Extended Biographical Note

The color reduction in digital images is an active research area in digital image processing. In many applications such as image segmentation, analysis, compression and transmission, it is preferable to have images with a limited number of colors. In this paper, a color clustering technique which is a combination of a Kohonen Self Organized Featured Map (KSOFM) and a fuzzy clustering algorithm is proposed. Initially, we reduce the number of image’s colors by using a KSOFM. Then, using the KSOFM color clustering results as starting values, we obtain the final colors by a Gustafson-Kessel Fuzzy Classifier (GKFC). Doing this, we lead to better color classification results because the final color classes obtained are not spherical. J[2] Accurate image retrieval based on compact composite descriptors and relevance feedback information Authors: S. A. Chatzichristofis, K. Zagoris, Y. S. Boutalis and N. Papamarkos Abstract: In this paper a new set of descriptors appropriate for image indexing and retrieval is proposed. The proposed descriptors address the tremendously increased need for efficient content-based image retrieval (CBIR) in many application areas such as the Internet, biomedicine, commerce and education. These applications commonly store image information in large image databases where the image information cannot be accessed or used unless the database is organized to allow efficient storage, browsing and retrieval. To be applicable in the design of large image databases, the proposed descriptors are compact, with the smallest requiring only 23 bytes per image. The proposed descriptors' structure combines color and texture information which are extracted using fuzzy approaches. To evaluate the performance of the proposed descriptors, the objective Average Normalized Modified Retrieval Rank (ANMRR) is used. Experiments conducted on five benchmarking image databases demonstrate the effectiveness of the proposed descriptors in outperforming other state-of-the-art descriptors. Also, a Auto Relevance Feedback (ARF) technique is introduced which is based on the proposed descriptors. This technique readjusts the initial retrieval results based on user preferences improving the retrieval score significantly. An online demo of the image retrieval system img(Anaktisi) that In this paper a new set of descriptors appropriate for image indexing and retrieval is proposed. The proposed descriptors address the tremendously increased need for efficient content-based image retrieval (CBIR) in many application areas such as the Internet, biomedicine, commerce and education. These applications commonly store image information in large image databases where the image information cannot be accessed or used unless the database is organized to allow efficient storage, browsing and retrieval. To be applicable in the design of large image databases, the proposed descriptors are compact, with the smallest requiring only 23 bytes per image. The proposed descriptors' structure combines color and texture information which are extracted using fuzzy approaches. To evaluate the performance of the proposed descriptors, the objective Average Normalized Modified Retrieval Rank (ANMRR) is used. Experiments conducted on five benchmarking image databases demonstrate the effectiveness of the proposed descriptors in outperforming other state-of-the-art descriptors. Also, a Auto Relevance Feedback (ARF) technique is introduced which is based on the proposed descriptors. This technique readjusts the initial retrieval results based on user preferences improving the retrieval score significantly. An online demo of the image retrieval system img(Anaktisi) that implements the proposed descriptors can be found at http://www.anaktisi.net. J[3] A Document Image Retrieval System», Engineering Applications of Artificial Intelligence Authors: K. Zagoris, Ε. Kavallieratou and N. Papamarkos Abstract: In this paper, a system is presented that locates words in document image archives. This technique performs the word matching directly in the document images bypassing character recognition and using word images as queries. First, it makes use of document image processing techniques, in order to extract powerful features for the description of the word images. The features used for the comparison are capable of capturing the general shape of the query, and escape details due to noise or different fonts. In order to demonstrate the effectiveness of our system, we used a collection of noisy documents and we compared our results with those of a commercial optical character recognition (OCR) package. In this paper, a system is presented that locates words in document image archives. This technique performs the word matching directly in the document images bypassing character recognition and using word images as queries. First, it makes use of document image processing techniques, in order to extract powerful features for the description of the word images. The features used for the comparison are capable of capturing the general shape of the query, and escape details due to noise or different fonts. In order to demonstrate the effectiveness of our system, we used a collection of noisy documents and we compared our results with those of a commercial optical character recognition (OCR) package. J[4] Image Retrieval Systems Based On Compact Shape Descriptor and Relevance Feedback Information Authors: K. Zagoris, Ε. Kavallieratou and N. Papamarkos Abstract: One of the most important and most used low-level image feature is the shape employed in a variety of systems such as document image retrieval through word spotting. In this paper an MPEG-like descriptor is proposed that contains conventional contour and region shape features with a wide applicability from any arbitrary shape to document retrieval through word spotting. Its size and storage requirements are kept to minimum without limiting its discriminating ability. In addition to that, a relevance feedback technique based on Support Vector Machines is provided that employs the proposed descriptor with the purpose to measure how well it performs with it. In order to evaluate the proposed descriptor it is compared against different descriptors at the MPEG-7 CE1 Set B database. One of the most important and most used low-level image feature is the shape employed in a variety of systems such as document image retrieval through word spotting. In this paper an MPEG-like descriptor is proposed that contains conventional contour and region shape features with a wide applicability from any arbitrary shape to document retrieval through word spotting. Its size and storage requirements are kept to minimum without limiting its discriminating ability. In addition to that, a relevance feedback technique based on Support Vector Machines is provided that employs the proposed descriptor with the purpose to measure how well it performs with it. In order to evaluate the proposed descriptor it is compared against different descriptors at the MPEG-7 CE1 Set B database. J[5] Text Localization using Standard Deviation Analysis of Structure Elements and Support Vector Machines Authors: K. Zagoris , S. A. Chatzichristofis, N. Papamarkos Abstract: A text localization technique is required to successfully exploit document images such as technical articles and letters. The proposed method detects and extracts text areas from document images. Initially a Connected Components Analysis technique detects blocks of foreground objects. Then, A text localization technique is required to successfully exploit document images such as technical articles and letters. The proposed method detects and extracts text areas from document images. Initially a Connected Components Analysis technique detects blocks of foreground objects. Then, a descriptor that consists of a set of suitable Document Structure Elements is extracted from the blocks. This is achieved by incorporating an algorithm called Standard Deviation Analysis of Structure Elements (SDASE) which maximizes the separability between the blocks. Another feature of the SDASE is that its length adapts according to the requirements of the application. Finally, the descriptor of each block is used as input to a trained Support Vector Machines (SVM) that classifies the block as text or not. The proposed technique is also capable of adjusting to the text structure of the documents. A preliminary version of this work has been presented in [1]. Experimental results on benchmarking databases demonstrate the effectiveness of the proposed method. J[6] Dynamic Two-Stage Image Retrieval from Large Multimedia Databases Authors: A. Arampatzis, K. Zagoris and S. A. Chatzichristofis Abstract: A text localization technique is required to successfully exploit document images such as technical articles and letters. The proposed method detects and extracts text areas from document images. Initially a Connected Components Analysis technique detects blocks of foreground objects. Then, a descriptor that consists of a set of suitable Document Structure Elements is extracted from the blocks. This is achieved by incorporating an algorithm called Standard Deviation Analysis of Structure Elements (SDASE) which maximizes the separability between the blocks. Another feature of the SDASE is that its length adapts according to the requirements of the application. Finally, the descriptor of each block is used as input to a trained Support Vector Machines (SVM) that classifies the block as text or not. The proposed technique is also capable of adjusting to the text structure of the documents. A preliminary version of this work has been presented in [1]. Experimental results on benchmarking databases demonstrate the effectiveness of the proposed method. A text localization technique is required to successfully exploit document images such as technical articles and letters. The proposed method detects and extracts text areas from document images. Initially a Connected Components Analysis technique detects blocks of foreground objects. Then, a descriptor that consists of a set of suitable Document Structure Elements is extracted from the blocks. This is achieved by incorporating an algorithm called Standard Deviation Analysis of Structure Elements (SDASE) which maximizes the separability between the blocks. Another feature of the SDASE is that its length adapts according to the requirements of the application. Finally, the descriptor of each block is used as input to a trained Support Vector Machines (SVM) that classifies the block as text or not. The proposed technique is also capable of adjusting to the text structure of the documents. A preliminary version of this work has been presented in [1]. Experimental results on benchmarking databases demonstrate the effectiveness of the proposed method. C[1] Web Document Image Retrieval System Based on Word Spotting Authors: K. Zagoris, N. Papamarkos, C. Chamzas Abstract: Nowadays, the huge non-indexing quantities of image archives (especially document images) require the development of intelligent tools for their retrieval with convenience comparable of the texts search engines. The proposed technique addresses the document retrieval problem by a word matching procedure. It performs matching directly in the images bypassing OCR and using word-images as queries. It is constituted of two different parts: The offline and the online operation. In the offline operation, the archive of document images Nowadays, the huge non-indexing quantities of image archives (especially document images) require the development of intelligent tools for their retrieval with convenience comparable of the texts search engines. The proposed technique addresses the document retrieval problem by a word matching procedure. It performs matching directly in the images bypassing OCR and using word-images as queries. It is constituted of two different parts: The offline and the online operation. In the offline operation, the archive of document images is examined and the results are stored in a database. The online operation consists of the web interface, the creation of the word’s image and finally, the matching stage. The proposed matching process it can be described shortly as a two threshold rating system. Finally, the proposed system has been build and it can be found in at the web address: http://orpheus.ee.duth.gr/irs2. C[2] Color Reduction using the combination of the Kohonen Self-Organized Feature Map and the Gustafson-Kessel fuzzy algorithm Authors: K. Zagoris, N. Papamarkos and I. Koustoudis Abstract: The color of the digital images is one of the most important components of the image processing research area. In many applications such as image segmentation, analysis, compression and transition, it is preferable to reduce the colors as much as possible. In this paper, a color clustering technique which is the combination of a neural network and a fuzzy algorithm is proposed. Initially, the Kohonen Self Organized Featured Map (KSOFM) is applied to the original image. Then, the KSOFM results are fed to the Gustafson-Kessel (GK) fuzzy clustering algorithm as starting values. Finally, the output classes of GK algorithm define the numbers of colors of which the image will be reduced. The color of the digital images is one of the most important components of the image processing research area. In many applications such as image segmentation, analysis, compression and transition, it is preferable to reduce the colors as much as possible. In this paper, a color clustering technique which is the combination of a neural network and a fuzzy algorithm is proposed. Initially, the Kohonen Self Organized Featured Map (KSOFM) is applied to the original image. Then, the KSOFM results are fed to the Gustafson-Kessel (GK) fuzzy clustering algorithm as starting values. Finally, the output classes of GK algorithm define the numbers of colors of which the image will be reduced. C[3] Developing Document Image Retrieval System Authors: K. Zagoris, E. Kavallieratou and N. Papamarkos Abstract: A system was developed able to retrieve specific documents from a document collection. In this system the query is given in text by the user and then transformed into image. Appropriate features were in order to capture the general shape of the query, and ignore details due to noise or different fonts. In order to demonstrate the effectiveness of our system, we used a collection of noisy documents and we compared our results with those of a commercial OCR package. A system was developed able to retrieve specific documents from a document collection. In this system the query is given in text by the user and then transformed into image. Appropriate features were in order to capture the general shape of the query, and ignore details due to noise or different fonts. In order to demonstrate the effectiveness of our system, we used a collection of noisy documents and we compared our results with those of a commercial OCR package. C[4] img(Anaktisi): A Web Content Based Image Retrieval System Authors: K. Zagoris, S. A. Chatzichristofis, N. Papamarkos and Y. S. Boutalis Abstract: img(Anaktisi) is a C#/.NET content base image retrieval application suitable for the web. It provides efficient retrieval services for various image databases using as a query a sample image, an image sketched by the user and keywords. The image retrieval engine is powered by innovative compact and effective descriptors. Also, an Auto Relevance Feedback img(Anaktisi) is a C#/.NET content base image retrieval application suitable for the web. It provides efficient retrieval services for various image databases using as a query a sample image, an image sketched by the user and keywords. The image retrieval engine is powered by innovative compact and effective descriptors. Also, an Auto Relevance Feedback (ARF) technique is provided to the user. This technique readjusts the initial retrieval results based on user preferences improving the retrieval score significantly. img(Anaktisi) can be found at http://www.anaktisi.net. C[5] Text Extraction using Document Structure Features and Support Vector Machines Authors: K. Zagoris and N. Papamarkos Abstract: In order to successfully locate and retrieve document images such as technical articles and newspapers, a text localization technique must be employed. The proposed method detects and extracts homogeneous text areas in document images indifferent to font types and size by using connected components analysis to detect blocks of foreground objects. Next, a descriptor that consists of a set of structural features is extracted from the merged blocks and used as input to a trained Support Vector Machines (SVM). Finally, the output of the SVM classifies the block as text or not. In order to successfully locate and retrieve document images such as technical articles and newspapers, a text localization technique must be employed. The proposed method detects and extracts homogeneous text areas in document images indifferent to font types and size by using connected components analysis to detect blocks of foreground objects. Next, a descriptor that consists of a set of structural features is extracted from the merged blocks and used as input to a trained Support Vector Machines (SVM). Finally, the output of the SVM classifies the block as text or not. C[6] Automatic Image Annotation and Retrieval Using the Joint Composite Descriptor Authors: K. Zagoris, S. Chatzichristofis, N. Papamarkos and Y. S. Boutalis Abstract: Capable tools are needed in order to successfully search and retrieve a suitable image from large image collections. Many content-based image retrieval systems employ low-level image features such as color, texture and shape in order to locate the image. Although the above approaches are successful, they lack the ability to include human perception in the query for retrieval because the query must be an image. In this paper a new image annotation technique and a keyword based image retrieval system are presented, which map the low-level features of the Joint Composite Descriptor to the high-level features constituted by a set of keywords. One set consists of colors-keywords and the other set consists of words. Experiments were performed to demonstrate the effectiveness of the proposed technique. Capable tools are needed in order to successfully search and retrieve a suitable image from large image collections. Many content-based image retrieval systems employ low-level image features such as color, texture and shape in order to locate the image. Although the above approaches are successful, they lack the ability to include human perception in the query for retrieval because the query must be an image. In this paper a new image annotation technique and a keyword based image retrieval system are presented, which map the low-level features of the Joint Composite Descriptor to the high-level features constituted by a set of keywords. One set consists of colors-keywords and the other set consists of words. Experiments were performed to demonstrate the effectiveness of the proposed technique. C[7] www.MMRetrieval.net: A Multimodal Search Engine, Authors: K. Zagoris, A. Arampatzis and S. A. Chatzichristofis Abstract: We introduce an experimental search engine for multilingual and multimedia information, employing a holistic web interface and enabling the use of highly distributed indices. Modalities are searched in parallel, and results can be fused via several selectable methods. The engine also provides multistage retrieval, as well as a single text index baseline for comWe introduce an experimental search engine for multilingual and multimedia information, employing a holistic web interface and enabling the use of highly distributed indices. Modalities are searched in parallel, and results can be fused via several selectable methods. The engine also provides multistage retrieval, as well as a single text index baseline for comparison purposes. Initial impressions on its effectiveness are positive, while its efficiency may easily be improved. C[8] Multimedia Search with Noisy Modalities: Fusion and Multistage Retrieval Authors: A. Arampatzis, S. A. Chatzichristofis, K. Zagoris Abstract: We report our experiences from participating to the controlled experiment of the ImageCLEF 2010Wikipedia Retrieval task. We built an experimental search engine which combines multilingual and multi-image search, employing a holistic web interface and enabling the use of highly distributed indices. Modalities are searched in parallel, and results can be fused via several selectable methods. The engine also provides multistage retrieval, as well as a single text index baselines for comparison purposes. Experiments show that the value added by image modalities is very small when textual annotations exist. The contribution of image modalities is larger when search is performed in a 2-stage fashion, i.e., using image search for re-ranking a smaller set of only the top results retrieved by text. Furthermore, first splitting annotations to many modalities with respect to natural language and/or type and then fusing results has the potential of achieving better effectiveness than using all textual information as a single modality. Concerning fusion, the simple method of linearly combining evidence is found to be the most robust, achieving the best effectiveness. We report our experiences from participating to the controlled experiment of the ImageCLEF 2010Wikipedia Retrieval task. We built an experimental search engine which combines multilingual and multi-image search, employing a holistic web interface and enabling the use of highly distributed indices. Modalities are searched in parallel, and results can be fused via several selectable methods. The engine also provides multistage retrieval, as well as a single text index baselines for comparison purposes. Experiments show that the value added by image modalities is very small when textual annotations exist. The contribution of image modalities is larger when search is performed in a 2-stage fashion, i.e., using image search for re-ranking a smaller set of only the top results retrieved by text. Furthermore, first splitting annotations to many modalities with respect to natural language and/or type and then fusing results has the potential of achieving better effectiveness than using all textual information as a single modality. Concerning fusion, the simple method of linearly combining evidence is found to be the most robust, achieving the best effectiveness. C[9] Fusion vs Two-Stage for Multimodal Retrieval Authors: A. Arampatzis, K. Zagoris and S. A. Chatzichristofis Abstract: We compare two methods for retrieval from multimodal collections. The first is a score-based fusion of results, retrieved visually and textually. The second is a two-stage method that visually re-ranks the top-K results textually retrieved. We discuss their underlying hypotheses and practical limitations, and contact a comparative evaluation on a standardized snapshot of Wikipedia. Both methods are found to be significantly more effective than single-modality baselines, with no clear winner but with different robustness features. Nevertheless, two-stage retrieval provides efficiency benefits over fusion. We compare two methods for retrieval from multimodal collections. The first is a score-based fusion of results, retrieved visually and textually. The second is a two-stage method that visually re-ranks the top-K results textually retrieved. We discuss their underlying hypotheses and practical limitations, and contact a comparative evaluation on a standardized snapshot of Wikipedia. Both methods are found to be significantly more effective than single-modality baselines, with no clear winner but with different robustness features. Nevertheless, two-stage retrieval provides efficiency benefits over fusion. C[10] Dynamic Two-Stage Image Retrieval from Large Multimodal Databases Authors: A. Arampatzis, K. Zagoris and S. A. Chatzichristofis Abstract: Content-based image retrieval (CBIR) with global feaContent-based image retrieval (CBIR) with global features is notoriously noisy, especially for image queries with low percentages of relevant images in a collection. Moreover, CBIR typically ranks the whole collection, which is inefficient for large databases. We experiment with a method for image retrieval from multimodal databases, which improves both the effectiveness and efficiency of traditional CBIR by exploring secondary modalities. We perform retrieval in a two-stage fashion: first rank by a secondary modality, and then perform CBIR only on the top-K items. Thus, effectiveness is improved by performing CBIR on a ‘better’ subset. Using a relatively ‘cheap’ first stage, efficiency is also improved via the fewer CBIR operations performed. Our main novelty is that K is dynamic, i.e. estimated per query to optimize a predefined effectiveness measure. We show that such dynamic two-stage setups can be significantly more effective and robust than similar setups with static thresholds previously proposed. C[11] Comparative Performance Evaluation of Image Descriptors over IEEE 802.11B Noisy Wireless Networks Authors: E. Chatzistavros, S. Α. Chatzichristofis, G. Stamatellos and K. Zagoris Abstract: In this paper we evaluate the image retrieval procedure over an IEEE 802.11b Ad Hoc network, operating in 2.4GHz, using IEEE Distributed Coordination Function CSMA/CA as the multiple access scheme. IEEE 802.11 is a widely used network standard, implemented and supported by a variety of devices, such as desktops, laptops, notebooks, mobile phones etc., capable of providing a variety of different services, such as file transfer, internet access et.al. Therefore, we consider IEEE 802.11b being a suitable technology to investigate the case of conducting image retrieval over a wireless noisy channel. The model we use to simulate the noisy environment is based on the scenario in which the wireless network is located in an outdoor noisy environment, or in an indoor environment of partial LOS Line-of-sight power. We used a large number of descriptors reported in literature in order to evaluate which one has the best performance in terms of Mean Average Precision MAP values under those circumstances. Experimental results on known benchmarking database show that the majority of the descriptors appear to have decreased performance when transferred and used in such noisy environments. In this paper we evaluate the image retrieval procedure over an IEEE 802.11b Ad Hoc network, operating in 2.4GHz, using IEEE Distributed Coordination Function CSMA/CA as the multiple access scheme. IEEE 802.11 is a widely used network standard, implemented and supported by a variety of devices, such as desktops, laptops, notebooks, mobile phones etc., capable of providing a variety of different services, such as file transfer, internet access et.al. Therefore, we consider IEEE 802.11b being a suitable technology to investigate the case of conducting image retrieval over a wireless noisy channel. The model we use to simulate the noisy environment is based on the scenario in which the wireless network is located in an outdoor noisy environment, or in an indoor environment of partial LOS Line-of-sight power. We used a large number of descriptors reported in literature in order to evaluate which one has the best performance in terms of Mean Average Precision MAP values under those circumstances. Experimental results on known benchmarking database show that the majority of the descriptors appear to have decreased performance when transferred and used in such noisy environments. C[12] Bag-of-Visual-Words vs Global Image Descriptors on Two-Stage Multimodal Retrieval Authors: K. Zagoris, S. A. Chatzichristofis and A. Arampatzis Abstract: Using Bag-of-Visual Words (BOVW) is fast becoming a widely used representation for content based image retrieval mainly, because of their better retrieval effectiveness over global feature representations on collections with images being Using Bag-of-Visual Words (BOVW) is fast becoming a widely used representation for content based image retrieval mainly, because of their better retrieval effectiveness over global feature representations on collections with images being near-duplicate to the test queries. In this experimental study we demonstrate that this advantage of BOVW is diminished when visual diversity is enhanced by using a secondary modality, such as text, to pre-filter images. In detail, the TOP-SURF descriptor is evaluated against Compact Composite Descriptors on a two-stage image retrieval system, which first uses a text modality to rank the collection and then perform CBIR only on the top-K items. C[13] The TREC Files: the (ground) truth is out there Authors: S. A. Chatzichristofis, K. Zagoris and A. Arampatzis Abstract: Traditional tools for information retrieval (IR) evaluation, such as TREC’s trec_eval, have outdated command-line interfaces with many unused features, or ‘switches’, accumulated over the years. They are usually seen as cumbersome applications by new IR researchers, steepening the learning curve. We introduce a platform independent application for IR evaluation with a graphical easy to use interface: the TREC_Files Evaluator. The application supports most of the standard measures used for evaluation in TREC, CLEF, and elsewhere, such as MAP, P10, P20, and bpref, as well as the Averaged Normalized Modified Retrieval Rank (ANMRR) proposed by MPEG for image retrieval evaluation. Additional features include a batch mode and statistical significance testing of the results against a pre-selected baseline. Traditional tools for information retrieval (IR) evaluation, such as TREC’s trec_eval, have outdated command-line interfaces with many unused features, or ‘switches’, accumulated over the years. They are usually seen as cumbersome applications by new IR researchers, steepening the learning curve. We introduce a platform independent application for IR evaluation with a graphical easy to use interface: the TREC_Files Evaluator. The application supports most of the standard measures used for evaluation in TREC, CLEF, and elsewhere, such as MAP, P10, P20, and bpref, as well as the Averaged Normalized Modified Retrieval Rank (ANMRR) proposed by MPEG for image retrieval evaluation. Additional features include a batch mode and statistical significance testing of the results against a pre-selected baseline. C[15] A Fuzzy Rank-Based Late Fusion Method for Image Retrieval Authors: S. A. Chatzichristofis, K. Zagoris, Y. S. Boutalis and A. Arampatzis Abstract: Rank-based fusion is indispensable in multiple search setups in lack of item retrieval scores, such as in meta-search with non-cooperative engines. We introduce a novel, simple, and efficient method for rank-based late fusion of retrieval result-lists. The approach taken is rule-based, employs a fuzzy system, and does not require training data. We evaluate on an image database by fusing results retrieved by three MPEG-7 descriptors, and find statistically significant improvements in effectiveness over other widely used rank-based fusion methods. Rank-based fusion is indispensable in multiple search setups in lack of item retrieval scores, such as in meta-search with non-cooperative engines. We introduce a novel, simple, and efficient method for rank-based late fusion of retrieval result-lists. The approach taken is rule-based, employs a fuzzy system, and does not require training data. We evaluate on an image database by fusing results retrieved by three MPEG-7 descriptors, and find statistically significant improvements in effectiveness over other widely used rank-based fusion methods. C[16] TSOKADO: An Image Search Engine Performing Recursive Query Recommendation Based on Visual Information Authors: L. T. Tsochatzidis, A. Ch. Kapoutsis, N. I. Dourvas, S. A. Chatzichristofis, Y. S. Boutalis and K. Zagoris Abstract: This paper tackles the problem of the user's incapaThis paper tackles the problem of the user's incapability to describe exactly the image that he seeks by introducing an innovative image search engine called TsoKaDo. Until now the traditional web image search was based only on the comparison between metadata of the webpage and the user's textual description, query. In the method proposed, images from various search engines are classified based on visual content and new tags are proposed to the user. Recursively, the results get closer to the user's desire. The aim of this paper is to present a new way of searching, especially in case with less query generality, giving greater weight in visual content rather than in metadata. An on-line early version of TsoKaDo is available at http://tsokado.nonrelevant.net. C[17] Handwritten and Machine Printed Text Separation in Document Images using the Bag of Visual Words Paradigm Authors: K. Zagoris, I. Pratikakis, A. Antonacopoulos, Basilis Gatos , N. Papamarkos Abstract: In a number of types of documents, ranging from forms to archive documents and books with annotations, machine printed and handwritten text may be present in the same document image, giving rise to significant issues within a digitisation and recognition pipeline. It is therefore necessary to separate the two types of text before applying different recognition methodologies to each. In this paper, a new approach is proposed which strives towards identifying and separating handwritten from machine printed text using the Bag of Visual Words paradigm (BoVW). Initially, blocks of interest are detected in the document image. For each block, a descriptor is calculated based on the BoVW. The final characterization of the blocks as Handwritten, Machine Printed or Noise is made by a Support Vector Machine classifier. The promising performance of the proposed approach is shown by using a consistent evaluation methodology which couples meaningful measures along with a new dataset. In a number of types of documents, ranging from forms to archive documents and books with annotations, machine printed and handwritten text may be present in the same document image, giving rise to significant issues within a digitisation and recognition pipeline. It is therefore necessary to separate the two types of text before applying different recognition methodologies to each. In this paper, a new approach is proposed which strives towards identifying and separating handwritten from machine printed text using the Bag of Visual Words paradigm (BoVW). Initially, blocks of interest are detected in the document image. For each block, a descriptor is calculated based on the BoVW. The final characterization of the blocks as Handwritten, Machine Printed or Noise is made by a Support Vector Machine classifier. The promising performance of the proposed approach is shown by using a consistent evaluation methodology which couples meaningful measures along with a new dataset. C[18] Scene Text Detection on Images using Cellular Automata Authors: K. Zagoris and I. Pratikakis Abstract: Textual information in images constitutes a very rich source of high-level semantics for retrieval and indexing. In this paper, a new approach is proposed using Cellular Automata (CA) which strives towards identifying scene text on natural images. Initially, a binary edge map is calculated. Then, taking advantage of the CA flexibility, the transition rules are changing and are applied in four consecutive steps resulting in four time steps CA evolution. Finally, a post-processing technique based on edge projection analysis is employed for high density edge images concerning the elimination of possible false positives. Evaluation results indicate considerable performance gains Textual information in images constitutes a very rich source of high-level semantics for retrieval and indexing. In this paper, a new approach is proposed using Cellular Automata (CA) which strives towards identifying scene text on natural images. Initially, a binary edge map is calculated. Then, taking advantage of the CA flexibility, the transition rules are changing and are applied in four consecutive steps resulting in four time steps CA evolution. Finally, a post-processing technique based on edge projection analysis is employed for high density edge images concerning the elimination of possible false positives. Evaluation results indicate considerable performance gains without sacrificing text detection accuracy.