We describe the design and evaluation of CamWorks, a system that employs a video camera as a means of supporting capture from paper sources during reading and writing. The user can view a live video image of the source document alongside the electronic document in preparation. We describe a novel user interface developed to support selection of text in the video window, and several new techniques for segmentation, restoration and resolution enhancement of camera images. An evaluation shows substantially faster text capture than with flatbed scanning. Keywords Advanced man-machine interfacing, image processing. Introduction One of the benefits offered by information technology is its capacity to convert information from one medium to another ? live video to static images, page images to coded text, text to synthesized speech, and so on. This capability, achieved with the aid of technologies such as optical character recognition (OCR), enables the user to work in the medium best suit...

The nearest-neighbor based document skew detection methods do not require the presence of a predominant text area, and are not subject to skew angle limitation. However, the accuracy of these methods is not perfect in general. In this paper, we present an improved nearest-neighbor based approach to perform accurate document skew estimation. Size restriction is introduced to the detection of nearest-neighbor pairs. Then the chains with a largest possible number of nearest-neighbor pairs are selected, and their slopes are computed to give the skew angle of document image. Experimental results on various types of documents containing different linguistic scripts and diverse layouts show that the proposed approach has achieved an improved accuracy for estimating document image skew angle and has an advantage of being language independent.

The existing skew estimation techniques usually assume that the input image is of high resolution and that the detectable angle range is limited. We present a more generic solution for this task that overcomes these restrictions. Our method is based on determination of the first eigenvector of the data covariance matrix. The solution comprises image resolution reduction, connected component analysis, component classification using a fuzzy approach, and skew estimation. Experiments on a large set of various document images and performance comparison with two Hough transformbased methods show a good accuracy and robustness for our method.

A system has been built that selects excerpts from a scanned document for presentation as a summary, without using character recognition. The method relies on the idea that the most significant sentences in a document contain words that are both specific to the document and have a relatively highfrequency of occurrence within it. Accordingly, and entirely within the image domain, each page image is deskewed and the text regions of are found and extracted as a set of textblocks. Blocks with font size near the median for the document are selected and then placed in reading order. The textlines and words are segmented, and the words are placed into equivalence classes of similar shape. The sentences are identified by finding baselines for each line of text and analyzing the size and location of the connected components relative to the baseline. Scores can then be given to each word, depending on its shape and frequency of occurrence, and to each sentence, depending on the scores for the words in the sentence. Other salient features, such as textblocks that have a large font or are likely to contain an abstract, can also be used to select image parts that are likely to be thematically relevant. The method has been applied to a variety of documents, including articles scanned from magazines and technical journals. Keywords: image analysis, image segmentation, page segmentation, classification, document image summarization, image morphology, logical analysis, information retrieval 1

In this paper, we propose a method of text retrieval from document images using a similarity measure based on an N-Gram algorithm. We directly extract image features instead of using optical character recognition. Character image objects are extracted from document images based on connected components first and then an unsupervised classifier is used to classify these objects. All objects are encoded according to one unified class set and each document image is represented by one stream of object codes. Next, we retrieve N-Gram slices from these streams and build document vectors. Lastly, we obtain the pair-wise similarity of document images by means of the scalar product of the document vectors. Four copora of news articles were used to test the validity of our method. During the test, the similarity of document images using this method was compared with the result of ASCII version of those documents based on the N-Gram algorithm for text documents.

A new method for registering forms has been developed at the National Institute of Standards and Technology. This method automatically estimates the amount of rotation and translation in the image without any detailed knowledge of the form. This is accomplished through the automatic detection of dominant vertical and horizontal structures (lines) commonly found in forms. A general method for rotation estimation and a robust method for translation estimation are presented. Results demonstrate that this technique is extremely tolerant to spurious annotations on the form and scanner noise in the image, and the computational requirements of the utility can be tuned by optionally choosing to process and analyze downsampled versions of the image. All 3,669 Handwriting Sample Forms distributed with NIST Special Database 19 were successfully registered with the new technique, and using the same code, 255 uniformly laid out IRS tax forms and 500 Census miniforms were also tested and registered....

We propose a concise definition of the skew angle of document, based on mathematical morphology. This definition has the advantages to be applicable both for binary and grey-scale images. We then discuss various possible implementations of this definition, and show that results we obtain are comparable to those of other existing algorithms.

In order to capture the content of an imaged document but avoid the time-consuming full-scale OCR which is fragile to handle touching characters, a fast and segmentationfree keyword spotting method is proposed in this paper. The keyword spotting method is based on word shape coding technique. The proposed coding scheme has little ambiguity, and can be swiftly executed. It is a promising technique to boost better document image retrieval. The strength of the proposed method is demonstrated in a document filtering experiment. The experimental results show that document filtering based on the proposed method is more than 20 times faster than the one based on OCR, and has comparable filtering accuracy. 1.

A common authoring technique involves making annotations on a printed draft and then typing the corrections into a computer at a later date. In this paper, we describe a system that goes some way towards automating this process. The author simply passes the annotated documents through a sheetfeed scanner and then brings up the electronic document in a text editor. The system then works out where the annotated words are and allows the author to skip from one annotation to the next at the touch of a key. At the heart of the system lies a procedure for reliably establishing correspondences between printed words and their electronic counterparts, without performing optical character recognition. This procedure might have interesting applications in document database retrieval, since it allows an electronic document to be indexed by a printed version of itself.

quality assurance, document image analysis, OCR, digital library Quality assurance (QA) plays a critical role in high volume document digitization projects by making sure that the specified quality standard is reached under cost and time constraints. This paper takes a systematic view on this issue by summarizing and abstracting related existing work: quality bottlenecks and technical solutions throughout the whole processing pipeline, including cataloging, capture, image analysis and recognition, and error cascading; various strategies to conduct costeffective QA, such as combination of auto-QA and manual QA, batch QA, special QA user interface, and open source QA.