Text localization and extraction from complex gray images

We propose two texture-based approaches, one involving Gabor filters and the other employing log-polar wavelets, for separating text from non-text elements in a document image. Both the proposed algorithms compute local energy at some information-rich points, which are marked by Harris' corner detector. The advantage of this approach is that the algorithm calculates the local energy at selected points and not throughout the image, thus saving a lot of computational time. The algorithm has been tested on a large set of scanned text pages and the results have been seen to be better than the results from the existing algorithms. Among the proposed schemes, the Gabor filter based scheme marginally outperforms the wavelet based scheme.

Systematic bias in MODIS dust aerosol retrieval at Kanpur (AERONET), Indo-Gangetic Basin - art.no.640816

We have compared the spectral aerosol optical depth (AOD) and aerosol fine mode fraction (AFMF) derived from Moderate Resolution Imaging Spectroradiometer (MODIS) with those of Aerosol Robotic Network (AERONET) at Kanpur (26.45N, 80.35E), northern India for the pre-monsoon season (March to June, 2001-2005). We found that MODIS systematically overestimates AOD during pre-monsoon season (known to be influenced by dust transport from north-west of India). The errors in AOD were correlated with the MODIS top-of-atmosphere apparent surface reflectance in 2.1 mu m channel (rho*(2.1)). MODIS aerosol algorithm uses p*(2.1) to derive the surface reflectance in visible channels (rho(0.47), rho(0.66)) using an empirical mid IR-visible correlation (rho(0.47) = rho(2.1)/4, rho(0.66) = rho(2.1)/2). The large uncertainty in estimating surface reflectance in visible channels (Delta rho(0.66)+/- 0.04, Delta rho(0.47)+/- 0.02) at higher values of p*(2.1) (p*(2.1) > 0.18) leads to higher aerosol contribution in the total reflected radiance at top-of atmosphere to compensate for the reduced surface reflectance in visible channels and thus leads to overestimation of AOD. This was also reflected in the very low values of AFMF during pre-monsoon whose accuracy depends on the aerosol path radiance in 0.47 and 0.66 mu m channels and aerosol models. The errors in AOD were also high in the scattering angle range 110 degrees-140 degrees, where the effect of dust non-spherity on its optical properties is significant. The direct measurements of spectral surface reflectance are required over the Indo-Gangetic basin in order to validate the mid IR-visible relationship. MODIS aerosol models should also be modified to incorporate the effect of non-spherity of dust aerosols.

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.

Binarization and localization of text images captured on a mobile phone camera

This paper proposes and compares four methods of binarzing text images captured using a camera mounted on a cell phone. The advantages and disadvantages(image clarity and computational complexity) of each method over the others are demonstrated through binarized results. The images are of VGA or lower resolution.

Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network

In this paper. we propose a novel method using wavelets as input to neural network self-organizing maps and support vector machine for classification of magnetic resonance (MR) images of the human brain. The proposed method classifies MR brain images as either normal or abnormal. We have tested the proposed approach using a dataset of 52 MR brain images. Good classification percentage of more than 94% was achieved using the neural network self-organizing maps (SOM) and 98% front support vector machine. We observed that the classification rate is high for a Support vector machine classifier compared to self-organizing map-based approach.

Elastic property estimation using Ultrasound Assisted Optical Elastography through Remote Palpation - A simulation study - art. no. 61640Q

We propose an effective elastography technique in which an acoustic radiation force is used for remote palpation to generate localized tissue displacements, which are directly correlated to localized variations of tissue stiffness and are measured using a light probe in the same direction of ultrasound propagation. The experimental geometry has provision to input light beam along the ultrasound propagation direction, and hence it can be prealigned to ensure proper interception of the focal region by the light beam. Tissue-mimicking phantoms with homogeneous and isotropic mechanical properties of normal and malignant breast tissue are considered for the study. Each phantom is insonified by a focusing ultrasound transducer (1 MHz). The focal volume of the transducer and the ultrasound radiation force in the region are estimated through solving acoustic wave propagation through medium assuming average acoustic properties. The forward elastography problem is solved for the region of insonification assuming the Lame's parameters and Poisson's ratio, under Dirichlet boundary conditions which gives a distribution of displacement vectors. The direction of displacement, though presented spatial variation, is predominantly towards the ultrasound propagation direction. Using Monte Carlo (MC) simulation we have traced the photons through the phantom and collected the photons arriving at the detector on the boundary of the object in the direction of ultrasound. The intensity correlations are then computed from detected photons. The intensity correlation function computed through MC simulation showed a modulation whose strength is found to be proportional to the amplitude of displacement and inversely related to the storage (elastic) modulus. It is observed that when the storage modulus in the focal region is increased the computed displacement magnitude, as indicated by the depth of modulation in the intensity autocorrelation, decreased and the trend is approximately exponential.

Computationally efficient optical tomographic reconstructions through waveletizing the normalized quadratic perturbation equation - art. no.61640R

In this paper, we present a wavelet - based approach to solve the non-linear perturbation equation encountered in optical tomography. A particularly suitable data gathering geometry is used to gather a data set consisting of differential changes in intensity owing to the presence of the inhomogeneous regions. With this scheme, the unknown image, the data, as well as the weight matrix are all represented by wavelet expansions, thus yielding the representation of the original non - linear perturbation equation in the wavelet domain. The advantage in use of the non-linear perturbation equation is that there is no need to recompute the derivatives during the entire reconstruction process. Once the derivatives are computed, they are transformed into the wavelet domain. The purpose of going to the wavelet domain, is that, it has an inherent localization and de-noising property. The use of approximation coefficients, without the detail coefficients, is ideally suited for diffuse optical tomographic reconstructions, as the diffusion equation removes most of the high frequency information and the reconstruction appears low-pass filtered. We demonstrate through numerical simulations, that through solving merely the approximation coefficients one can reconstruct an image which has the same information content as the reconstruction from a non-waveletized procedure. In addition we demonstrate a better noise tolerance and much reduced computation time for reconstructions from this approach.

Memory-based reasoning approach for pattern recognition of binary images

Template matching is concerned with measuring the similarity between patterns of two objects. This paper proposes a memory-based reasoning approach for pattern recognition of binary images with a large template set. It seems that memory-based reasoning intrinsically requires a large database. Moreover, some binary image recognition problems inherently need large template sets, such as the recognition of Chinese characters which needs thousands of templates. The proposed algorithm is based on the Connection Machine, which is the most massively parallel machine to date, using a multiresolution method to search for the matching template. The approach uses the pyramid data structure for the multiresolution representation of templates and the input image pattern. For a given binary image it scans the template pyramid searching the match. A binary image of N × N pixels can be matched in O(log N) time complexity by our algorithm and is independent of the number of templates. Implementation of the proposed scheme is described in detail.

Narratives of Travel and the Travelling Concept of Narrative: Genre Blending and the Art of Transformation

In this article I shall argue that understandings of what constitutes narrative, how it functions, and the contexts in which it applies have broadened in line with cultural, social and intellectual trends which have seen a blurring, if not the dissolution, of boundaries between ‘fact’ and ‘fiction’; ‘literary’ and ‘non-literary’ narrative spaces; history and story; concepts of time and space, text and image, teller and tale, representation and reality.To illustrate some of the ways in which the concept of narrative has travelled across disciplinary and generic boundaries, I shall look at The Art of Travel (de Botton 2003), with a view to demonstrating how the blending of genres works to produce a narrative that is at once personal and philosophical; visual and verbal; didactic and poetic. I shall show that such a text constitutes a site of interrogation of concepts of narrative, even as it depends on the reader’s ability to narrativize experience.

Narrative, Memory and the Crisis of Mimesis: the Case of Adam Elsheimer and Giordano Bruno

The triangular space between memory, narrative and pictorial representation is the terrain on which this article is developed. Taking the art of memory developed by Giordano Bruno (1548 – 1600) and the art of painting subtly revolutionised by Adam Elsheimer (1578 – 1610) as test-cases, it is shown how both subvert the norms of mimesis and narration prevalent throughout the Renaissance, how disrupted memory creates “incoherent” narratives, and how perspective and the notion of “place” are questioned in a corollary way. Two paintings by Elsheimer are analysed and shown to include, in spite of their supposed “realism”, numerous incoherencies, aporias and strange elements – often overlooked. Thus, they do not conform to two of the basic rules governing both the classical art of memory and the humanist art of painting: well-defined places and the exhaustive translatability of words into images (and vice-versa). In the work of Bruno, both his philosophical claims and the literary devices he uses are analysed as hints for a similar (and contemporaneous) undermining of conventions about the transparency and immediacy of representation.

Multiple contour extraction from graylevel images using an artificial neural network

For active contour modeling (ACM), we propose a novel self-organizing map (SOM)-based approach, called the batch-SOM (BSOM), that attempts to integrate the advantages of SOM- and snake-based ACMs in order to extract the desired contours from images. We employ feature points, in the form of ail edge-map (as obtained from a standard edge-detection operation), to guide the contour (as in the case of SOM-based ACMs) along with the gradient and intensity variations in a local region to ensure that the contour does not "leak" into the object boundary in case of faulty feature points (weak or broken edges). In contrast with the snake-based ACMs, however, we do not use an explicit energy functional (based on gradient or intensity) for controlling the contour movement. We extend the BSOM to handle extraction of contours of multiple objects, by splitting a single contour into as many subcontours as the objects in the image. The BSOM and its extended version are tested on synthetic binary and gray-level images with both single and multiple objects. We also demonstrate the efficacy of the BSOM on images of objects having both convex and nonconvex boundaries. The results demonstrate the superiority of the BSOM over others. Finally, we analyze the limitations of the BSOM.

Pietismin kuva - ikkuna yksityiseen hengellisyyteen : Johann Arndtin opetukset pietistisen embleemin perustana

The image of Pietism a window to personal spirituality. The teachings of Johann Arndt as the basis of Pietist emblems The Pietist effect on spiritual images has to be scrutinised as a continuum initiating from the teachings of Johann Arndt who created a protestant iconography that defended the status of pictures and images as the foundation of divine revelation. Pietist artworks reveal Arndtian part of secret, eternal world, and God. Even though modern scholars do not regarded him as a founding father of Pietism anymore, his works have been essential for the development of iconography, and the themes of the Pietist images are linked with his works. For Arndt, the starting point is in the affecting love for Christ who suffered for the humankind. The reading experience is personal and the words point directly at the reader and thus appear as evidence of the guilt of the reader as well as of the love of God. Arndt uses bounteous and descriptive language which has partially affected promoting and picturing of many themes. Like Arndt, Philipp Jakob Spener also emphasised the heart that believes. The Pietist movement was born to oppose detached faith and the lack of the Holy Ghost. Christians touched by the teachings of Arndt and Spener began to create images out of metaphors presented by Arndt. As those people were part of the intelligentsia, it was natural that the fashionable emblematics of the 17th century was moulded for the personal needs. For Arndt, the human heart is manifested as a symbol of soul, personal faith or unbelief as well as an allegory of the burning love for Jesus. Due to this fact, heart emblems were gradually widely used and linked with the love of Christ. In the Nordic countries, the introduction of emblems emanated from the gentry s connections to the Central Europe where emblems were exploited in order to decorate books, artefacts, interiors, and buildings as well as visual/literal trademarks of the intelligentsia. Emblematic paintings in the churches of the castles of Venngarn (1665) and Läckö (1668), owned by Magnus Gabriel De la Gardie, are one of the most central interior paintings preserved in the Nordic countries, and they emphasise personal righteous life. Nonetheless, it was the books by Arndt and the Poet s Society in Nurnberg that bound the Swedish gentry and the scholars of the Pietist movement together. The Finnish gentry had no castles or castle churches so they supported county churches, both in building and in maintenance. As the churches were not private, their iconography could not be private either. Instead, people used Pietist symbols such as Agnus Dei, Cor ardens, an open book, beams, king David, frankincense, wood themes and Virtues. In the Pietist images made for public spaces, the attention is focused on pedagogical, metaphorical, and meaningful presentation as well as concealed statements.

Many Faces of Mao Zedong

The main aim of this work was to explore the use of Mao Zedong s (毛泽东, 1893—1976) visual image in contemporary Chinese art during the years 1976—2006. Chairman Mao is the most visually reproduced person in the People's Republic of China (PRC), and the presence of his image is still unquestionable at many levels. Although several scholars have provided insightful observations on this topic, research focusing on Mao's visual image has been neglected. Employing the interdisciplinary approach of visual studies and using image as the main concept, this research combines different theoretical frameworks, deriving from art history, image studies and social sciences, for each chapter in order to explain the origins, intentions and major strategies of the contemporary Chinese artists. The focus of this research was to elucidate how Mao's visual image, deriving from the Maoist era, is re-created and negotiated in contemporary Chinese art works. The material reproductions - the visual images in contemporary art - are created to be juxtaposed with the immaterial mental images of Mao that were created during the Maoist era through the original visual images of Mao. This complex interaction between visual and mental images is further exemplified by art works that do not include Mao's visual image, but still imply his mental image. The methods used derive from both sinology and art history. The research is based on extensive fieldwork in China, which was crucial for gathering new information and materials from this vigorous art scene. The topic is approached through a Chinese cultural, political and historical perspective that is necessary for a further understanding of how the original visual images of Mao obtained their omnipotent status and what kind of iconography was created. Close structural analysis, taking into account the format, style, techniques, composition, colors, materials and space used in the art works, is employed to demonstrate the great variety of visual images created. The analysis is further placed in a continuous dialogue both with the contemporary art works of Mao and with the original visual images of Mao from the past. In this study it is shown that contemporary Chinese art relating to Chairman Mao is a more versatile and multilayered phenomenon than is generally assumed. Although some of the art works seem to fit into the definition of superficial art, the study demonstrates that this reading of the art works is not adequate. The author argues that employing Mao's visual images in contemporary Chinese art is based on three main strategies used by artists: to create a visual dialogue with a traumatizing past, to employ transcontextual parody, and to explore the importance of Tian'anmen through site-dependent art. These strategies are not exclusionary, but instead interdependent and many art works employ more than one of them. In addition, these three main strategies include versatile methods used by artists that make the use of Mao's visual images even more multifaceted.

Esteettinen kokemus kulttuurisiltana : Soile Yli-Mäyryn taide kiinalaisen, japanilaisen ja suomalaisen yleisön kokemana

AESTHETIC EXPERIENCE AS A BRIDGE ACROSS CULTURES Soile Yli-Mäyry s art as experienced by Chinese, Japanese and Finnish audiences This study focuses on surveying and analysing experiences of Soile Yli-Mäyry s art in eleven different countries. Questionnaires were translated into nine different languages. In addition, interviews were conducted on the experiences of Chinese, Japanese and Finnish art audiences concerning a painting called Sun Wind . The study was mainly inspired by John Dewey s ideas of art as an interactive communication where the artist, the piece and those who experience it make up an interactive process. In this process experience is a meeting point with both individual and communal characteristics. The data was collected in conjunction with exhibitions in 1997−2005. The survey was carried out in eleven countries (Finland, United States, Brazil, China, Taiwan, Japan, India, Israel, Argentina, Germany and Switzerland). The survey data was made up of 2,563 returned questionnaires. The interviews in China, Japan and Finland were about the same painting Sun Wind , which was transported from Finland to Japan (Tokyo) and China. A total of 89 people were interviewed in Shanghai Art Museum, 30 people in Port-Ginza Gallery, Tokyo and 45 people in Soile Yli-Mäyry s Gallery in Finland. Three hypotheses that were turned into research questions directed the study: 1. Are there differences/ similarities between culturally different communities in the meanings attributed to experiences, e.g. according to emotional dimensions, or do experiences focus more on reflecting on one s own life or meanings attributed to the world around us? What kinds of experiential dimensions are there in different countries? Do similar, analogous experiences that transcend cultural barriers emerge in culturally different countries such as China, Japan and Finland? 2. Does the data display different types of experiencing subjects which are typical to a subject s own country or are they experiences that can be compared to those generated by an ideal landscape , where the art touches the subconscious and collective selfhood, being thus transnational and timeless? Closer analysis focuses on audience experiences in China, Japan and Finland (interviews, textual survey data). 3. Are the experiences and interpretations of experts similar/different to those of larger audiences? The survey data has been analysed with the help of cross-tabulation. After content analysis of the interviews and textual survey data, different ways of experiencing subjects were sketched by country (China, Japan, Finland). The types were both similar and dissimilar. The most important types were social/ecological (China), therapeutic/reserved (Japan) and narrative/projecting (Finland). There were differences in how experiences were emphasised: the Chinese public approached their experiences from the viewpoint of pragmatism and utility, where they could obtain new ideas for their own work or experiencing the exhibition gave courage to approach their own lives from a new perspective. In turn, the Japanese public experienced the art from a therapeutic angle and from a very reserved perspective, which Dylan Evans (2001, 13−17) has described as typical to Japanese culture. The experiences of the Finnish audience were strongly therapeutic and narrative. The people projected their emotions onto the piece and in a concrete manner forged them into a story. The partly similar results of this study in China, Japan and Finland demonstrate that the art displayed in the exhibitions contain images of the beginning or elements connected to the beginning of life, which touch the subconscious in the way an ideal landscape would. Experiencing the meaningfulness of one s own life through art is a common thread and a bridge across cultures that unites the experiences of the audiences of this study, be they Taoists, Confucians, Buddhists or Maoists in China, Shinto followers, Zen Buddhists in Japan or Evangelist-Lutherans in Finland. Keywords: experience, reception, bridge across cultures, types of experiencing subjects, experiential process, ideal landscape, elementality