Giorgos Sfikas

An analytic distance metric for Gaussian mixture models with application in image retrieval

In this paper we propose a new distance metric for probability density functions (PDF). The main advantage of this metric is that unlike the popular Kullback-Liebler (KL) divergence it can be computed in closed form when the PDFs are modeled as Gaussian Mixtures (GM). The application in mind for this metric is histogram based image retrieval. We experimentally show that in an image retrieval scenario the proposed metric provides as good results as the KL divergence at a fraction of the computational cost. This metric is also compared to a Bhattacharyya-based distance metric that can be computed in closed form for GMs and is found to produce better results.

Edge preserving spatially varying mixtures for image segmentation

A new hierarchical Bayesian model is proposed for image segmentation based on Gaussian mixture models (GMM) with a prior enforcing spatial smoothness. According to this prior, the local differences of the contextual mixing proportions (i.e. the probabilities of class labels) are Studentpsilas t-distributed. The generative properties of the Students t-pdf allow this prior to impose smoothness and simultaneously model the edges between the segments of the image. A maximum a posteriori (MAP) expectation-maximization (EM) based algorithm is used for Bayesian inference. An important feature of this algorithm is that all the parameters are automatically estimated from the data in closed form. Numerical experiments are presented that demonstrate the superiority of the proposed model for image segmentation as compared to standard GMM-based approaches and to GMM segmentation techniques with ldquostandardrdquo spatial smoothness constraints.

Robust Image Segmentation with Mixtures of Student's t-Distributions

Gaussian mixture models have been widely used in image segmentation. However, such models are sensitive to outliers. In this paper, we consider a robust model for image segmentation based on mixtures of Students t-distributions which have heavier tails than Gaussian and thus are not sensitive to outliers. The t-distribution is one of the few heavy tailed probability density functions (pdf) closely related to the Gaussian, that gives tractable maximum likelihood inference via the Expectation-Maximization (EM) algorithm. Numerical experiments that demonstrate the properties of the proposed model for image segmentation are presented.

Spatially Varying Mixtures Incorporating Line Processes for Image Segmentation

Spatially varying mixture models are characterized by the dependence of their mixing proportions on location (contextual mixing proportions) and they have been widely used in image segmentation. In this work, Gauss-Markov random field (MRF) priors are employed along with spatially varying mixture models to ensure the preservation of region boundaries in image segmentation. To preserve region boundaries, two distinct models for a line process involved in the MRF prior are proposed. The first model considers edge preservation by imposing a Bernoulli prior on the normally distributed local differences of the contextual mixing proportions. It is a discrete line process model whose parameters are computed by variational inference. The second model imposes Gamma prior on the Student’s-t distributed local differences of the contextual mixing proportions. It is a continuous line process whose parameters are also automatically estimated by the Expectation-Maximization (EM) algorithm. The proposed models are numerically evaluated and two important issues in image segmentation by mixture models are also investigated and discussed: the constraints to be imposed on the contextual mixing proportions to be probability vectors and the MRF optimization strategy in the frameworks of the standard and variational EM algorithm.

A survey of document image word spotting techniques

This work reviews the word spotting methods for document indexing.The nature of texts addressed by word spotting techniques is analyzed.The core steps that compose a word spotting system are thoroughly explored.Several boosting mechanisms which enhance the retrieved results are examined.Results achieved by the state of the art imply that there are still goals to be reached. Vast collections of documents available in image format need to be indexed for information retrieval purposes. In this framework, word spotting is an alternative solution to optical character recognition (OCR), which is rather inefficient for recognizing text of degraded quality and unknown fonts usually appearing in printed text, or writing style variations in handwritten documents. Over the past decade there has been a growing interest in addressing document indexing using word spotting which is reflected by the continuously increasing number of approaches. However, there exist very few comprehensive studies which analyze the various aspects of a word spotting system. This work aims to review the recent approaches as well as fill the gaps in several topics with respect to the related works. The nature of texts and inherent challenges addressed by word spotting methods are thoroughly examined. After presenting the core steps which compose a word spotting system, we investigate the use of retrieval enhancement techniques based on relevance feedback which improve the retrieved results. Finally, we present the datasets which are widely used for word spotting, we describe the evaluation standards and measures applied for performance assessment and discuss the results achieved by the state of the art.

GRPOLY-DB: An old Greek polytonic document image database

Recognition of old Greek document images containing polytonic (multi accent) characters is a challenging task due to the large number of existing character classes (more than 270) which cannot be handled sufficiently by current OCR technologies. Taking into account that the Greek polytonic system was used from the late antiquity until recently, a large amount of scanned Greek documents still remains without full test search capabilities. In order to assist the progress of relevant research, this paper introduces the first publicly available old Greek polytonic database GRPOLY-DB for the evaluation of several document image processing tasks. It contains both machine-printed and handwritten documents as well as annotation with ground-truth information that can be used for training and evaluation of the most commou document image processing tasks, i.e.. text line and word segmentation, test recognition, isolated character recognition and word spotting. Results using several representative baseline technologies are also presented in order to help researchers evaluate their methods and advance the frontiers of old Greek document image recognition and word spotting.

Majorization-minimization mixture model determination in image segmentation

A new Bayesian model for image segmentation based on a Gaussian mixture model is proposed. The model structure allows the automatic determination of the number of segments while ensuring spatial smoothness of the final output. This is achieved by defining two separate mixture weight sets: the first set of weights is spatially variant and incorporates an MRF edge-preserving smoothing prior; the second set of weights is governed by a Dirichlet prior in order to prune unnecessary mixture components. The model is trained using variational inference and the Majorization-Minimization (MM) algorithm, resulting in closed-form parameter updates. The algorithm was successfully evaluated in terms of various segmentation indices using the Berkeley image data base.

MR Brain Tissue Classification Using an Edge-Preserving Spatially Variant Bayesian Mixture Model

In this paper, a spatially constrained mixture model for the segmentation of MR brain images is presented. The novelty of this work is an edge-preserving smoothness prior which is imposed on the probabilities of the voxel labels. This prior incorporates a line process, which is modeled as a Bernoulli random variable, in order to preserve edges between tissues. The main difference with other, state of the art methods imposing priors, is that the constraint is imposed on the probabilities of the voxel labels and not onto the labels themselves. Inference of the proposed Bayesian model is obtained using variational methodology and the model parameters are computed in closed form. Numerical experiments are presented where the proposed model is favorably compared to state of the art brain segmentation methods as well as to a spatially varying Gaussian mixture model.

Shape-based word spotting in handwritten document images

In this paper, we address the problem of word spotting using a shape-based matching scheme between segmented word images represented by local contour features. As in a typical query-by-example (QBE) paradigm, a user selects an instance of the query word from the collection of interest and a ranked list of images is returned, based on their similarity with the query. This is accomplished in two steps. The query image is firstly aligned with the test image according to a similarity measure defined on their descriptors and then the aligned images are matched through a deformable non-rigid point matching algorithm. Experiments are carried out on historical handwritten text, written in Greek and English, respectively. Moreover, comparisons with other QBE methods show the efficiency of our system as well as its flexibility in adapting to different scripts.

Zoning Aggregated Hypercolumns for Keyword Spotting

In this paper we present a novel descriptor and method for segmentation-based keyword spotting. We introduce Zoning-Aggregated Hypercolumn features as pixel-level cues for document images. Motivated by recent research in machine vision, we use an appropriately pretrained convolutional network as a feature extraction tool. The resulting local cues are subsequently aggregated to form word-level fixed-length descriptors. Encoding is computationally inexpensive and does not require learning a separate feature generative model, in contrast to other widely used encoding methods (such as Fisher Vectors). Keyword spotting trials on machine-printed and handwritten documents show that the proposed model gives very competitive results.