The Experts below are selected from a list of 6996 Experts worldwide ranked by ideXlab platform

Beatriz Marcotegui - One of the best experts on this subject based on the ideXlab platform.

  • Adaptive scene-text binarization on images captured by smartphones
    Image Processing IET, 2016
    Co-Authors: Amira Belhedi, Beatriz Marcotegui
    Abstract:

    We address, in this paper, a new adaptive binarization method on images captured by smartphones. This work is part of an application for visually impaired people assistance, that aims at making text information accessible to people who cannot read it. The main advantage of the proposed method is that the windows underlying the local thresh-olding process are automatically adapted to the image content. This avoids the problematic parameter setting of local thresholding approaches, difficult to adapt to a heterogeneous database. The adaptive windows are extracted based on ultimate opening (a Morphological Operator) and then used as thresholding windows to perform a local Otsu's algorithm. Our method is evaluated and compared with the Niblack, Sauvola, Wolf, TMMS and MSER methods on a new challenging database introduced by us. Our database is acquired by visually impaired people in real conditions. It contains 4000 annotated characters (available online for research purposes). Experiments show that the proposed method outperforms classical binarization methods for degraded images such as low-contrasted or blurred images, very common in our application.

  • Text detection in street level images
    Pattern Analysis and Applications, 2013
    Co-Authors: Jonathan Fabrizio, Beatriz Marcotegui, Matthieu Cord
    Abstract:

    Text detection system for natural images is a very challenging task in Computer Vision. Image acquisition introduces distortion in terms of perspective, blurring, illumination, and characters may have very diff erent shape, size, and color. We introduce in this article a full text detection scheme. Our architecture is based on a new process to combine a hypothesis generation step to get potential boxes of text and a hypothesis validation step to filter false detections. The hypothesis generation process relies on a new efficient segmentation method based on a Morphological Operator. Regions are then filtered and classi ed using shape descriptors based on Fourier, Pseudo Zernike moments and an original polar descriptor, which is invariant to rotation. Classi cation process relies on three SVM classi ers combined in a late fusion scheme. Detected characters are finally grouped to generate our text box hypotheses. Validation step is based on a global SVM classi cation of the box content using dedicated descriptors adapted from the HOG approach. Results on the well-known ICDAR database are reported showing that our method is competitive . Evaluation protocol and metrics are deeply discussed and results on a very challenging street-level database are also proposed.

  • Text segmentation in natural scenes using toggle-mapping
    2009
    Co-Authors: Jonathan Fabrizio, Beatriz Marcotegui, Matthieu Cord
    Abstract:

    We offer, in this paper, a new method to segment text in natural scenes. This method is based on the use of a Morphological Operator: the Toggle Mapping. The efficiency of the method is illustrated and the method is compared, according to various criteria, with common methods issued from the state of the art. This comparison shows that our method gives better results and is faster than the state of the art methods. Our method reduces also the number of segmented regions. This can lead to time saving in a complete scheme (executing time of multiple processing steps usually depends on the number of regions) and proves that our algorithm is more relevant.

  • TEXT EXTRACTION FROM STREET LEVEL IMAGES
    2009
    Co-Authors: Jonathan Fabrizio, Matthieu Cord, Beatriz Marcotegui
    Abstract:

    We offer in this article, a method for text extraction in images issued from city scenes. This method is used in the French iTowns project (iTowns ANR project, 2008) to automatically enhance cartographic database by extracting text from geolocalized pictures of town streets. This task is difficult as 1. text in this environment varies in shape, size, color, orientation... 2. pictures may be blurred, as they are taken from a moving vehicle, and text may have perspective deformations, 3. all pictures are taken outside with various objects that can lead to false positives and in unconstrained conditions (especially light varies from one picture to the other). Then, we can not make the assumption on searched text. The only supposition is that text is not handwritten . Our process is based on two main steps: a new segmentation method based on Morphological Operator and a classification step based on a combination of multiple SVM classifiers. The description of our process is given in this article. The efficiency of each step is measured and the global scheme is illustrated on an example

  • Ultimate attribute opening segmentation with shape information
    2009
    Co-Authors: Jorge Hernandez, Beatriz Marcotegui
    Abstract:

    In this paper, a method for Morphological segmentation using shape information is presented. This method is based on a Morphological Operator named ultimate attribute opening (UAO). Our approach considers shape information to favor the detection of specific shapes. The method is validated in the framework of two applications: façade analysis and scene-text detection. The experimental results show that our approach is more robust than the standard UAO.

Terrance E. Boult - One of the best experts on this subject based on the ideXlab platform.

  • statistical characterization of Morphological Operator sequences
    European Conference on Computer Vision, 2002
    Co-Authors: Xiang Gao, Visvanathan Ramesh, Terrance E. Boult
    Abstract:

    Detection followed by Morphological processing is commonly used in machine vision. However, choosing the Morphological Operators and parameters is often done in a heuristic manner since a statistical characterization of their performance is not easily derivable. If we consider a morphology Operator sequence as a classifier distinguishing between two patterns, the automatic choice of the Operator sequence and parameters is possible if one derives the misclassification distribution as a function of the input signal distributions, the Operator sequence, and parameter choices. The main essence of this paper is the illustration that misclassification statistics, the distribution of bit errors measured by the Hamming distance, can be computed by using an embeddable Markov chain approach. License plate extraction is used as a case study to illustrate the utility of the theory on real data.

  • ECCV (4) - Statistical Characterization of Morphological Operator Sequences
    Computer Vision — ECCV 2002, 2002
    Co-Authors: Visvanathan Ramesh, Terrance E. Boult
    Abstract:

    Detection followed by Morphological processing is commonly used in machine vision. However, choosing the Morphological Operators and parameters is often done in a heuristic manner since a statistical characterization of their performance is not easily derivable. If we consider a morphology Operator sequence as a classifier distinguishing between two patterns, the automatic choice of the Operator sequence and parameters is possible if one derives the misclassification distribution as a function of the input signal distributions, the Operator sequence, and parameter choices. The main essence of this paper is the illustration that misclassification statistics, the distribution of bit errors measured by the Hamming distance, can be computed by using an embeddable Markov chain approach. License plate extraction is used as a case study to illustrate the utility of the theory on real data.

Fernand Meyer - One of the best experts on this subject based on the ideXlab platform.

  • First departure algorithms and image decompositions into peaks and wells
    IEEE Journal of Selected Topics in Signal Processing, 2012
    Co-Authors: Fernand Meyer
    Abstract:

    An image may be decomposed as a difference between an image of peaks and an image of wells. This decomposition depends upon the point of view, an arbitrary set from where the image is considered: a peak appears as a peak if it is impossible to reach it starting from any position in the point of view without climbing. A well cannot be reached without descending. To each particular point of view corresponds a different decomposition. The decomposition is reversible. If one applies a Morphological Operator to the peaks-and-wells components before applying the inverse transform, one gets a new, transformed image. The decomposition is produced by a generalized shortest path algorithm on weighted graphs; the node weights represent departure times and the arc weights represent traversal times. If a train starts at each node at a time equal to the weight of this node and crosses each arc in a time equal to the weight of the node, the outcome of the algorithm is the earliest departure time of a train from each node: equal to the initial node weight if no other train arrives earlier, and equal to the earliest train coming from another node otherwise. Reconstruction closings or floodings also belong to this family of first departure algorithms. A number of applications illustrate the method.

  • Image decompositions and transformations as peaks and wells
    2011
    Co-Authors: Fernand Meyer
    Abstract:

    An image may be decomposed as a difference between an image of peaks and an image of wells. Applying a Morphological Operator to these two components before reconstructing a final image produces interesting filters for grey tone or binary images. This decomposition depends upon the point of view from where the image is considered.

Xiang Gao - One of the best experts on this subject based on the ideXlab platform.

  • statistical characterization of Morphological Operator sequences
    European Conference on Computer Vision, 2002
    Co-Authors: Xiang Gao, Visvanathan Ramesh, Terrance E. Boult
    Abstract:

    Detection followed by Morphological processing is commonly used in machine vision. However, choosing the Morphological Operators and parameters is often done in a heuristic manner since a statistical characterization of their performance is not easily derivable. If we consider a morphology Operator sequence as a classifier distinguishing between two patterns, the automatic choice of the Operator sequence and parameters is possible if one derives the misclassification distribution as a function of the input signal distributions, the Operator sequence, and parameter choices. The main essence of this paper is the illustration that misclassification statistics, the distribution of bit errors measured by the Hamming distance, can be computed by using an embeddable Markov chain approach. License plate extraction is used as a case study to illustrate the utility of the theory on real data.

Matthieu Cord - One of the best experts on this subject based on the ideXlab platform.

  • Text detection in street level images
    Pattern Analysis and Applications, 2013
    Co-Authors: Jonathan Fabrizio, Beatriz Marcotegui, Matthieu Cord
    Abstract:

    Text detection system for natural images is a very challenging task in Computer Vision. Image acquisition introduces distortion in terms of perspective, blurring, illumination, and characters may have very diff erent shape, size, and color. We introduce in this article a full text detection scheme. Our architecture is based on a new process to combine a hypothesis generation step to get potential boxes of text and a hypothesis validation step to filter false detections. The hypothesis generation process relies on a new efficient segmentation method based on a Morphological Operator. Regions are then filtered and classi ed using shape descriptors based on Fourier, Pseudo Zernike moments and an original polar descriptor, which is invariant to rotation. Classi cation process relies on three SVM classi ers combined in a late fusion scheme. Detected characters are finally grouped to generate our text box hypotheses. Validation step is based on a global SVM classi cation of the box content using dedicated descriptors adapted from the HOG approach. Results on the well-known ICDAR database are reported showing that our method is competitive . Evaluation protocol and metrics are deeply discussed and results on a very challenging street-level database are also proposed.

  • Text segmentation in natural scenes using toggle-mapping
    2009
    Co-Authors: Jonathan Fabrizio, Beatriz Marcotegui, Matthieu Cord
    Abstract:

    We offer, in this paper, a new method to segment text in natural scenes. This method is based on the use of a Morphological Operator: the Toggle Mapping. The efficiency of the method is illustrated and the method is compared, according to various criteria, with common methods issued from the state of the art. This comparison shows that our method gives better results and is faster than the state of the art methods. Our method reduces also the number of segmented regions. This can lead to time saving in a complete scheme (executing time of multiple processing steps usually depends on the number of regions) and proves that our algorithm is more relevant.

  • TEXT EXTRACTION FROM STREET LEVEL IMAGES
    2009
    Co-Authors: Jonathan Fabrizio, Matthieu Cord, Beatriz Marcotegui
    Abstract:

    We offer in this article, a method for text extraction in images issued from city scenes. This method is used in the French iTowns project (iTowns ANR project, 2008) to automatically enhance cartographic database by extracting text from geolocalized pictures of town streets. This task is difficult as 1. text in this environment varies in shape, size, color, orientation... 2. pictures may be blurred, as they are taken from a moving vehicle, and text may have perspective deformations, 3. all pictures are taken outside with various objects that can lead to false positives and in unconstrained conditions (especially light varies from one picture to the other). Then, we can not make the assumption on searched text. The only supposition is that text is not handwritten . Our process is based on two main steps: a new segmentation method based on Morphological Operator and a classification step based on a combination of multiple SVM classifiers. The description of our process is given in this article. The efficiency of each step is measured and the global scheme is illustrated on an example