In this paper, the feasibility is investigated to improve discrimination between different defect and diseases on
raw French fries with multispectral imaging. Four different potato cultivars are selected from which French
Fries are cut. Both multispectral images and RGB color images are classified with linear Bayes normal classifier
and a support vector classifier. The effect of applying different preprocessing techniques on the spectra prior
to classification was also investigated. The classification result are compared with both RGB images and the
full spectra classification results. Experimental results indicate that the support vector classifier gives the best
performance for both multispectral and RGB color images and is less preprocessing dependent. The multispectral
image classification results outperform the RGB color classification results with a factor 15 at best. An explorative
multispectral analysis also shows that latent defects can be detected with multispectral imaging, in contrast with
traditional color imaging.
Fuzzy C-means (FCM) is an unsupervised clustering technique and is often used for the unsupervised segmentation of multivariate images. The segmentation is based on spectral information only and geometrical relationship between neighboring pixels is not used. In this paper, a semi-supervised FCM technique is used to add geometrical information during clustering. Geometrical information can be adapted from the local neighborhood, or from a more extended shape model such as the hough circle detection. Segmentation experiments with the Geometrically Guided FCM (GG-FCM) show improved segmentation above traditional FCM such as more homogeneous regions and less spurious pixels.
A high-speed machine vision system for the quality inspection and grading of potatoes has been developed. The vision system grades potatoes on size, shape and external defects such as greening, mechanical damages, rhizoctonia, silver scab, common scab, cracks and growth cracks. A 3-CCD line-scan camera inspects the potatoes in flight as they pass under the camera. The use of mirrors to obtain a 360-degree view of the potato and the lack of product holders guarantee a full view of the potato. To achieve the required capacity of 12 tons/hour, 11 SHARC Digital Signal Processors perform the image processing and classification tasks. The total capacity of the system is about 50 potatoes/sec. The color segmentation procedure uses Linear Discriminant Analysis (LDA) in combination with a Mahalanobis distance classifier to classify the pixels. The procedure for the detection of misshapen potatoes uses a Fourier based shape classification technique. Features such as area, eccentricity and central moments are used to discriminate between similar colored defects. Experiments with red and yellow skin-colored potatoes have shown that the system is robust and consistent in its classification.
Two versions of a kilometric interferometer with equivalent science capabilities have been studied, one located on the Moon and the other operating as a free-flyer. It has been found that the Moon is not the ideal site for interferometry because of tidal and micro-meteorite induced disturbances, the need for long delay lines and the large temperature swings from day to night. Automatic deployment of the Moon- based interferometer would be difficult and site preparation and assistance by man appear to be essential. The free-flyer would be implemented as a very accurately controlled cluster of independent satellites placed in a halo orbit around the 2nd Lagrange point of the Sun-Earth system. Both versions could attain the required scientific performances and each one needs the same type of metrology control. The free-flyer is intrinsically advantageous because of its reconfiguration flexibility, quasi-unlimited baseline length and observation efficiency (the Moon-based interferometer cannot be operated during the lunar day because of stray light). The free-flyer is better suited for implementation in the near or mid-term future, but the Moon-based version could be considered in the long term when a human presence would permit maintenance and upgrading leading to a longer lifetime with continuous performance enhancement.
We describe a concept for an interferometric space mission dedicated to global (wide-angle) astrometry. The GAIA satellite contains two small (baseline APEQ 3 m) optical interferometers of the Fizeau type, mechanically set at a large and fixed angle to each other. Each interferometer has a field of view of about one degree. Continuous rotation of the whole satellite provides angular connections between the stars passing through the two fields of view. Positions, absolute parallaxes and annual proper motions can be determined with accuracies on the 20 micro-arcsec level. The observing programme may consist of all objects to a limiting magnitude around V = 15-16, including 50 million stars. The GAIA concept, which has been proposed for a Cornerstone Mission within the European Space Agency's long-term science programme, is based on the same general principles as the very successful ESA Hipparcos mission, but takes advantage of the much higher resolution and efficiency permitted by interferometry and modern detector techniques.
The conclusions, recommendations, and target design parameters for a 100-m class optical space interferometer that has been recommended by a study group of the ESA for launching around the year 2005 are summarized. The desirability of an interferometer on the moon, covering the entire wavelength range from UV to sub-mm, with a space interferometer as a possible intermediate step, is considered.