MAROT , Julien

The food industry is in constant demand of performing and easy to implement Non-Destructive Evaluation NDE techniques. In this paper, we tackle the problem of the automatic inspection of fruits and more specifically, the sorting of healthy and damaged fruits, taking apples and peaches as examples. In a recent work, we have explained how to...

Based on various applications involving millimeter- wave (mm-wave) imaging, we highlight the importance of processing the measurements prior to their classification with Artificial Intelligence (AI) algorithms. The key point for enabling a good classification accuracy is to obtain the same structure for the training and the test datasets....

To avoid economic losses due to fruit diseases, farmers need to control quality before harvesting and thus before the fruit reaches the consumer. In this paper, we present a proof of concept for damages detection in fruit with a minimum number of measurement points. By using the Grey Wolf Optimizer, the number of measurement points drops from...

This work tackles the problem of the detection of slow moving targets with a FM-CW mm-Wave radar operating in the frequency band of automotive radars. Gradient-based and Principal Component Analysis methods were developped.

L'identification des techniques de fabrication des poteries préhistoriques est l'un des moyens les plus précieux pour tracer la carte des mobilités humaines avant l'invention de l'écriture. Nous nous intéressons ici au peuplement de la Méditerranée occidentale à travers le tri de tessons de poterie. L'objectif est de différencier deux...

Fighting fruit diseases, farmers are in demand of an automatic Non Destructive Evaluation system for detecting the damages in fruits. In this paper, we propose a proof of concept using amplitude-only measurements associated with a Machine learning Algorithm of linear Support Vector Machine type, for sorting healthy from damaged peaches hidden...

The purpose of this work is to perform co-engineering of an object classification system including both a radar sensor and a software of image processing. We aim at the smallest possible false recognition rate, considering three classes of imaged objects. For this we retain five relevant parameters which impact the recognition performances. We...

The purpose of this work is to perform the joint design of a classification system including both a radar sensor and an image processing software. Experimental data were generated with a three-dimensional scanner. The criterion which rules the design is the false recognition rate, which should be as small as possible. The classifier involved is...

In this paper we present a complete process that goes from measurements to image extraction with the objective to help radar designers to set their system specifications. We focus on objects of interest for security scanners and therefore choose to perform the tests on a ceramic knife and a fake gun made of aluminum. We highlight polarization...

In order to map the migration and introduction of farming into Europe during the 7th and 6th millennia Before Common Era, archaeologists have made a connection between the study of pottery and farming migration. We are interested here in the classification of pottery into coiling and spiral types, based on their manufacturing techniques. To...

Fast and efficient non-Destructive evaluation methods for food control is still an ongoing field of research. Wehave recently proposed to combine W-band imaging with nonlinear SVM classifier to sort out healthy from damaged fruits for a single variety of fruits. We have tested it on apples and peaches separately with a mean accuracy of 96%. We...