A Study On Layout Analysis Method Of Complex Structure Name Cards Recognition

With the rapid development of image processing technology more and more application are using image-processing based software in their specific field. Many companies have developed a lot of products with Image-Processing application. In nowadays name cards are more and more important in now daily life. But in most time, it's very boring and slow to input the information of name card to digital device manually. We must input the name, position, telephone number, and other information. We must modify if we input it as error; We must find the record when we use it and store it after we input. So many things are not funny to us.The function of the name card recognition is promoted specially for the business man, it has exempted a name card manual input contact person name material and the telephone trouble and it saves the time and makes the enhancement working efficiency.To carry out the character recognition based on the photographic picture signal, there are many different aspects aimed at different applied methods. But it can be divided into several parts totally: image acquisition, image pre-processing, layout analysis and character recognition.The layout analysis module is the pre-processing part of the optical character recognition system. The accuracy of layout analysis directly affects the degree of automation of OCR. In this paper, according to name cards layout with complex structure, here presents a layout analysis method based on projections combined with connected domain, thus so it is realized for analyzing general kinds of name cards'binary images either in pictures or in texts. The results of experiments show that this method is suitable for analyzing general kinds of images of Chinese and Western language documents.