本文選題：收件人地址塊定位 + BING�。� 參考：《華東師范大學(xué)》2017年碩士論文

【摘要】：郵件圖像的收件人地址塊定位作為郵政自動(dòng)化的第一步,是實(shí)現(xiàn)自動(dòng)分揀的先決條件。如何定位郵件圖像的收件人地址塊變成一個(gè)亟待解決的問(wèn)題。尤其是塑封郵件的背景復(fù)雜,使得針對(duì)塑封郵件圖像的收件人地址塊定位具有很大挑戰(zhàn)性。本文提出了一種塑封郵件圖像的收件人地址塊定位方法,研究了候選域提取、特征表示和特征匹配的方法。本文的主要工作包括:1.提出基于改進(jìn)BING模型的候選域提取方法。通過(guò)刻畫(huà)塑封郵件圖像中某塊區(qū)域的目標(biāo)顯著性水平,自適應(yīng)的產(chǎn)生一些高質(zhì)量的收件人地址塊候選域。該方法克服了滑動(dòng)窗口法無(wú)法適應(yīng)收件人地址塊尺寸變化的缺點(diǎn),能夠減少候選域的數(shù)目,降低塑封郵件圖像的搜索空間。2.提出采用稠密SIFT描述子對(duì)候選域進(jìn)行特征描述。在詞袋模型的基礎(chǔ)上引入金字塔匹配原理,將候選域進(jìn)行層級(jí)網(wǎng)格劃分,逐層基于視覺(jué)詞典對(duì)候選域的SIFT特征進(jìn)行重新表示。該方法考慮了候選域中的視覺(jué)單詞在不同空間位置上的分布情況,保留了候選域的空間布局信息,是對(duì)詞袋模型的一種有效擴(kuò)展。3.提出使用直方圖交叉核SVM對(duì)提取的特征進(jìn)行匹配。對(duì)候選域提取基于視覺(jué)詞典的金字塔視覺(jué)直方圖,將直方圖作為特征向量輸入到訓(xùn)練好的SVM模型中,得到每個(gè)候選域的概率。因?yàn)閱蝹€(gè)候選域無(wú)法完全覆蓋收件人地址塊,并且候選域與候選域之間有重疊,所以合并概率最高的前五個(gè)候選域,為最終提取收件人地址塊的文字區(qū)域提供基礎(chǔ)。我們?cè)谏虾｀]政科學(xué)研究院提供的塑封郵件圖像庫(kù)上進(jìn)行了實(shí)驗(yàn),并對(duì)本文方法和對(duì)比方法的數(shù)據(jù)進(jìn)行了分析。實(shí)驗(yàn)數(shù)據(jù)顯示本文方法取得了較好的結(jié)果,可以有效定位出塑封郵件圖像的收件人地址塊。
[Abstract]:As the first step of postal automation, the location of recipient address block of mail image is the precondition of automatic sorting. How to locate the recipient address block of mail image becomes an urgent problem. Especially, the background of plastic mail is very complicated, which makes it challenging to locate the recipient address block of plastic mail image. In this paper, a method of location of addressee address block in plastic mail image is proposed, and the methods of candidate domain extraction, feature representation and feature matching are studied. The main work of this paper includes: 1. A candidate domain extraction method based on improved BING model is proposed. By characterizing the target significance level of a certain area in a plastic mail image, some candidate domains of high quality addressee address blocks are generated adaptively. This method overcomes the shortcoming that the sliding window method can not adapt to the size change of addressee address block and can reduce the number of candidate fields and the search space of plastic mail image. A dense SIFT descriptor is proposed to describe candidate domains. Based on the lexical bag model, the pyramid matching principle is introduced, the candidate fields are divided into hierarchical grids, and the SIFT features of the candidate domains are re-represented layer by layer based on visual dictionaries. This method takes into account the distribution of visual words in candidate domains in different spatial locations and retains the spatial layout information of candidate domains. It is an effective extension of the word bag model. A histogram cross kernel SVM is proposed to match the extracted features. The pyramid visual histogram based on visual dictionary is extracted from candidate domain and the histogram is input into the trained SVM model as feature vector to obtain the probability of each candidate domain. Because a single candidate domain can not completely cover the addressee address block and there is overlap between the candidate domain and the candidate domain, the first five candidate domains with the highest merging probability provide the basis for the final extraction of the text area of the recipient address block. We have carried out experiments on the plastic mail image library provided by Shanghai Postal Science Research Institute, and analyzed the data of our method and comparison method. The experimental data show that the proposed method can effectively locate the recipient address block of the plastic mail image.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：F250;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 程美玲;張漢超;續(xù)晉華;;基于視覺(jué)顯著性的信封地址塊定位方法[J];計(jì)算機(jī)工程;2015年11期

2 薛君良,丁曉青,劉長(zhǎng)松,潘世言,錢(qián)偉威;中文手寫(xiě)信封目的地址塊的定位[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2000年01期

相關(guān)碩士學(xué)位論文 前2條

1 閆錫鵬;快遞郵件分揀條形碼圖像分析[D];華東理工大學(xué);2014年

2 諶微微;不同分揀模式下卷煙配送中心分揀成本控制研究[D];重慶交通大學(xué);2011年

，

本文編號(hào)：1796591