Cédric Lemaitre

Detection and matching of curvilinear structures

We propose an approach to curvilinear and wiry object detection and matching based on a new curvilinear region detector (CRD) and a shape context-like descriptor (COH). Standard methods for local patch detection and description are not directly applicable to wiry objects and curvilinear structures, such as roads, railroads and rivers in satellite and aerial images, vessels and veins in medical images, cables, poles and fences in urban scenes, stems and tree branches in natural images, since they assume the object is compact, i.e. that most elliptical patches around features cover only the object. However, wiry objects often have no flat parts and most neighborhoods include both foreground and background. The detection process is first evaluated in terms of segmentation quality of curvilinear regions. The repeatability of the detection is then assessed using the protocol introduced in Mikolajczyk et al. [1]. Experiments show that the CRD is at least as robust as to several image acquisition conditions changes (viewpoint, scale, illumination, compression, blur) as the commonly used affine-covariant detectors. The paper also introduces an image collection containing wiry objects and curvilinear structures (the W-CS dataset).

Colour Object recognition combining Motion Descriptors, Zernike Moments and Support Vector Machine

Fourier descriptors have been used successfully in the past to grey-level images, rigid bodied object. Here we used motion descriptors (MD) introduced recently by Gauthier et al., combined with Zernike Moments (ZM), in order to perform a recognition task in colour images. The feature vector for the MD obtained for each object appears to be unique and can be used for shape recognition. The MD, alone or combined with ZM, are used as an input of a support vector machine (SVM) based classifier. We illustrate results on three available datasets: ORL faces database, COIL-100, which consists of 3D objects and A R faces

Combining text/image in wikipediaMM task 2009

This paper reports our multimedia information retrieval experiments carried out for the ImageCLEF Wikipedia task 2009. We extend our previous multimedia model defined as a vector of textual and visual information based on a bag of words approach [6]. We extract additional textual information from the original Wikipedia articles and we compute several image descriptors (local colour and texture features). We show that combining linearly textual and visual information significantly improves the results.

Definition of a model-based detector of curvilinear regions

This paper describes a new approach for detection of curvilinear regions. These features detection can be useful for any matching based algorithm such as stereoscopic vision. Our detector is based on curvilinear structure model, defined observing the real world. Then, we propose a multi-scale search algorithm of curvilinear regions and we report some preliminary results.

Finding Invariants of Group Actions on Function Spaces, a General Methodology from Non-Abelian Harmonic Analysis

In this paper, we describe a general method using the abstract non-Abelian Fourier transform to construct “rich” invariants of group actions on functional spaces.

Hardware Implementation of Moment Functions in a CMOS Retina: Application to Pattern Recognition

We present in this paper a method for implementing moment functions in a CMOS retina for object localization, and pattern recognition and classification applications. The method is based on the use of binary patterns and it allows the computation of different moment functions such as geometric and Zernike moments of any orders by an adequate choice of the binary patterns. The advantages of the method over other methods described in the literature are that it is particularly suitable for the design of a programmable retina circuit where moment functions of different orders are obtained by simply loading the correct binary patterns into the memory devices implemented on the circuit. The moment values computed by the method are approximate values, but we have verified that in spite of the errors the approximate values are significant enough to be applied to classical shape localization and shape representation and description applications.

A hardware architecture for fast video object recognition using SVM and Zernike moments

An architecture for fast video object recognition is proposed. This architecture is based on an approximation of featureextraction function: Zernike moments and an approximation of a classification framework: Support Vector Machines (SVM). We review the principles of the moment-based method and the principles of the approximation method: dithering. We evaluate the performances of two moment-based methods: Hu invariants and Zernike moments. We evaluate the implementation cost of the best method. We review the principles of classification method and present the combination algorithm which consists in rejecting ambiguities in the learning set using SVM decision, before using the learning step of the hyperrectangles-based method. We present result obtained on a standard database: COIL-100. The results are evaluated regarding hardware cost as well as classification performances.