Supervised machine learning algorithm has been extensively studied and applied to different fields of image processing in past decades. This paper proposes a new machine learning algorithm, called margin setting (MS), for restoring images that are corrupted by salt and pepper impulse noise. Margin setting generates decision surface to classify the noise pixels and non-noise pixels. After the noise pixels are detected, a modified ranked order mean (ROM) filter is used to replace the corrupted pixels for images reconstruction. Margin setting algorithm is tested with grayscale and color images for different noise densities. The experimental results are compared with those of the support vector machine (SVM) and standard median filter (SMF). The results show that margin setting outperforms these methods with higher Peak Signal-to-Noise Ratio (PSNR), lower mean square error (MSE), higher image enhancement factor (IEF) and higher Structural Similarity Index (SSIM).
Artificial color uses the projection of the spectrum into two or more broad, overlapping spectral bands to discriminate, pixel by pixel, among user-defined classes of objects. As initially practiced, it used a sequence of hyperspherical regions of the decision space to define class membership. Of course, a hypersphere is just a degenerate hyperellipsoid; thus, exploring the effect of loosening that degeneracy seemed appropriate. Initially, we use two-foci hyperellipsoids with a hyperellipsoidal distance metric to classify pixels with dramatic improvement in performance. We explore the work even further by allowing many foci and noting the effects of increased complexity of the decision surfaces. In the example case, three foci gave superior performance to one or two foci, but four added little improvement.
By definition, HSC (HyperSpectral Camera) images are much richer in spectral data than, say, a COTS (Commercial-Off-The-Shelf) color camera. But data are not information. If we do the task right, useful information can be derived from the data in HSC images. Nature faced essentially the identical problem. The incident light is so complex spectrally that measuring it with high resolution would provide far more data than animals can handle in real time. Nature's solution was to do irreversible POCS (Projections Onto Convex Sets) to achieve huge reductions in data with minimal reduction in information. Thus we can arrange for our manmade systems to do what nature did - project the HSC image onto two or more broad, overlapping curves. The task we have undertaken in the last few years is to develop this idea that we call Artificial Color. What we report here is the use of the measured HSC image data projected onto two or three convex, overlapping, broad curves in analogy with the sensitivity curves of human cone cells. Testing two quite different HSC images in that manner produced the desired result: good discrimination or segmentation that can be done very simply and hence are likely to be doable in real time with specialized computers. Using POCS on the HSC data to reduce the processing complexity produced excellent discrimination in those two cases. For technical reasons discussed here, the figures of merit for the kind of pattern recognition we use is incommensurate with the figures of merit of conventional pattern recognition. We used some force fitting to make a comparison nevertheless, because it shows what is also obvious qualitatively. In our tasks our method works better.
Holographic spectroscopy has been a subject of continuing interest for several decades. Recently, the use of optical filters to allow fast discrimination and segmentation of images has been shown to be very powerful. Conventional filters are restricted to being nonnegative, but that restriction does not apply to holographic filters. So more useful filters can be designed and used holographically to produce a pixel-by-pixel spectral image analyzer.
KEYWORDS: Color vision, Cameras, CCD cameras, Optical filters, Beam splitters, Image processing, Brain, Machine vision, Human vision and color perception, Signal detection
Animals accomplish color vision by characterizing the scene in two or more spectrally overlapping bands, normalizing to minimize brightness effects, computing spectral discriminants (called hues) from the normalized readings, and attributing those hues to the scene with the brightness variations restored in the "colored image." We explore doing the same process in forming images for camera systems. To make experimental testing simpler, we use available spectrally overlapping band cameras—"color" CCD cameras—whose bands show considerable overlap but were not chosen for the task to which we employ them. We use these bands and a very small number of samples from each class of object to form a single artificial color—"green pepper but not snow peas and not carrots." An image of a plate of such vegetables in that artificial color shows the green pepper but not the snow peas and not the carrots.
The features and operation of an electro-optically switched binary optical time delay system are discussed. THe system based on polarization switching using the low cost ferro- electric liquid crystal and polarizing beam splitters provides compactness, low complexity, low insertion loss and arbitrary time delay. We present the design, component selection, fabrication, testing, and evaluation of a prototype.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.