溝通延伸轉變為多功能導向的的生活工具。目 前多數的智慧型手機均具備攝影鏡頭,而此模組更已被公認為基本的標準 配備。使用者透過手機,可以輕易且自然地拍攝感興趣的物體、景色或文 字等,並且建立屬於自己的影像資料庫。在眾多的手機軟體中,旅遊類的 程式是其中一種常見整合內容與多項感測模組的應用實例。在行動平台上, 設計一個影像辨識系統服務可以大幅地協助遊客們在旅途中去瞭解、認識 知名的地標、建築物、或別具意義的物體與文字等。 然而在行動平台上的可用資源是有限的,因此想要在行動平台上開發有效 率的影像辨識系統,是頗具挑戰性的任務。如何在準確率與計算成本之間 取得最佳的平衡點往往是行動平台上開發影像辨識技術的最重要課題。 根據上述的目標,本研究擬於行動平台上設計、開發行動影像搜尋與智慧 型文字辨識系統。具體而言,我們將在影像搜尋上整合兩個全域的特徵描 述子,並針對印刷與手寫字體去開發智慧型文字辨識系統。實驗結果顯示, 在行動影像搜尋與文字辨識的效能測試部分,前三名的辨識率皆可達到的 80%。 / The roles of smart phones have extended from simple voice communications to multi-purpose applications. Smart phone equipped with miniaturized image capturing modules are now considered standard. Users can easily take pictures of interested objects, scenes or texts, and build their own image database. Travel-type mobile app is one example that takes advantage of the array of sensors on the device. A mobile image search engine can bring much convenience to tourists when they want to retrieve information regarding specific landmarks, buildings, or other objects. However, devising an effective image recognition system for smart phone is a quite challenging task due to the complexity of image search and pattern recognition algorithms. Image recognition techniques that strike a balance between accuracy and efficiency need to be developed to cope with limited resources on mobile platforms. Toward the above goal, this thesis seeks to design effective mobile visual search and intelligent character recognition systems on mobile platforms. Specifically, we propose two global feature descriptors for efficient image search. We also develop an intelligent character recognition engine that can handle both printed and handwritten texts. Experimental results show that the accuracy reaches 80% for top-3 candidates in visual search and intelligent character recognition tasks.

本論文使用非監督式新細胞認知機（Unsupervised neocognitron）神經網路來便是印刷體中文字。 關於非監督式新細胞認知機，本論文提出兩項修改。第一項，Us1子層的結點不進行學習，而是直接套用人為方式所指定的12個區域特徵，而Us1之後的S子層仍然使用非監督式學習的方式決定其所要偵測的區域特徵。第二項修改則是，在學習過中設定一個上限值來限制代表節點（representative）產生的個數。如此設計的目的是為了避免模板（cell-planes）分配不均的問題。在本研究，採用這兩項修改的新細胞認知機稱為模式一，而使用第二項修改的新細胞認知機稱為模式二。 本論文裡的所有實驗分為兩部分。在第一部分有四個實驗，這些實驗都使用相同的訓練範例與測試範例。訓練範例有兩組，第一組包含“川”,“三”,“大”,“人”,“台”等五個中文字。而第二組包含“零”,“壹”,“貳”,“參”,“肆”等中文字。訓練範例都市採用細明體，而測試範例則是採用其他九種不同字體。第一個實驗的主要目的是測試模式一的績效。實驗結果顯示，模式一很容易學習成功而且辨識率可以接受。另外三個實驗的目的是想要了解某些參數值與系統績效的關係。這些參數包含S-欄的大小（the size of S-column），模板樹（the number of cell-planes），以及節點的接收場大小（the size of cells’ receptive field）。這三個實驗所使用的網路系統是模式一。 第二部分有二個實驗，主要的目的是比較模式一與模式二的系統績效。在第一個實驗，所使用的訓練範例與第一部分實驗相同。實驗結果顯示模式一比較容易成功地學習，而且系統有不錯的表現。第二個實驗，使用17個中文字做為訓練範例。這17個字包括“零”,“壹”,“貳”,“參”,“肆”,“伍”,“陸”,“柒”,“捌”,“玖”,“拾”,“佰”,“仟”,“萬”,“億”,“圓”,“角”。實驗結果顯示，模式一仍然是一個不錯的系統。 / In this study, we are investigating the feasibility of applying the unsupervised neocognitron to the recognition of printed Chinese characters. Two propositions for the unsupervised neocognitron are mentioned. The first on proposes that the input connections of the first layer are manually given, and all subsequent layers are trained unsupervised. The second one concerns the selection of representatives. During the process of learning, the number of cell-planes that send representatives for each training pattern has an upper bound. The unsupervised neocognitron with implementing these two propositions is named as Model 1, and the unsupervised neocognitron with implementing only the second proposition is named as Model 2. Experiment in this study are grouped into two parts, called Part I and Part II. In Part I, four experiments are conducted. For each experiment, two sets of training patterns will be conducted respectively. The first one, called the simple training set, consists of five printed Chinese characters“川”,“三”,“大”,“人”, and “台” with size of 25*25 in MingLight font. The second one, called the complex training set, contains another five printed Chinese characters“零”,“壹”,“貳”,“參”, and “肆” in the some font and size. After training, these characters of other nine different fonts are presented to test the generalization of the network. The objective of the first experiment of Part I is to investigate the performance of Model 1. Simulation results shot that Model 1 demonstrates a good ability to achieve a successful learning. In other three experiments, the effect of choosing different value for some parameters in investigated. The parameters include the size of S-column, the number of cell-planes, and the receptive field of cells. In Part II, a comparison of the performance of Model 1 and Model 2 is made. In the first experiment, Model 1 and Model 2 are trained to recognize the simple and complex training sets described above. Experimental results show that Model 1 shows higher ability to achieve a successful learning, and performance of Model 1 is acceptable. In the second experiment, 17 training patterns are presented during the learning process. These training patterns include “零”,“壹”,“貳”,“參”,“肆”,“伍”,“陸”,“柒”,“捌”,“玖”,“拾”,“佰”,“仟”,“萬”,“億”,“圓”,, and “角”. From the simulation results, Model 1 is a promising approach for the recognition of printed Chinese characters.