Papers by Alexey Podlasov
Lecture Notes in Computer Science, 2005
Map images are composed of semantic layers depicted in arbitrary color. Layer extraction and remo... more Map images are composed of semantic layers depicted in arbitrary color. Layer extraction and removal is often needed for improving readability as well as for further processing. When image is separated into the set of layers with respect to the colors, it results in appearance of severe artifacts because of the layer overlapping. In this way the extracted layers differ from the semantic data, which affects further map image processing analysis tasks. In this work, we introduce techniques for extraction and removal of the semantic layers from the map images. The techniques utilize low-complexity morphological image restoration algorithms. The restoration provides good quality of the reconstructed layers, and alleviates the affect of artifacts on the precision of image analysis tasks.
25. The role of images in social media analytics: A multimodal digital humanities approach
De Gruyter eBooks, Mar 14, 2014
The analysis of social media data is an emerging research field that aims to study the dynamics o... more The analysis of social media data is an emerging research field that aims to study the dynamics of urban life. In this study, we adopt a multimodal digital humanities approach to combine the analysis of text-based social media data with visual social media data in an interactive map to investigate urban life in Singapore from a social semiotic perspective. Twitter is used as a source of user-defined localised textual data, Instagram as a source of localised user-generated images and Foursquare as a source of user-defined location-based information where is semantically organised according to Wikipedia's classification tree. In this way, we track the multimodal content of social media according to semantically organised location-based sources. This study suggests that users of Twitter express emotion about their own lives and the world around them, but these linguistic resources are differentially deployed according to venue. However, this is less variation in the use of photos to construe personal relationships, suggesting that photos fulfil and intrinsic need to be observed which transcends the nature of the social practice which is taking place. It is envisaged that the role of the visual will continue to expand as digital technologies refashion and transform out semiotic world
We propose a statistical filter using a context tree modeling. The idea of context tree is to per... more We propose a statistical filter using a context tree modeling. The idea of context tree is to perform selective context expansion including only those pixel combinations that really appear in the image. This makes it possible to use much larger spatial neighborhood. The proposed context tree filtering is evaluated for a set of indexed-color raster map images corrupted with generated impulsive and content-dependent noise. The objective evaluation shows improvement of 15% for content-dependent noise and up to 30% for impulsive noise comparing to the closest competitor. Visual comparisons show that the spatial structures are preserved better than by vector median, morphological and peer group averaging filter.
Journal of Electronic Imaging, 2006
Map images are composed of semantic layers depicted in arbitrary color. Color separation is often... more Map images are composed of semantic layers depicted in arbitrary color. Color separation is often needed to divide the image into layers for storage and processing. Separation can result in severe artifacts because of the overlapping of the layers. In this work, we introduce a technique to restore the original semantic layers after the color separation. The proposed restoration technique improves compression performance of the reconstructed layers in comparison to the corrupted ones when compressed by lossless algorithms such as International Communication Unit (ITU) Group 4 (TIFF G4), Portable Network Graphics (PNG), Joint Bi-level Image experts Group (JBIG), and context tree method. The resulting technique also provides good visual quality of the reconstructed image layers, and can therefore be applied for selective layer removal/ extraction in other map processing applications, e.g., area measurement.
Journal of Electronic Imaging, Oct 1, 2006
Color separation and highly optimized context tree modeling for binary layers have provided the b... more Color separation and highly optimized context tree modeling for binary layers have provided the best compression results for color map images that consist of highly complex spatial structures but only a relatively few number of colors. We explore whether this kind of approach works on photographic and palette images as well. The main difficulty is that these images can have a much higher number of colors, and it is therefore much more difficult to exploit spatial dependencies via binary layers. The original contributions of this work include: 1. the application of context-tree-based compression (previously designed for map images) to natural and color palette images; 2. the consideration of four different methods for bit-plane separation; and 3. Extension of the two-layer context to a multilayer context for better utilization of the crosslayer correlations. The proposed combination is extensively compared to state of the art lossless image compression methods.
Japanese Street Fashion for Young People: A Multimodal Digital Humanities Approach for Identifying Sociocultural Patterns and Trends
O'Halloran, K. L., Tan, S., Smith, B. A., & Podlasov, A. (2010; accepted for publication). Challenges in Designing Digital Interfaces for the Study of Multimodal Phenomena. Information Design Journal
Challenges and solutions for multimodal analysis: Technology, theory and practice
12. Challenges and solutions to multimodal analysis: Technology, theory and practice
Equinox Publishing, Jan 2, 2014
In what follows, the principal functionalities of Semiomix are first described (see also O’Hallor... more In what follows, the principal functionalities of Semiomix are first described (see also O’Halloran et al., 2012) and then illustrated via screenshots from Professor W. Gilbert Strang’s first lecture in Linear Algebra from Massachusetts Institute of Technology (MIT) Open Courseware (OCW).1 Following this, Professor Strang’s use of language and gesture are interpreted in relation to the different stages of the mathematics lecture. Finally, the achievements and limitations of the existing version of Semiomix are described with view to future research.
Information Design Journal, 2010
The paper discusses the challenges faced by researchers in developing effective digital interface... more The paper discusses the challenges faced by researchers in developing effective digital interfaces for analyzing the meaning-making processes of multimodal phenomena. The authors propose a social semiotic approach as the underlying theoretical foundation, because interactive digital technology is the embodiment of multimodal social semiotic communication. The paper outlines the complex issues with which researchers are confronted in designing digital interface frameworks for modeling, analyzing, and retrieving meaning from multimodal data, giving due consideration to the multiplicity of theoretical frameworks and theories which have been developed for the study of multimodal text within social semiotics, and their impact on the development of a computer-based tool for the exploration, annotation, and analysis of multimodal data.
multimodal-analysis-lab.org
Orchestration of meaning in multimodal semiosis and semiotics 1. Studying multimodal semiosis: Th... more Orchestration of meaning in multimodal semiosis and semiotics 1. Studying multimodal semiosis: Theoretical and technical challenges and resources A major challenge for scholars concerned with multimodal semiotic phenomena-that is, semiotic acts and discourse involving the interaction of more than one semiotic resource such as language, gaze, gesture, vocal features, proxemics, graphic display, cinematography, pagelayout etc-has been to not only develop an account of the range of semiotic phenomena and their affordances discernable in multimodal texts but to show how such phenomena (can and do) work together inter-semiotically to produce meanings within texts. Scholars drawing upon Halliday's (e.g. 1978) social semiotic approach to language, known as systemic functional linguistic theory (Halliday and Matthiessen 2004; Martin 1992), have pointed the way to a holistic account of multimodal semiosis by urging attention to sign-making as a motivated social process, rather than simply as product and (isolated, self-contained) sign system, highlighting Hodge and Kress' (1988, 1) focus on the "functions and social uses of semiotic systems, the complex interrelations of semiotic systems in social practice" (cf. also
On the restoration of semantic data in raster map images
Merge-Based Color Quantization and Context Tree Modeling for Compression of Color Quantized Images
2006 International Conference on Image Processing, 2006
A two-stage lossless compression method based on a binary tree representation of colors and on co... more A two-stage lossless compression method based on a binary tree representation of colors and on context-based arithmetic coding has been recently proposed. We propose two improvements to this method: merge-based color quantization instead of the original splitting strategy, and context tree modeling optimized for each layer separately. The proposed method achieves better compression performance and a better reproduction quality in
25. The role of images in social media analytics: A multimodal digital humanities approach
Spatial pedagogy: mapping meanings in the use of classroom space
Cambridge Journal of Education, 2012
The positioning and movement of the teacher in the classroom are fundamental to the pedagogical p... more The positioning and movement of the teacher in the classroom are fundamental to the pedagogical process. Specific spaces in the classroom take on certain meanings because of the nature of pedagogic discourse that occurs on the site and the positioning and distance of the site relative to the students and the teaching resources. Spatial pedagogy is realised through the patterns
An algorithm for lossy compression of scanned map images is proposed. The algorithm is based on c... more An algorithm for lossy compression of scanned map images is proposed. The algorithm is based on color quantization, efficient statistical context tree modeling and arithmetic coding. The ratedistortion performance is evaluated on a set of scanned maps and compared to JPEG2000 lossy compression algorithm, and to ECW, which is a commercially available solution for compression of satellite and aerial images. The proposed algorithm outperforms these competitors in rate-distortion sense for the most part of the operational rate-distortion curve.
Multi-layer context tree modeling for lossless compression of gray-scale images
ABSTRACT
Raster topographic images consist of a set of layers depicted in arbitrary color. There exist str... more Raster topographic images consist of a set of layers depicted in arbitrary color. There exist strong correspondence between the color of the layer and its semantic meaning. Often there is a need to separate or extract semantic layers from the map. The separation results in severe artifacts in places where semantic layers would overlap (e.g. elevations lines drawn on top of the topographic map). In the current work, we design the technique to reconstruct the semantic layers from the color layers resulting from the image separation process. The proposed technique provides good visual quality of the reconstructed image layers, and can therefore be applied for selective layer removal/extraction, which is often necessary in map processing and analyzing applications. It improves the accuracy of the data analysis and measurement tasks. The technique requires few computation resources and can be successfully used in mobile computers and terminals.
Raster map images consist of a set of layers depicted in arbitrary color. There exist strong corr... more Raster map images consist of a set of layers depicted in arbitrary color. There exist strong correspondence between the color o the layer and its semantic meaning. Often there is a need to separate or extract semantic layers from the maps. The separation results in severe artifacts in places where semantic layers would overlap (e.g. elevations lines drawn on top of the topographic map). In the current work, we design the technique to reconstruct the semantic layers from the color layers resulting from the image separation process. The proposed technique provides good visual quality of the reconstructed image layers, and can therefore be applied for selective layer removal/extraction, which is often necessary in map processing and analyzing applications. It improves the accuracy of the data analysis and measurement tasks. It also alleviates compression deficiency of reconstructed layers versus corrupted ones with lossless compression algorithms (ITU Group 4, PNG, JBIG). The technique requires few computation resources and can therefore be successfully used in mobile computers and terminals.
As a standard, research work in the field of image processing and compression includes lots of ex... more As a standard, research work in the field of image processing and compression includes lots of experimentation. New ideas shall be first implemented in some programming languages or environment, and then undergo extensive empirical evaluation. Analysis of the weak sides will lead to a further research and development work. The implementation process (programming of the developed method) is usually the most time-consuming part of any research process. Therefore the flexibility of the implementation, such as code readability, fast modification feasibility, friendly programming environment, etc. do often prevail over the implementation efficiency, memory load and computation time. The efficient implementation could be often too expensive to conclude, especially in the research process, when frequent algorithm modifications are required. Still, the implementation efficiency should not be overlooked in the algorithm design process. The experiments should possible be conducted in a realistic time-frame and using reasonable hardware resources. The current work examines the usability of NIH ImageJ Java-based framework in the image processing research in the case of implementing morphological operations. We demonstrate how the environment can be easily understood, and the new operations implemented and modified by researchers familiar with the basics of Java language. The set of morphological operators is implemented as a test case and shows good usability in terms of ease programming and computation efficiency.
Uploads
Papers by Alexey Podlasov