使用卷積神經網路偵測街景文字圖案;Detecting Texts and Graphs in Street View Images by Convolutional Neural Networks

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/73009

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/73009

Title:	使用卷積神經網路偵測街景文字圖案;Detecting Texts and Graphs in Street View Images by Convolutional Neural Networks
Authors:	張瓊方;CHANG, CHIUNG-FANG
Contributors:	資訊工程學系
Keywords:	文字偵測;卷積神經網路;全卷積神經網路;最大極值穩定區域;text detection;convolution neural network;fully convolutional network;MSER
Date:	2017-01-23
Issue Date:	2017-05-05 17:38:25 (UTC+8)
Publisher:	國立中央大學
Abstract:	本論文提出於街景畫面中尋找文字與圖案的偵測機制，主要考量街景環境所拍攝的畫面常出現具識別性的人為標記，包括交通路牌與商家招牌，這些人造圖案提供了關於該影像的若干資訊，例如拍攝的所在位置與商家招牌的廣告效果等。然而，這類物件的多種圖案或形狀並不容易以固定的樣板予以分析，再加上街景影像常包含雜亂背景(建築、道路、林木等)，路/招牌在畫面中也可能重疊，或遭到街道中的其他物體遮蔽，而天候光線等因素也會影響偵測結果，這些因素都增加了偵測街景影像人為資訊的困難。我們所提出的偵測機制分成兩個部分，第一部分定位影像中之路牌及招牌所屬區域，我們採用基於全卷積網路(Fully Convolutional Network, FCN)分割技術，訓練街景路牌及招牌的偵測模型，以期迅速且有效地確認目標。第二部分則於該區域中擷取文字及商標，我們利用招牌及路牌的特性，即不論兩者形狀為何，通常都由一塊平滑區域組成背景，而文字及商標存在於其中。我們依據灰階梯度強度(Gradient Magnitude)，建構平滑區域圖，再根據第一部分所偵測的區域，以比對平滑區域的方式確認畫面中招牌的實際區域，根據文字與圖案的特性定義人為資訊位置機率圖。最後以適用於文本檢測的最大穩定極值區域 (Maximally Stable Extremal Regions,MSER)方法，從資訊位置機率大的區域中擷取文字及商標。實驗結果顯示本機制在各類複雜街景畫面中能有效取得文字與圖案，並依此探討FCN在此應用中的使用方式。;Considering that traffic and shop signs appearing in street view images contain useful information, such as locations of scenes or effects of advertising billboards, a text and graph detection mechanism in street view images is proposed in this research. Many of these artificial objects in street view images are not easy to extract with a fixed template. Besides, cluttered backgrounds containing such items as buildings or trees may block some parts of the signs, increasing the challenges of detection. Weather or light conditions further complicate the detection process. The proposed detection mechanism is divided into two parts; first, we use the Fully Convolutional Network (FCN) to train a detection model for effectively locating the positions of signs in street view images. In the second part, we extract the texts and graphs in the selected areas employing their characteristics. By observing that, regardless of various shapes, the texts/graphs are usually superimposed on smooth areas, we construct smooth-region maps according to the gradient magnitudes and then confirm the actual areas of signs. The texts and graphs can then be extracted by Maximally Stable Extremal Regions (MSER), which is suitable for text detection. Experimental results show that this mechanism can effectively extract texts and graphs in different types of complex street scenes.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	297	View/Open

社群 sharing

Loading...