Search

• A new feature extraction method based on Discrete Modal Decomposition is proposed. • Modal features can firstly be computed as the DMD coordinates of the image. • Modal features can secondly be computed using the DMD as a local transform process. • Experimental tests show the relevance of the method on a texture classification task, with lower extraction times than state-of-the art methods. Feature extraction is a key step in image processing for pattern recognition and machine learning processes. Its purpose lies in reducing the dimensionality of the input data through the computing of features which accurately describe the original information. In this article, a new feature extraction method based on Discrete Modal Decomposition (DMD) is introduced, to extend the group of space and frequency based features. These new features are called modal features. Initially aiming to decompose a signal into a modal basis built from a vibration mechanics problem, the DMD projection is applied to images in order to extract modal features with two approaches. The first one, called full scale DMD, consists in exploiting directly the decomposition resulting coordinates as features. The second one, called filtering DMD, consists in using the DMD modes as filters to obtain features through a local transformation process. Experiments are performed on image texture classification tasks including several widely used data bases, compared to several classic feature extraction methods. We show that the DMD approach achieves good classification performances, comparable to the state of the art techniques, with a lower extraction time. [ABSTRACT FROM AUTHOR]

The quality control of mechanical parts is generally performed on a coordinate measuring machine (CMM). The choice of the number of points to be sampled, their distributions and their positions on the surface, as well as the association criterion remains unresolved. This paper studies the variation of the flatness defect with regard to the number of palpated points. The methodology begins by sampling a cloud of points on a CMM. Then, a modal analysis study is carried out in order to generate a modal surfaces (digitally deformed). Insertion of the coordinate cloud points of these modal surfaces in the GEOVERIF software will allow estimation of the flatness defect. The results of the measured flatness by the three fitting criteria (minimum zone, least squares and minimum volume) are compared. [ABSTRACT FROM AUTHOR]

Quality control is a key requirement of the Fourth Industrial Revolution, especially in manufacturing. For high-value technical parts, the geometric and appearance quality need to be guaranteed. The control of the part, directly on the manufacturing line, can be achieved with noncontact sensors. Visible spectrum imaging is commonly used. However, more information could be obtained from broader spectrum imaging and from the degree of linear polarization of the light from the part. We investigate polarimetry. We have developed a simple polarimetric imaging system to verify whether linear polarization is capable of amplifying geometric and appearance defects. We evaluate the use of this polarimetric imager given the industrial constraints of injection molding. We compare the performances of different machine learning pipelines with hand-crafted feature extraction and deep transfer learning. With its industrial robustness, polarimetry could be a valuable addition to noncontact imagers for geometric and appearance quality control of plastic molded parts. [ABSTRACT FROM AUTHOR]