Pierre Courtellemont

Multi-Bank Check Recognition System: Consideration on the Numeral Amount Recognition Module

This paper presents a complete numeral amount recognition module which is integrated in an automatic system aimed at reading all types of French checks. This module is combined with an automatic reading system of literal amounts. This complete working system, called LIRECheques, is developed by MATRA MS&I and is now in advanced test at SERINTEL, a pilot site. Two aspects of the numeral amount recognition system are particularly emphasized: the numeral recognition stage itself and the syntactic analysis stage. The numeral recognition module relies on a combination of two individual classifiers, the first one is based on concavity measurements, the second one on both statistical and structural features. The syntactic analysis, called syntactic/contextual analysis, is combined with contextual information to take into account the segmentation behaviour and the presence of literal entities in the numeral amount. We demonstrate that very good performances can be obtained on digits such as those extracted from numeral amounts since a substitution rate of 0.06% while still preserving a recognition rate of near 87% can be achieved. As for the syntactic/contextual analysis stage, results obtained on a test set (containing checks from more than 40 different banks and 15/ of typed checks, thus being a good representation of the real tests realized on site) show clearly that introduction of contextual information in association with syntactic analysis allows to process much more numeral amounts than a simple syntactic analysis and increases perceptibility of the recognition rate.

The Color Monogenic Signal: Application to Color Edge Detection and Color Optical Flow

The aim of this paper is to define an extension of the analytic signal for a color image. We generalize the construction of the so-called monogenic signal to mappings with values in the vectorial part of the Clifford algebra ℝ5,0. Solving a Dirac equation in this context leads to a multiscale signal (relatively to the Poisson scale-space) which contains both structure and color information. The color monogenic signal can be used in a wide range of applications. Two examples are detailed: the first one concerns a multiscale geometric segmentation with respect to a given color; the second one is devoted to the extraction of the optical flow from moving objects of a given color.

Automatic analysis of the structuring of children's drawings and writing

The aim of this work was to build an objective tool for the detection of graphomotor difficulties involving disorders in the writing of children. We outline some characteristics of layouts, describing the automation level of the graphic activity. We have defined exercises, like copying figures or writing sentences under different conditions that allowed us to measure simple aspects of graphomotor skill up to complex ones. A tool was conceived which was able to automatically extract low-level and high-level primitives. Based on such descriptors, we focus on the analysis of the temporal structuring of two particular drawings. In the final part, we present the method we used to select features that can describe the automation level of the graphic activity and we show that, in most cases, these features allow to discriminate children with academic difficulties.

Recent progress in automatic digital restoration of color motion pictures

The motion pictures represent a precious cultural heritage, however the chemical support on which they are recorded becomes unstable with time, unless they are stored at low temperatures. Some defects affecting color movies, such as bleaching, are out of reach of photochemical restoration means, digital restoration is hence unquestionable. We propose an original automatic technique for faded image correction. Bleaching results in damage to one or two chromatic layers, giving a drab image with poor saturation and an overall color cast. Our automatic fading correction technique consists in reviving the colors of the image (color enhancement), then in balancing the colors of the image.

Alive Fishes Species Characterization from Video Sequences

This article presents a method suitable for the characterization of fishes evolving in a basin. It is based on the analysis of video sequences obtained from a fixed camera. One of the main difficulties of analyzing natural scenes acquired from an aquatic environment is the variability of illumination. This disturbs every phase of the whole process. We propose to make each task more robust. In particular, we propose to use a clustering method allowing to provide species parameters estimates that are less sensitive to outliers.

The Color Monogenic Signal: A new framework for color image processing. application to color optical flow

We use in this paper the formalism of Clifford algebras to define the so-called Color Monogenic Signal associated to a color image. It consists in a function with values in the Clifford algebra ℝ5,0 that codes color (RGB) and geometric structures information. Using geometric calculus, a notion of local color phase is introduced, generalizing the one for gray level image. As an example of application, a color optical flow robust against noise and brightness variation is provided. It extends the gray level CLG method to color images. The results we obtain on images from the Middleburry database show the relevance of the proposed approach.

Handwritten word recognition by image segmentation and hidden Markov models

In this paper, we propose a method for the recognition of handwritten literal amount on various bank checks. We present the pre-processing of the original 256 gray-levels image, containing inhomogeneous background, and the locating of the handwritten information. For recognition of the amount, we choose a Markovian approach, which is first applied to the sequences of words. The first results allow to consider an extension of the method to the sequences of graphems in words in order to improve the recognition rate.<<ETX>>

School level recognition from children's drawings and writing

This paper presents part of the work aiming at building a tool for the detection of graphomotor difficulties involving disorders in the writing of children. We have defined an experimental protocol, containing exercises such as copying figures or writing sentences under different conditions. It allows to measure simple aspects of graphomotor skill up to complex ones. A great number of features were obtained from on-line childrens productions. We focus on the method used to select low-level features that can describe the automation level of graphic activity. It is based on hierarchical clustering of features and sequential forward selection. Every exercise is represented by two relevant features at least. We show that, in most cases, the selected features allow to recognize the school level of children having regular schooling but to discriminate children with scholar difficulties as well.

A Metric and Multiscale Color Segmentation Using the Color Monogenic Signal

In this paper, we use the formalism of Clifford algebras to extend the so-called Monogenic Signal to color images. This extension consists in a function with values in the Clifford algebra ?5,0 that encodes color as well as geometric structure information. Using geometric calculus, such a mathematical object can be used to extend classical concepts of signal processing (filtering, Fourier Transform...) to color images in a consistent manner. Regarding this paper, a local color phase is introduced, which generalizes the one for grayscale image. As an example of application, we provide a new method for color segmentation. Based on our phase definition and the multiscale aspect of the Color Monogenic Signal, we provide a metric approach using differential geometry which reveals relevant on the Berkeley Image Dataset.

Feature point extraction in compressed domain

This document presents several approaches to extract interest points within compressed images (based on DCT compression methods). The goal is to minimize the stages and/or the calculation costs for image sequence indexing tasks or database retrieval from a significant MPEG file repository. Initially, only the fixed images (I-Frames) are take under consideration, motion will be integrated in further research. The traditional invariant feature points (Harris corner points, points with remarquable principal curvatures) are extracted from images using a gradient estimate (first order derivative) or the Laplacian (second-order derivative) of an image. So the first part of this paper handles in detail the derivation of the signal from DCT blocks. The trials to implement feature points detection as close as possible to the DCT coefficient are explained. Results provided by our last DCT-blockwise curvature estimatiorare also shown.