Edge-based connected component approach for skew correction of complex document images

Skew correction of complex document images is a difficult task. We propose an edge-based connected component approach for robust skew correction of documents with complex layout and content. The algorithm essentially consists of two steps - an 'initialization' step to determine the image orientation from the centroids of the connected components and a 'search' step to find the actual skew of the image. During initialization, we choose two different sets of points regularly spaced across the the image, one from the left to right and the other from top to bottom. The image orientation is determined from the slope between the two succesive nearest neighbors of each of the points in the chosen set. The search step finds succesive nearest neighbors that satisfy the parameters obtained in the initialization step. The final skew is determined from the slopes obtained in the 'search' step. Unlike other connected component based methods, the proposed method does not require any binarization step that generally precedes connected component analysis. The method works well for scanned documents with complex layout of any skew with a precision of 0.5 degrees.

Entropy based Skew correction of document images

The document images that are fed into an Optical Character Recognition system, might be skewed. This could be due to improper feeding of the document into the scanner or may be due to a faulty scanner. In this paper, we propose a skew detection and correction method for document images. We make use of the inherent randomness in the Horizontal Projection profiles of a text block image, as the skew of the image varies. The proposed algorithm has proved to be very robust and time efficient. The entire process takes less than a second on a 2.4 GHz Pentium IV PC.

Place categorization and semantic mapping on a mobile robot

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot with-out environment-specific training. Motivated by their ongoing success in various visual recognition tasks, we build our system upon a state-of-the-art convolutional network. We overcome its closed-set limitations by complementing the network with a series of one-vs-all classifiers that can learn to recognize new semantic classes online. Prior domain knowledge is incorporated by embedding the classification system into a Bayesian filter framework that also ensures temporal coherence. We evaluate the classification accuracy of the system on a robot that maps a variety of places on our campus in real-time. We show how semantic information can boost robotic object detection performance and how the semantic map can be used to modulate the robot’s behaviour during navigation tasks. The system is made available to the community as a ROS module.

HALLINNONTASOJEN VÄLINEN DIALOGI JA ERITYISOPETUKSEN MUUTOS BYROKRAATTISENA INSTITUUTIONA : - Kymppikuntien loppuraportin ja Erityisopetuksen strategian sisällönanalyyttinen vertailu

The rise of Special education numbers in Finland has caused a situation where Finland s ten largest LEA s so called kymppikunnat (ten communes) have expressed their growing concern of organizing the special education in the current institutional settings. The LEA s started the conversation of redefining special education system in 2004. Their aim was to target the governments attention to the problematics of special education. By the request of the Ministry of Education the LEA s prepared a final report concerning the central questions in the Finnish special education system. On the basis of the LEA s survey it became even clearer that the legislation, funding system and curriculum are tightly linked together. The following LEA s took part into the writing process Espoo, Helsinki, Jyväskylä, Kuopio, Lahti, Lappeenranta, Tampere, Turku and Vantaa. The report was hand over to the Ministry of Education at 18.8.2006. After the delivery the Ministry organized special education development group meetings 17 times in the year 2007. The result of the LEA s report and the development meetings was a new Special Education Strategy 2007. I am observing the dialogue between administrational levels in governmental institutions change process. The research is a content analysis where I compare the Erityistä tukea tarvitsevan oppilaan opetuksen järjestämisen uudistaminen osana yhtenäistä perusopetusta- kohti laatua ja joustavuutta (The renewal of the organization of teaching for student with special educational needs as part of unified education for all - towards quality and flexibility) document to Erityisopetuksen strategia (Special education strategy) document. My aim was to find out how much of their own interests have the LEA s been able to integrate into the official governmental documentation. The data has been organized and analyzed quantitatively with Macros created as additional parts in Microsoft Excel software. The document material has also been arranged manually on sentence based categorization into an Excel matrix. The results have been theoretically viewed from the special education reform dialogue perspective, and from the angle of the change process of a bureaucratic institution. My target has been to provide a new viewpoint to the change of special education system as a bureaucratic institution. The education system has traditionally been understood as a machine bureaucracy. By the review provided in my pro gradu analysis it seems however that the administrational system in special education is more of a postmodern network bureaucracy than machine bureaucracy. The system appears to be constructed by overlapping, crossing and complex networks where things are been decided. These kinds of networks are called "governance networks . It seems that the governmental administrational - and politic levels, the third sector actors and other society s operators are mixed in decision making.

Electronic Document Management in Construction – Research Issue and Results

Electronic document management (EDM) technology has the potential to enhance the information management in construction projects considerably, without radical changes to current practice. Over the past fifteen years this topic has been overshadowed by building product modelling in the construction IT research world, but at present EDM is quickly being introduced in practice, in particular in bigger projects. Often this is done in the form of third party services available over the World Wide Web. In the paper, a typology of research questions and methods is presented, which can be used to position the individual research efforts which are surveyed in the paper. Questions dealt with include: What features should EMD systems have? How much are they used? Are there benefits from use and how should these be measured? What are the barriers to wide-spread adoption? Which technical questions need to be solved? Is there scope for standardisation? How will the market for such systems evolve?

Use of Document Management Systems - a Case Study of the Finnish Construction Industry

Triggered by the very quick proliferation of Internet connectivity, electronic document management (EDM) systems are now rapidly being adopted for managing the documentation that is produced and exchanged in construction projects. Nevertheless there are still substantial barriers to the efficient use of such systems, mainly of a psychological nature and related to insufficient training. This paper presents the results of empirical studies carried out during 2002 concerning the current usage of EDM systems in the Finnish construction industry. The studies employed three different methods in order to provide a multifaceted view of the problem area, both on the industry and individual project level. In order to provide an accurate measurement of overall usage volume in the industry as a whole telephone interviews with key personnel from 100 randomly chosen construction projects were conducted. The interviews showed that while around 1/3 of big projects already have adopted the use of EDM, very few small projects have adopted this technology. The barriers to introduction were investigated through interviews with representatives for half a dozen of providers of systems and ASP-services. These interviews shed a lot of light on the dynamics of the market for this type of services and illustrated the diversity of business strategies adopted by vendors. In the final study log files from a project which had used an EDM system were analysed in order to determine usage patterns. The results illustrated that use is yet incomplete in coverage and that only a part of the individuals involved in the project used the system efficiently, either as information producers or consumers. The study also provided feedback on the usefulness of the log files.

Automatic text block separation in document images

Separation of printed text blocks from the non-text areas, containing signatures, handwritten text, logos and other such symbols, is a necessary first step for an OCR involving printed text recognition. In the present work, we compare the efficacy of some feature-classifier combinations to carry out this separation task. We have selected length-nomalized horizontal projection profile (HPP) as the starting point of such a separation task. This is with the assumption that the printed text blocks contain lines of text which generate HPP's with some regularity. Such an assumption is demonstrated to be valid. Our features are the HPP and its two transformed versions, namely, eigen and Fisher profiles. Four well known classifiers, namely, Nearest neighbor, Linear discriminant function, SVM's and artificial neural networks have been considered and efficiency of the combination of these classifiers with the above features is compared. A sequential floating feature selection technique has been adopted to enhance the efficiency of this separation task. The results give an average accuracy of about 96.

Document page layout analysis using Harris corner points

Extraction of text areas from the document images with complex content and layout is one of the challenging tasks. Few texture based techniques have already been proposed for extraction of such text blocks. Most of such techniques are greedy for computation time and hence are far from being realizable for real time implementation. In this work, we propose a modification to two of the existing texture based techniques to reduce the computation. This is accomplished with Harris corner detectors. The efficiency of these two textures based algorithms, one based on Gabor filters and other on log-polar wavelet signature, are compared. A combination of Gabor feature based texture classification performed on a smaller set of Harris corner detected points is observed to deliver the accuracy and efficiency.

Similarity relations in visual search predict rapid visual categorization

How do we perform rapid visual categorization?It is widely thought that categorization involves evaluating the similarity of an object to other category items, but the underlying features and similarity relations remain unknown. Here, we hypothesized that categorization performance is based on perceived similarity relations between items within and outside the category. To this end, we measured the categorization performance of human subjects on three diverse visual categories (animals, vehicles, and tools) and across three hierarchical levels (superordinate, basic, and subordinate levels among animals). For the same subjects, we measured their perceived pair-wise similarities between objects using a visual search task. Regardless of category and hierarchical level, we found that the time taken to categorize an object could be predicted using its similarity to members within and outside its category. We were able to account for several classic categorization phenomena, such as (a) the longer times required to reject category membership; (b) the longer times to categorize atypical objects; and (c) differences in performance across tasks and across hierarchical levels. These categorization times were also accounted for by a model that extracts coarse structure from an image. The striking agreement observed between categorization and visual search suggests that these two disparate tasks depend on a shared coarse object representation.

Obtaining single document summaries using latent dirichlet allocation

In this paper, we present a novel approach that makes use of topic models based on Latent Dirichlet allocation(LDA) for generating single document summaries. Our approach is distinguished from other LDA based approaches in that we identify the summary topics which best describe a given document and only extract sentences from those paragraphs within the document which are highly correlated given the summary topics. This ensures that our summaries always highlight the crux of the document without paying any attention to the grammar and the structure of the documents. Finally, we evaluate our summaries on the DUC 2002 Single document summarization data corpus using ROUGE measures. Our summaries had higher ROUGE values and better semantic similarity with the documents than the DUC summaries.

Discriminative feature analysis and selection for document classification

Classification of a large document collection involves dealing with a huge feature space where each distinct word is a feature. In such an environment, classification is a costly task both in terms of running time and computing resources. Further it will not guarantee optimal results because it is likely to overfit by considering every feature for classification. In such a context, feature selection is inevitable. This work analyses the feature selection methods, explores the relations among them and attempts to find a minimal subset of features which are discriminative for document classification.

Evaluation of document binarization using eigen value decomposition

A necessary step for the recognition of scanned documents is binarization, which is essentially the segmentation of the document. In order to binarize a scanned document, we can find several algorithms in the literature. What is the best binarization result for a given document image? To answer this question, a user needs to check different binarization algorithms for suitability, since different algorithms may work better for different type of documents. Manually choosing the best from a set of binarized documents is time consuming. To automate the selection of the best segmented document, either we need to use ground-truth of the document or propose an evaluation metric. If ground-truth is available, then precision and recall can be used to choose the best binarized document. What is the case, when ground-truth is not available? Can we come up with a metric which evaluates these binarized documents? Hence, we propose a metric to evaluate binarized document images using eigen value decomposition. We have evaluated this measure on DIBCO and H-DIBCO datasets. The proposed method chooses the best binarized document that is close to the ground-truth of the document.