Application Research On Image Processing In Industrial And Commercial Enterprise Document Management Information System

With the development of techniques such as computer, communication and network, the management and utilization of government resource document are confronted with challenges and chances. Also more and more information systems whose main data are document images are used widely. But in the document image information systems now, there are some problems. These problems include the standard should be defined when document image is processing, the quality of document image should be enhanced more, and the size of document image should be compressed more. From the digitalization procedure of paper document to electronical document, we analyzed and summarized the attributes of AIC(Administrator of Industry and Commerce) document image. Then we present the researching results of slant correction, enhancement and binarization of document images. In the end, we introduce an actual document inquiring information system which these image processing techniques applied to.Document digitalization is the procedure of transferring paper entitative document to digital virtual document. It's the first job of constructing image information system. From the practical manufacture of digital document, we analyzed every digitalization step of documents such as AIC, Municipal Bureau of Land Resource and Housing Management. Furthermore, we could define the differences between the document image and the other natural images.Document digitalizing provides a method to utilize the archival resources of government comprehensively. Slant correction of digitalized document is necessary for the quality of digital image, and it's a preprocessing of any other procedure. By a Gaussian filter of multi-scale, the global structure of the original document image was enhanced. Based on gradients of enhanced image, a structural analysis tensor was defined also for the detection of line structure at the each pixel. For the line-likeness value at every pixel, which is greater than a given number, the corresponding angle was calculated. From the histogram of these angles, document skew could be determined. Our experiments show that the method we introduced is adaptive to various documents with rich text.Histogram equilibrium (HE) of image can extend the image's grey range. It's a classic and efficient method of image enhancement. But this method can blur image also, because of the algorithm is constructed by the basis of combination of similar grey pixels. Detail emphasized adaptive histogram equilibrium (DEAHE) has not only holding the advantage of HE--extend the grey range, but also amplifying image detail. Due to some noises were added to the images in the document digitalization procedure, so DEAHE amplified the noises simultaneously while it amplified the image detail. Therefore, we proposed an improved DEAHE method, called IAHE, to suppress noise, to amplify the image detail, and to adjust the grey range of the image. The experiments show that the IDEAHE method could improve the document image visually. It's an alternative method of image enhancement in digital document image producing.For the gray-level image of government document resource, a linear transform was employed to enhance the image contrast. A spatial filter was applied to bate image noise. Based on this preprocessing, the global threshold T2 was calculated by modified Otsu method. The threshold surface T1 was computed by Bernsen algorithm. On the basis of T1 and T2 , some thresholds such as the stroke breaking value T3 , the average value T4 of local processing window and the union value T5 between global and local were defined. Then the gray-level image was binarized through the combination of these five values. Our experiments show that the proposed method, based on the union of global and local threshold, is adaptive to various documents of government resource. It could achieve also our purpose of processing of image ghost and broke rupture.In the next chapter, we introduced an actual document information system which used these image processing techniques above. The system has two inquiring functions of document images mainly. One is inner local inquiring by C/S, another is outer long-distance inquiring by C/S/S. It produced good society benefit and great economic benefit. The content of this paper covers four parts. They are system requirement analysis, system design, system implementation and system test. The test and the use of the system show that the system is running steadily. It has friend interfaces and full functions. The image quality is compatible with the National rules and can satisfy the pratical needs of users. Moreover, the image accessing time is less than the system pre-defined time that most users inquire.Finally, we summarized our research work, simultaneously we pointed out what should we do in the future.