Κεφάλαια βιβλίων http://hdl.handle.net/11728/34 2026-04-05T16:59:55Z 2026-04-05T16:59:55Z Barlas, Georgios Zagoris, Konstantinos Pratikakis, Ioannis http://hdl.handle.net/11728/11652 2021-02-13T01:00:21Z 2017-07-21T00:00:00Z

Handwritting: keyword spotting The Query by Example (QbE) case Barlas, Georgios; Zagoris, Konstantinos; Pratikakis, Ioannis The traditional approach in document indexing usually involves an Optical Character Recognition (OCR) step. Although OCR performs well in modern printed documents and documents of high quality printing, in the case of handwritten documents OCR, several factors affect the final performance like intense degradation, paper-positioning variations (skew, translations, etc.) and writing styles variety. Handwritten word spotting has attracted the attention of the research community in the field of document image analysis and recognition since it appears to be a feasible solution for indexing and retrieval of handwritten documents in the case that OCR-based methods fail to deliver satisfactory results. Handwritten keyword spotting (KWS) is the task of retrieving all instances of a given query word in handwritten document image collections without involving a traditional OCR step. There exist two basic variations for KWS approaches: (a) the Query by Example case (QbE) where the query is a word image and (b) the Query by String case (QbS) where, as the name implies, the query is a string. The study presented in this chapter will focus on the QbE approach For a better understanding, QbE methods will be presented taking into account two different perspectives which relate to the use of segmentation and learning. The segmentation- based methods are divided into 2 subcategories based upon the segmented entity which could be either the word image or the textline. They are strongly dependent on the segmentation step, so that to compare different methods regardless of segmentation errors, many researchers do not implement a segmentation method but they use datasets where the segments are given. In the case of segmentation-free methods the whole image is tested against similarities between the query image and the patches of the document image without segmenting it at any level. The methods of this class, on the one hand bypass the step of segmentation but on the other hand they cannot avoid searching for the words in parts of the image that may not contain text. Therefore, segmentation-free methods avoid failures due to bad segmentation but the running time increases considerably. It is worth-mentioning that the methods of this class are not the trend. Training-based methods are those that require training data at a particular stage of the process. A common problem in these methods is the availability of training data. Further- more, an extra weakness is that to apply such a method to a new word, usually ground truthing work is required to obtain training data, which is quite time consuming and often it has to be done totally manual. Training - free are methods that as the name implies do not include any training stage in the operational KWS pipeline. The training - free methods can be applied directly to new word although, they usually require a particular configuration to be effective in the corresponding text. This chapter is structured as follows: Section “Segmentation-based Context” will present the KWS methodologies that operate in a segmentation-based context wherein methods based on training and methods that are independent of any training involvement will be detailed. Both variations will be separately reviewed depending on the type of segmentation which is used. In Section “Segmentation - Free Context”, methodologies that do account for a segmentation will be discussed with a particular focus on the use or not of training. Section “Experimental Datasets and Evaluation Metrics” deals with an overview of the current efforts for performance evaluation and a brief description of datasets that were used in QbE KWS, while the Section “Conclusive Remarks” is dedicated to a fruitful discussion which aims to identify the current trends of the QbE KWS.

2017-07-21T00:00:00Z Chatzichristofis, Savvas A. Boutalis, Yiannis S. Lux, Mathias http://hdl.handle.net/11728/10178 2017-11-02T01:00:50Z 2011-01-01T00:00:00Z

Combining Color and Spatial Color Distribution Information in a Fuzzy Rule Based Compact Composite Descriptor Chatzichristofis, Savvas A.; Boutalis, Yiannis S.; Lux, Mathias In this paper, a novel low level feature for content based image retrieval is presented. The proposed feature structure combines color and spatial color distribution information. The combination of these two features in one vector classifies the proposed descriptor to the family of Composite Descriptors. In order to extract the color information, a fuzzy system is being used, which is mapping the number of colors that are included in the image into a custom palette of 8 colors. The way by which the vector of the proposed descriptor is being formed, describes the color spatial information contained in images. To be applicable in the design of large image databases, the proposed descriptor is compact, requiring only 48 bytes per image. Experiments presented in this paper demonstrate the effectiveness of the proposed technique especially for Hand-Drawn Sketches.

2011-01-01T00:00:00Z Kapoutsis, Athanasios Ch. Chatzichristofis, Savvas A. Sirakoulis, Georgios Ch. Doitsidis, Lefteris Kosmatopoulos, Elias B. http://hdl.handle.net/11728/10177 2017-11-02T01:00:39Z 2015-01-01T00:00:00Z

Employing Cellular Automata for Shaping Accurate Morphology Maps Using Scattered Data from Robotics’ Missions Kapoutsis, Athanasios Ch.; Chatzichristofis, Savvas A.; Sirakoulis, Georgios Ch.; Doitsidis, Lefteris; Kosmatopoulos, Elias B. Accurate maps are essential in the case of robot teams, so that they can operate autonomously and accomplish their tasks efficiently. In this work we present an approach which allows the generation of detailed maps, suitable for robot navigation, from a mesh of sparse points using Cellular Automata and simple evolutions rules. The entire map area can be considered as a 2D Cellular Automaton (CA) where the value at each CA cell represents the height of the ground in the corresponding coordinates. The set of measurements form the original state of the CA. The CA rules are responsible for generating the intermediate heights among the real measurements. The proposed method can automatically adjust its rules, so as to encapture local morphological attributes, using a pre-processing procedure in the set of measurements. The main advantage of the proposed approach is the ability to maintain an accurately reconstruction even in cases where the number of measurements are significant reduced. Experiments have been conducted employing data collected from two totally different real-word environments. In the first case the proposed approach is applied, so as to build a detailed map of a large unknown underwater area in Oporto, Portugal. The second case concerns data collected by a team of aerial robots in real experiments in an area near Zurich, Switzerland and is also used for the evaluation of the approach. The data collected, in the two aforementioned cases, are extracted using different kind of sensors and robots, thus demonstrating the applicability of our approach in different kind of devices. The proposed method outperforms the performance of other well-known methods in literature thus enabling its application for real robot navigation. The research leading to these results has received funding from the European Communities Seventh Framework Programme (FP7/2007–2013) under grant agreements n. 270180 (NOPTILUS)

2015-01-01T00:00:00Z Bitsakidis, Nikolaos P. Dourvas, Nikolaos I. Chatzichristofis, Savvas A. Sirakoulis, Georgios Ch. http://hdl.handle.net/11728/10176 2017-11-02T01:00:45Z 2017-01-01T00:00:00Z

Cellular Automata Ants Bitsakidis, Nikolaos P.; Dourvas, Nikolaos I.; Chatzichristofis, Savvas A.; Sirakoulis, Georgios Ch. During the last decades much attention was given to bio-inspired techniques able to successfully handle really complex algorithmic problems. As such Ant Colony Optimization (ACO) algorithms have been introduced as a metaheuristic optimization technique arriving from the swarm intelligence methods family and applied to several computational and combinatorial optimization problems. However, long before ACO, Cellular Automata (CA) have been proposed as a powerful parallel computational tool where space and time are discrete and interactions are local. It has been proven that CA are ubiquitous: they are mathematical models of computation and computer models of natural systems and their research in interdisciplinary topics leads to new theoretical constructs, novel computational solutions and elegant powerful models. As a result, in this chapter we step forward presenting a combination of CA with ant colonies aiming at the introduction of an unconventional computational model, namely “Cellular Automata Ants”. This rather theoretical approach is stressed in rather competitive field, namely clustering. It is well known that the spread of data for almost all areas of life has rapidly increased during the last decades. Nevertheless, the overall process of discovering true knowledge from data demands more powerful clustering techniques to ensure that some of those data are useful and some are not. In this chapter it is presented that Cellular Automata Ants can provide efficient, robust and low cost solutions to data clustering problems using quite small amount of computational resources.

2017-01-01T00:00:00Z