Color Signature Research Articles

Using Distinctive Colour Signatures to Capture Team Behaviour During Matches

To capture team behaviour, kinematic variables, such as the surface area and the geometrical centre of the team, have been used. Although these variables have shown interesting results in capturing team behaviour, they reduce individual differences to a unique measure, losing the contribution of each player to the team. Using infrared (IR) dyes, it is possible for each player to have a distinctive colour signature to capture their behaviour online. The first stage of this study consisted in the selection of appropriate IR dyes with peak absorbance at different wavelengths (800nm, 910nm, 949nm and 1031nm) that were dissolved in solutions and diluted two times with a 1/5 ratio. To assess the contrast between the solutions, they were applied in a 6x4 chessboard. A unique colour signature was made composing an image from three different charge-coupled devices (CCDs) (one in the visible spectral region and two in the near IR) that were used like the RGB colour system. The IR markers absorbing at shorter wavelengths (800nm and 910nm) have a darker tone in the range 750-900nm and appear white between 900-1900nm. The markers with longer absorption wavelengths have a dark tone in both regions. We calibrated the images from the three CCDs and composed an image in which we give a different colour signature to each square. It is possible to create distinctive colour signatures using the coordinates from three different images.

A SEARCH FOR PLANETARY NEBULAE WITH THE SLOAN DIGITAL SKY SURVEY: THE OUTER REGIONS OF M31

We have developed a method to identify planetary nebula (PN) candidates in imaging data of the Sloan Digital Sky Survey (SDSS). This method exploits the SDSS' five-band sampling of emission lines in PN spectra, which results in a color signature distinct from that of other sources. Selection criteria based on this signature can be applied to nearby galaxies in which PNe appear as point sources. We applied these criteria to the whole area of M31 as scanned by the SDSS, selecting 167 PN candidates that are located in the outer regions of M31. The spectra of 80 selected candidates were then observed with the 2.2m telescope at Calar Alto Observatory. These observations and cross-checks with literature data show that our method has a selection rate efficiency of about 90%, but the efficiency is different for the different groups of PNe candidates. In the outer regions of M31, PNe trace different well-known morphological features like the Northern Spur, the NGC205 Loop, the G1 Clump, etc. In general, the distribution of PNe in the outer region 8<R<20 kpc along the minor axis shows the "extended disk" - a rotationally supported low surface brightness structure with an exponential scale length of 3.21+/-0.14 kpc and a total mass of ~10^10 M_{\sun}, which is equivalent to the mass of M33. We report the discovery of three PN candidates with projected locations in the center of Andromeda NE, a very low surface brightness giant stellar structure in the outer halo of M31. Two of the PNe were spectroscopically confirmed as genuine PNe. These two PNe are located at projected distances along the major axis of ~48 Kpc and ~41 Kpc from the center of M31 and are the most distant PNe in M31 found up to now.

A Hybrid Memetic Algorithm (Genetic Algorithm and Tabu Local Search) with Back-Propagation Classifier for Fish Recognition

In this research our goal is to develop a hybrid approach for optimizing and enhancing back- propagation classifier (BPC) performance using a Memetic Algorithm (Genetic algorithm and Tabu Local Search), thus; Memetic Algorithm used to tune the parameters of the BPC. The proposed hybrid approach (HGATS-BPC) was tested based on fish images recognition. To recognize the pattern of interest (fish object) in the image based on extracted features from color signature. Histogram technique and Gray Level Co-occurrence Matrix (GLCM) used to extract 20 features from fish images based on color signature. The general BPC has several issues to be optimized by Memetic Algorithm such as speed, and easy for running into local minimum. In our study we used 800 fish images for 20 different fish families; each family has a different number of fish types. These images are divided into two datasets: 560 training images and 240 testing images. HGATS-BPC successfully optimized and enhanced the performance of the BPC in term of accuracy and outperformed the traditional BPC and previous methodologies by obtaining more accurate results but with a high cost of computational time compared to the BPC. The overall accuracy obtained by BPC was 85%, while the HGATS-BPC obtained 94% based on 800 fish images. Finally; the HGATS-BPC classifier is able to classify the given fish images into poisonous or non-poisonous fish and classify the poisonous and non-poisonous fish into its family.

Classification and quantitative optical analysis of liquid and solid samples using a mobile phone as illumination source and detector

A mobile phone has been used both as illumination source and image detector for quantitative optical analysis of colored liquid samples (4 different colorants) and solid samples (printed color patterns, plastic beads and colored sand grains). Even though the measurement conditions were far from ideal, because the light source was strongly polychromatic and the illumination was not a collimated light beam with homogeneous light intensity, a logarithmic concentration dependence, in accordance with the Beer–Lambert law, described the data of the colored liquids quite well. By utilizing blue–blue (420–510nm), green–green (480–590nm) and red–red (575–695nm) illumination/detection combinations, each sample could be assigned a unique color signature for classification that agreed with reference absorbance spectra measured with a spectrometer. Quantification of validation samples within a few percent of the actual values was achieved. Also the long-term repeatability of the measurements was investigated and was surprisingly good for such a simple system. Analysis of the colored solid samples was more complex with results being dependent on the morphology and colorimetric properties of the samples.

Target recognitions in multiple-camera closed-circuit television using color constancy

People tracking in crowded scenes from closed-circuit television (CCTV) footage has been a popular and challenging task in computer vision. Due to the limited spatial resolution in the CCTV footage, the color of people’s dress may offer an alternative feature for their recognition and tracking. However, there are many factors, such as variable illumination conditions, viewing angles, and camera calibration, that may induce illusive modification of intrinsic color signatures of the target. Our objective is to recognize and track targets in multiple camera views using color as the detection feature, and to understand if a color constancy (CC) approach may help to reduce these color illusions due to illumination and camera artifacts and thereby improve target recognition performance. We have tested a number of CC algorithms using various color descriptors to assess the efficiency of target recognition from a real multicamera Imagery Library for Intelligent Detection Systems (i-LIDS) data set. Various classifiers have been used for target detection, and the figure of merit to assess the efficiency of target recognition is achieved through the area under the receiver operating characteristics (AUROC). We have proposed two modifications of luminance-based CC algorithms: one with a color transfer mechanism and the other using a pixel-wise sigmoid function for an adaptive dynamic range compression, a method termed enhanced luminance reflectance CC (ELRCC). We found that both algorithms improve the efficiency of target recognitions substantially better than that of the raw data without CC treatment, and in some cases the ELRCC improves target tracking by over 100% within the AUROC assessment metric. The performance of the ELRCC has been assessed over 10 selected targets from three different camera views of the i-LIDS footage, and the averaged target recognition efficiency over all these targets is found to be improved by about 54% in AUROC after the data are processed by the proposed ELRCC algorithm. This amount of improvement represents a reduction of probability of false alarm by about a factor of 5 at the probability of detection of 0.5. Our study concerns mainly the detection of colored targets; and issues for the recognition of white or gray targets will be addressed in a forthcoming study.

Detection of transit timing variations in excess of one hour in theKeplermulti-planet candidate system KOI 806 with the GTC

We report the detection of transit timing variations (TTVs) well in excess of one hour in the Kepler multi-planet candidate system KOI 806. This system exhibits transits consistent with three separate planets -- a Super-Earth, a Jupiter, and a Saturn -- lying very nearly in a 1:2:5 resonance, respectively. We used the Kepler public data archive and observations with the Gran Telescopio de Canarias to compile the necessary photometry. For the largest candidate planet (KOI 806.02) in this system, we detected a large transit timing variation of -103.5$\pm$6.9 minutes against previously published ephemeris. We did not obtain a strong detection of a transit color signature consistent with a planet-sized object; however, we did not detect a color difference in transit depth, either. The large TTV is consistent with theoretical predictions that exoplanets in resonance can produce large transit timing variations, particularly if the orbits are eccentric. The presence of large TTVs among the bodies in this systems indicates that KOI806 is very likely to be a planetary system. This is supported by the lack of a strong color dependence in the transit depth, which would suggest a blended eclipsing binary.

The Hubble Space Telescope colours of high-redshift Population III galaxies with strong Lyα emission

ABSTRACT Population III (pop III) galaxies, made partly or exclusively of metal-free stars, are predicted to exist at high redshifts and may produce very strong Lyα emission. A substantial fraction of these Lyα photons are likely absorbed in the intergalactic medium at z &amp;gt; 6, but recent simulations suggest that significant Lyα emission may be detectable up to z≈ 8.5, i.e. well into the reionization epoch. Here, we argue that high-redshift pop III galaxies with strong Lyα emission can be identified in Hubble Space Telescope imaging data because of their unusual colours. We quantify this effect in some of the filters used in Y-band dropout searches for galaxies at z≈ 8 and find that pop III galaxies with high Lyα fluxes may exhibit much bluer J−H colours at z≈ 8–10 than any normal type of galaxy at these redshifts. This colour signature can arise even if pop III stars account for as little as ∼10−3 to 10−2 of the stellar mass in these galaxies. Some of the anomalously blue objects reported in current Y-band dropout samples do in fact meet the colour criteria for Lyα-emitting pop III galaxies.

Robust Face Detection Based on Knowledge-Directed Specification of Bottom-Up Saliency

This paper presents a novel approach to face detection by localizing faces as the goal-specific saliencies in a scene, using the framework of selective visual attention of a human with a particular goal in mind. The proposed approach aims at achieving human-like robustness as well as efficiency in face detection under large scene variations. The key is to establish how the specific knowledge relevant to the goal interacts with the bottom-up process of external visual stimuli for saliency detection. We propose a direct incorporation of the goal-related knowledge into the specification and/or modification of the internal process of a general bottom-up saliency detection framework. More specifically, prior knowledge of the human face, such as its size, skin color, and shape, is directly set to the window size and color signature for computing the center of difference, as well as to modify the importance weight, as a means of transforming into a goal-specific saliency detection. The experimental evaluation shows that the proposed method reaches a detection rate of 93.4% with a false positive rate of 7.1%, indicating the robustness against a wide variation of scale and rotation.

Summer blooms of diatom-diazotroph assemblages and surface chlorophyll in the North Pacific gyre: A disconnect

[1] The discovery of large summer chlorophyll blooms in oligotrophic regions of the ocean has led to questions about the relationship between these blooms and the frequently cooccurring outburst of nitrogen‐fixing phytoplankton. We compared diatom‐diazotroph assemblage (DDA) abundance to size‐fractionated chlorophyll (chl) and satellite ocean color chlorophyll estimates to evaluate how DDAs affected ocean color estimates in the eastern and central North Pacific gyre at 28–30°N. DDA blooms were dominated by either Hemiaulus hauckii (in the central Pacific in 2003 and the eastern Pacific in 2002) or by Rhizosolenia (eastern Pacific in 2002), both with nitrogen‐fixing Richelia symbionts. The 2002 DDA bloom was measured a week prior to the development of a satellite‐ observed chlorophyll bloom at the same location. In contrast, the 2003 Hemiaulus bloom was not within a clearly defined satellite feature. Although DDA abundance increased 10 4 –10 5 ‐fold relative to the background and they dominated the net plankton (≥5 m mo r >10 mm chl size) fraction, the in situ chl (maximum ≤0.11 mg m −3 ) never reached the 0.15 mg m −3 threshold used to define satellite‐observed chlorophyll blooms in oligotrophic waters. The DDA blooms were not evident in the in situ fluorometer data; however, the blooms occurred within high beam attenuation features observed in the transmissometer data. Trichodesmium was not a component of either diatom bloom although elevated levels of Trichodesmium were observed at two stations where DDAs were not abundant. While DDA blooms and satellite ocean chlorophyll blooms are sometimes coincident, our data do not support that DDAs are the sole source of the satellite‐observed chlorophyll in summertime blooms. DDA blooms are likely underreported in the North Pacific, particularly in the waters west of Hawaii, due to their frequent lack of distinctive ocean color, fluorescence, and chlorophyll signatures. The source of the ocean color signature in the blooms remains elusive, but scattered literature observations suggest that cooccurring members of the near‐surface flora such as the small pennate diatom Mastogloia may play an important role.

Fish Classification Based on Robust Features Extraction From Color Signature Using Back-Propagation Classifier

Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish) in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any problems. Eventually, the classifier was able to categorize the given fish into its cluster and categorize the clustered fish into its poison or nonpoison fish and categorizes the poison and non-poison fish into its family.

Image-based phenotyping: use of colour signature in evaluation of melon fruit colour

Fruit colour, both external and internal, is important because it relates directly to the commercial value of the product. In breeding and in pre- and postharvest studies of fruit colour, an effective method for evaluating colour is needed to replace subjective evaluations by eye. We used a series of data processing and statistical analyses used in content-based image retrieval to evaluate melon flesh colour, and assessed the efficacy of this approach. This method relies on summarizing colour information from images into colour signatures, calculating the earth mover’s distance (EMD) between colour signatures, and multi-dimensional scaling (MDS) based on an EMD matrix. Performing MDS on a set of fruit flesh images revealed important colour features, such as the yellowish-green strength in green-fleshed melons and the relative size of the green and red parts in red-fleshed melons, without the need for an explicit definition of these features. The proportion of variance due to differences among cultivars was higher by MDS than by traditional evaluation, indicating that this new method performed best at detecting colour differences among cultivars. The method provides effective, objective indicators of fruit colour, and shows considerable promise for use in research and breeding programs.

Comparison Between Color Doppler Twinkling Artifact and Acoustic Shadowing for Renal Calculus Detection: An In Vitro Study

To assess the ability of the color Doppler twinkling artifact to detect renal stones relative to acoustic shadowing, we scanned seven uric acid calculi embedded in a tissue mimicking phantom and in sheep kidneys using a high frequency linear array and a standard curved linear array ultrasound scanheads (L12–5 and C5–2; Philips Ultrasound, Bothel, WA, USA). The stones were scanned in and out of focus. The scans were optimized for shadow formation in gray-scale imaging and for color twinkling in color Doppler imaging. The images were analyzed using Image J ( http://rsb.info.nih.gov/ij/). We calculated the contrast to noise ratios (C/N) for the acoustic shadows and the color twinkling artifact compared with background. These measurements were then evaluated using a single factor analysis of variance (ANOVA) and paired two-tailed t tests. With these comparisons, the C/Ns for twinkling were significantly higher than for acoustic shadowing. On average, twinkling produced 19.2 dB greater C/Ns for stones in the phantom and 17.6 dB more for the stones in the kidneys. In addition, ANOVA showed that twinkling is resistant to focusing and scanning frequency differences. The results suggest that the twinkling artifact is a robust method for detecting the presence of renal calculi. The color signature is easier to detect than is acoustic shadowing. Twinkling may be relatively resistant to many of the problems that plague ultrasound examinations for renal stones, i.e., out-of-focus scans that might be caused by beam aberration effects due to patient body habitus. (E-mail: jrubin@med.umich.edu)

Color-Based Image Retrieval Using Perceptually Modified Hausdorff Distance

In most content-based image retrieval systems, the color information is extensively used for its simplicity and generality. Due to its compactness in characterizing the global information, a uniform quantization of colors, or a histogram, has been the most commonly used color descriptor. However, a cluster-based representation, or a signature, has been proven to be more compact and theoretically sound than a histogram for increasing the discriminatory power and reducing the gap between human perception and computer-aided retrieval system. Despite of these advantages, only few papers have broached dissimilarity measure based on the cluster-based nonuniform quantization of colors. In this paper, we extract the perceptual representation of an original color image, a statistical signature by modifying general color signature, which consists of a set of points with statistical volume. Also we present a novel dissimilarity measure for a statistical signature called Perceptually Modified Hausdorff Distance (PMHD) that is based on the Hausdorff distance. In the result, the proposed retrieval system views an image as a statistical signature, and uses the PMHD as the metric between statistical signatures. The precision versus recall results show that the proposed dissimilarity measure generally outperforms all other dissimilarity measures on an unmodified commercial image database.

DAG-based visual interfaces for navigation in indexed video content

Indexing and segmenting of video content by motion, color and texture has been intensively explored leading to a commonly used representation in a storyboard. In this paper, a novel method of visualization of video content is proposed. First of all, the content is segmented into shots, and then a spatio-temporal color signature of shots, based on color distribution in the frames, is proposed. This spatio-temporal color signature serves as a basis for graph clustering and graph visualization tools. Those, integrated in a platform for visualization of huge graphs, Tulip, supply an exciting graph-based navigation interface for multimedia content. The results obtained on feature documentaries are promising.

The color signature of the transit of HD 209458: discrepancies between stellar atmospheric models and observations

Exoplanetary transits produce a double-horned color signature that is distinct from both binaries and blends and can thus be used to separate exoplanets from false positives in transit searches. Color photometry with precision sufficient to detect this signal in transits of HD 209458 is available in the literature. Analysis of these observations reveals that, while the signature does exhibit the expected shape, it is significantly stronger than PHOENIX atmospheric models predict.

Colour™

Colour™

Unusual upwelling event and current reversal off the Italian Adriatic coast in summer 2003

An exceptional upwelling event occurred near the Conero Promontory along the Italian Adriatic coast between 11 and 23 July 2003, as a result of dominant southeasterly sirocco winds. Contemporarily, surface currents off central and southern Italy reversed to the northwest direction. This peculiar dynamic situation happened when the Adriatic river discharge rates were extremely low due to a prolonged dry season. Satellite images of sea surface temperature and chlorophyll concentration and satellite‐tracked drifters revealed that the upwelling event first appeared northwest of the promontory and then progressed to the southeast. Its offshore extension (20–30 km) includes convoluted filament structures. Surface temperature and ocean color signatures are correlated, indicating that the cold‐upwelled water is rich in nutrients. Coldest temperatures are as low as 18–19°C (8°C lower than the open sea). The northwestward currents reached maximum speeds larger than 40 cm/s inshore of the 20 m‐isobath (&lt;10 km from shore).

Spectral gradients for color-based object recognition and indexing

In the past decade color has been developed as an effective cue for object recognition and image indexing. The initial draw of color was how easily object signatures could be captured and compared. Simple histograms of colors radiated from an object proved to be a stable representation of many objects without requiring complex geometric processing to address object pose. While recognition/indexing should depend only on colors intrinsic to object reflectance, a color signature computed from raw image colors is highly sensitive to the color and pose (direction) of incident illumination. Several methods have explored illumination-color invariants, and most of the recent invariants to illumination color and pose employ some form of chromacity representations based on the ratios of image color values or their combinations. This paper presents a comprehensive framework for logarithmic chromacities for the interpretation of image color change due to illumination pose and color. A log-chromacity space is developed from spectral (color) derivatives of logarithmic image irradiance, called spectral gradients, to achieve invariance to global illumination color and pose. In this space, the multiplicative influence of illumination color and pose on image irradiance become additive effects, and this facilitates the analysis of illumination color and pose. A representation from spatial derivatives of spectral gradients, called spectral–spatial gradients is also developed to additionally provide invariance to local variation of illumination color within an image. Experimental results are presented to demonstrate the efficacy of the proposed descriptors.

Vertical structure of the phytoplankton community associated with a coastal plume in the Gulf of Mexico

Low salinity plumes of coastal origin are occasionally found far offshore, where they dis- play a distinct color signature detectable by satellites. The impact of such plumes on carbon fixation and phytoplankton community structure in vertical profiles and on basin wide scales is poorly under- stood. On a research cruise in June 1999, ocean-color satellite-images (Sea-viewing Wide Field-of- view Sensor, SeaWiFS) were used in locating a Mississippi River plume in the eastern Gulf of Mexico. Profiles sampled within and outside of the plume were analyzed using flow cytometry, HPLC pig- ment analysis and primary production using 14 C incorporation. Additionally, RubisCO large subunit (rbcL) gene expression was measured by hybridization of extracted RNA using 3 full-length RNA gene probes specific for individual phytoplankton clades. We also used a combination of RT- PCR/PCR and TA cloning in order to generate cDNA and DNA rbcL clone libraries from samples taken in the plume. Primary productivity was greatest in the low salinity surface layer of the plume. The plume was also associated with high Synechococcus counts and a strong peak in Form IA rbcL expression. Form IB rbcL (green algal) mRNA was abundant at the subsurface chlorophyll maximum (SCM), whereas Form ID rbcL (chromophytic) expression showed little vertical structure. Phyloge- netic analysis of cDNA libraries demonstrated the presence of Form IA rbcL Synechococcus phylo- types in the plume. Below the plume, 2 spatially separated and genetically distinct rbcL clades of Prochlorococcus were observed. This indicated the presence of the high- and low-light adapted clades of Prochlorococcus. A large and very diverse clade of Prymnesiophytes was distributed throughout the water column, whereas a clade of closely related prasinophytes may have dominated at the SCM. These data indicate that the Mississippi river plume may dramatically alter the surface picoplankton composition of the Gulf of Mexico, with Synechococcus displacing Prochlorococcus in the surface waters.

Visualizing Preferential Flow Paths using Ammonium Carbonate and a pH Indicator

Despite their negative charge, anionic dyes are less‐than‐ideal tracers of water flow in soil. A new method is presented here for detecting flow patterns faithfully representing the movement of water flow paths in structured and nonstructured soils. The method is based on application of ammonium carbonate during infiltration, which displays a unique color signature when sprayed with a pH indicator after excavation and exposure of the soil profile along a trench face. We compare its performance with that of the popular Brilliant Blue in a laboratory study, and show that it is a more conservative tracer of the water front. We also illustrate its use in a field experiment to detect preferential flow. In contrast to other methods, ammonium carbonate is inexpensive, nontoxic, and leaves negligible residue.