Eye Detectors Research Articles

Assessment of Meat Content and Foreign Object Detection in Cattle Meatballs Using Ultrasonography, Radiography, and Electrical Impedance Tomography Imaging.

Meat content and physically hazardous contaminants in the internal section of meatballs cannot be detected by the naked eye or surface detectors. This study is aimed at analyzing the meat content of cattle meatballs and detecting foreign objects using ultrasonography (USG), digital radiography (DR), and electrical impedance tomography (EIT). Meatballs were produced using four different meat formulations (0%, 25%, 50%, and 75% meat) and three treatments (no preservative (control), borax, and formalin preservatives). Cast iron and plastic beads were used as models of foreign objects embedded in the samples. The echogenicity, opacity, and resistivity values of each sample were evaluated and compared across groups. The results showed that the shelf life of the control meatballs was shorter than that of meatballs with preservatives. The echogenicity and opacity values for the different meat formulations were hypoechoic in USG and grey in DR. USG was able to distinguish between control and preservative-treated meatballs but could not differentiate meat content and detect foreign objects. Conversely, DR effectively assessed meat content and detected iron-based foreign objects, while EIT showed higher resistivity values for iron and plastic beads compared to the meatball bodies.

Real-Time Face Detection and Recognition in Complex Background

This paper provides efficient and robust algorithms for real-time face detection and recognition in complex backgrounds. The algorithms are implemented using a series of signal processing methods including Ada Boost, cascade classifier, Local Binary Pattern (LBP), Haar-like feature, facial image pre-processing and Principal Component Analysis (PCA). The Ada Boost algorithm is implemented in a cascade classifier to train the face and eye detectors with robust detection accuracy. The LBP descriptor is utilized to extract facial features for fast face detection. The eye detection algorithm reduces the false face detection rate. The detected facial image is then processed to correct the orientation and increase the contrast, therefore, maintains high facial recognition accuracy. Finally, the PCA algorithm is used to recognize faces efficiently. Large databases with faces and non-faces images are used to train and validate face detection and facial recognition algorithms. The algorithms achieve an overall true-positive rate of 98.8% for face detection and 99.2% for correct facial recognition.

Eye detection in a facial image under pose variation based on multi-scale iris shape feature

The accurate location of eyes in a facial image is important to many human facial recognition-related applications, and has attracted considerable research interest in computer vision. However, most prevalent methods are based on the frontal pose of the face, where applying them to non-frontal poses can yield erroneous results.In this paper, we propose an eye detection method that can locate the eyes in facial images captured at various head poses. Our proposed method consists of two stages: eye candidate detection and eye candidate verification. In eye candidate detection, eye candidates are obtained by using multi-scale iris shape features and integral image. The size of the iris in face images varies as the head pose changes, and the proposed multi-scale iris shape feature method can detect the eyes in such cases. Since it utilizes the integral image, its computational cost is relatively low. The extracted eye candidates are then verified in the eye candidate verification stage using a support vector machine (SVM) based on the feature-level fusion of a histogram of oriented gradients (HOG) and cell mean intensity features.We tested the performance of the proposed method using the Chinese Academy of Sciences' Pose, Expression, Accessories, and Lighting (CAS-PEAL) database and the Pointing'04 database. The results confirmed the superiority of our method over the conventional Haar-like detector and two hybrid eye detectors under relatively extreme head pose variations.

Impact of eye detection error on face recognition performance

The locations of the eyes are the most commonly used features to perform face normalisation (i.e. alignment of facial features), which is an essential preprocessing stage of many face recognition systems. In this study, the authors study the sensitivity of open source implementations of five face recognition algorithms to misalignment caused by eye localisation errors. They investigate the ambiguity in the location of the eyes by comparing the difference between two independent manual eye annotations. They also study the error characteristics of automatic eye detectors present in two commercial face recognition systems. Furthermore, they explore the impact of using different eye detectors for training/enrolment and query phases of a face recognition system. These experiments provide an insight into the influence of eye localisation errors on the performance of face recognition systems and recommend a strategy for the design of training and test sets of a face recognition algorithm.

Confidence Measure Using Composite Features for Eye Detection in a Face Recognition System

We propose a new confidence measure to evaluate the eye detection results and combine two different eye detectors. The confidence for the results of eye detection is measured by the distances from the test sample and the positive samples, where the distance is calculated in the composite feature space. By using the proposed confidence measure, we construct a hybrid detector by combining two different detectors, which are complementary to each other. The experimental results show that the proposed detector provides more accurate eye detection results and consequently results in better face recognition rates compared to when using an individual eye detector.

Combining Face and Eye Detectors in a High- Performance Face-Detection System

A combined face and eye detector system based on multiresolution local ternary patterns and local phase quantization descriptors can achieve noticeable performance improvements by extracting features locally.

Competitive Combination of Multiple Eye Detection and Tracking Techniques

Reliable detection and tracking of eyes is an important requirement for attentive user interfaces. In this paper, we present an innovative approach to the problem of eye tracking. A number of traditional eye detectors, chosen for their own properties, are combined by two different competitive schemes with the aim to obtain a higher degree of robustness and reliability. To illustrate our work and validate our competitive combination approach, we introduce a proof-of-concept single-camera remote eye tracker and discuss its implementation and the produced experimental results.

On origin of ultra high energy cosmic rays

Propagation of UHE protons through CMB radiation leaves the imprint on energy spectrum in the form of Greisen–Zatsepin–Kuzmin (GZK) cutoff, bump (pile-up protons) and dip. The dip is a feature in energy range 1×1018–4×1019 eV, caused by electron-positron pair production on CMB photons. Calculated for power-law generation spectrum with index γ g =2.7, the shape of the dip is confirmed with high accuracy by data of Akeno—AGASA, HiRes, Yakutsk and Fly’s Eye detectors. The predicted shape of the dip is robust: it is valid for the rectilinear and diffusive propagation, for different discretenesses in the source distribution, for local source overdensity and deficit etc. This property of the dip allows us to use it for energy calibration of the detectors. The energy shift λ for each detector is determined by minimum χ 2 in comparison of observed and calculated dip. After this energy calibration the absolute fluxes, measured by AGASA, HiRes and Yakutsk detectors remarkably coincide in energy region 1×1018–1×1020 eV. Below the characteristic energy E c ≈1×1018 eV the spectrum of the dip flattens for both diffusive and rectilinear propagation, and more steep galactic spectrum becomes dominant at E<E c . The energy of transition E tr<E c approximately coincides with the position of the second knee E 2kn , observed in the cosmic ray spectrum. The dip-induced transition from galactic to extragalactic cosmic rays at the second knee is compared with traditional model of transition at ankle, the feature observed at energy ∼1×1019 eV.

Propagation and origin of ultra high-energy cosmic rays

Propagation of UHE protons through CMB radiation leaves the imprint on energy spectrum in the form of Greisen–Zatsepin–Kuzmin (GZK) cutoff, bump (pile-up protons) and dip. The dip is a feature in energy range 1 × 10 18–4 × 10 19 eV, caused by electron–positron pair production on CMB photons. Calculated for power-law generation spectrum with index γ g = 2.7, the shape of the dip is confirmed with high accuracy by data of Akeno-AGASA, HiRes, Yakutsk and Fly’s Eye detectors. The predicted shape of the dip is robust: it is valid for the rectilinear and diffusive propagation, for different discreteness in the source distribution, for local source overdensity, deficit, etc. This property of the dip allows us to use it for energy calibration of the detectors. The energy shift λ for each detector is determined by minimum χ 2 in comparison of observed and calculated dip. After this energy calibration the absolute fluxes, measured by AGASA, HiRes and Yakutsk detectors remarkably coincide in energy region 1 × 10 18–1 × 10 20 eV. Below the characteristic energy E c ≈ 1 × 10 18 eV the spectrum of the dip flattens for both diffusive and rectilinear propagation, and more steep galactic spectrum becomes dominant at E < E c. The energy of transition E tr < E c approximately coincides with the position of the second knee E 2kn, observed in the cosmic ray spectrum. The dip-induced transition from galactic to extragalactic cosmic rays at the second knee is compared with traditional model of transition at ankle, the feature observed at energy ∼1 × 10 19 eV.

PRECISE EYE LOCATION USING DEMPSTER–SHAFER THEORY

Eye location is an important step in automatic visual interpretation and face recognition. In this paper, we present a novel eye location algorithm based on Dempster–Shafer's evidential reasoning. Four eye detectors are trained by AdaBoost with different combinations of feature spaces and samples. They detect face region respectively and produce an eye candidate set, then two of the four eye detectors calculate the confidence of every eye candidate. The confidence is converted to belief and plausibility. We use the combining rule to obtain combined belief and plausibility of each eye candidate, which represent the fusion information of the two eye detectors. The centers of eye candidates with great plausibility are considered as actual eye centers. Experimental results on several open face databases demonstrate that our method is precise, robust and has less computational complexity than other newly proposed ones.

A dip in the UHECR spectrum and the transition from galactic to extragalactic cosmic rays

The dip is a feature in the diffuse spectrum of ultra-high energy (UHE) protons in the energy range 1 × 10 18–4 × 10 19 eV, which is caused by electron–positron pair production on the cosmic microwave background (CMB) radiation. For a power-law generation spectrum E −2.7, the calculated position and shape of the dip is confirmed with high accuracy by the spectra observed by the Akeno-AGASA, HiRes, Yakutsk and Fly’s Eye detectors. When the particle energies, measured in these detectors, are calibrated by the dip, their fluxes agree with a remarkable accuracy. The predicted shape of the dip is quite robust: it is modified very weakly when the discreteness and inhomogeneities in the source distribution are taken into account, and for different regimes of propagation (from rectilinear to diffusive). The cosmological evolution of the sources, with parameters inspired by observations of Active Galactic Nuclei (AGN), also results in the same shape of the dip. The dip is modified strongly when the fraction of nuclei heavier than protons is high at injection, which imposes some restrictions on the mechanisms of acceleration operating in UHECR sources. The existence of the dip, confirmed by observations, implies that the transition from galactic to extragalactic cosmic rays occurs at E ≲ 1 × 10 18 eV. We show that at energies lower than a characteristic value E cr ≈ 1 × 10 18 eV, determined by the equality between the rate of energy losses due to pair production and adiabatic losses, the spectrum of extragalactic cosmic rays flattens in all cases of interest, and it provides a natural transition to a steeper galactic cosmic ray spectrum. This transition occurs at some energy below E cr, corresponding to the position of the so-called second knee. We discuss extensively the constraints on this model imposed by current knowledge of acceleration processes and sources of UHECR and compare it with the traditional model of transition at the ankle.

On transiton from galactic to extragalactic cosmic rays

The dip is a feature in the diffuse spectrum of UHE protons in energy range 1 × 1018 − 4 × 1019 eV, which is caused by electron-positron pair production on CMB photons. Calculated for power-law generation spectrum with index γg = 2.7, the shape of the dip is confirmed with high accuracy by data of Akeno - AGASA, HiRes, Yakutsk and Fly's Eye detectors. The predicted shape of the dip is robust: it is valid for the rectilinear and diffusive propagation, for different discretenesses in the source distribution, for local source overdensity and deficit, for source inhomogeneities on scale∼l100 Mpc etc. Below the characteristic energy Ec ≈ 1 × 1018 eV the spectrum of the dip flattens for both diffusive and rectilinear propagation, and more steep galactic spectrum becomes dominant at E < Ec. The energy of transition Etr < Ec approximately coincides with the position of the second knee E2kn observed in the cosmic ray spectrum. The critical energy Ec is determined by the energy Eeq = 2.3 × 1018 eV, where adiabatic and pair-production energy losses are equal. Thus, position of the second knee is explained by proton energy losses on CMB photons. The transition from galactic to extragalactic cosmic rays is quantitatively described by the AGN model for UHECR.

On astrophysical solution to ultrahigh energy cosmic rays

We argue that an astrophysical solution to UHECR problem is viable. The pectral features of extragalactic protons interacting with CMB are calculated in model-independent way. Using the power-law generation spectrum $\propto E^{-\gamma_g}$ as the only assumption, we analyze four features of the proton spectrum: the GZK cutoff, dip, bump and the second dip. We found the dip, induced by electron-positron production on CMB, as the most robust feature, existing in energy range $1\times 10^{18} - 4\times 10^{19}$ eV. Its shape is stable relative to various phenomena included in calculations. The dip is well confirmed by observations of AGASA, HiRes, Fly's Eye and Yakutsk detectors. The best fit is reached at $\gamma_g =2.7$, with the allowed range 2.55 - 2.75. The dip is used for energy calibration of the detectors. After the energy calibration the fluxes and spectra of all three detectors agree perfectly, with discrepancy between AGASA and HiRes at $E> 1\times 10^{20}$ eV being not statistically significant. The agreement of the dip with observations should be considered as confirmation of UHE proton interaction with CMB. The dip has two flattenings. The high energy flattening at $E \approx 1\times 10^{19}$ eV automatically explains ankle. The low-energy flattening at $E \approx 1\times 10^{18}$ eV provides the transition to galactic cosmic rays. This transition is studied quantitatively. The UHECR sources, AGN and GRBs, are studied in a model-dependent way, and acceleration is discussed. Based on the agreement of the dip with existing data, we make the robust prediction for the spectrum at $1\times 10^{18} - 1\times 10^{20}$ eV to be measured in the nearest future by Auger detector.

Measurements of cosmic-ray air shower development at energies above 10 to the 17th eV

Measurements are presented of the depth of maximum for extensive air showers (EAS) produced by cosmic-ray nuclei with energies above 10 to the 17th eV. The air showers were observed using the University of Utah's Fly's Eye detectors operating in stereo mode. Measurements of the atmospheric nitrogen fluorescence light generated by EAS have been used to obtain longitudinal development curves of individual showers and, in particular, the depth of maximum of each shower. The data imply an elongation rate of 69.4 + or - 5.0 g/sq cm per decade above 10 to the 17th eV without correction for triggering and resolution effects. These effects contribute approximately +5 g/sq cm per decade to the apparent elongation rate. The distribution of depths of shower maximum has a mean value of 690 + or - 3 g/sq cm (with an estimated systematic uncertainty of + or - 20 g/sq cm) and a width (standard deviation) of 85 + or - 2 g/sq cm for showers with energies above 3 x 10 to the 17th eV. The tail of the distribution has a logarithmic decrement of lambda = 70 + or - 14 g/sq cm. Comparison with predictions for a pure proton and amore » pure iron flux indicates that the data are not consistent with either and are instead consistent with a mixture. 14 refs.« less

Measurement of cosmic ray air shower development at energies above 10 17eV

We present measurements of the depth of maximum for extensive air showers (EAS) produced by cosmic ray nuclei with energies above 10 17eV. The air showers were observed using the University of Utah's Fly's Eye detectors operating in stereo mode. Measurements of the atmospheric nitrogen fluorescence light generated by EAS have been used to obtain longitudinal development curves of individual showers and, in particular, the depth of maximum of each shower. The data imply an elongation rate of 89 ± 6 g cm −2 per decade above 10 17eV. The distribution of depths of shower maximum has a mean value of 690 ± 3 g cm −2 (with an estimated systematic uncertainty of ± 20 g cm −2) and a width (standard deviation) of 85 ± 2 g cm −2 for showers with energies above 3 × 10 17eV. The tail of the distribution has a logarithmic decrement of λ = 70 ± 14 g cm −2. Comparisons with predictions for a pure proton and a pure iron flux indicate that the data are not consistent with either.

Measurement of the angular distribution of Cerenkov light in ultra-high-energy extensive air showers

The authors report on a direct measurement of the angular distribution of Cerenkov light in extensive air showers with energies greater than 1017 eV. The measurement is performed by viewing sections of showers simultaneously at different emission angles with two Fly's Eye detectors. The data imply a value of the multiple scattering parameter theta 0=4.0+or-1.2 degrees for threshold energies between 20 and 60 MeV.

Implications of the ultrahigh-energy cosmic-ray spectrum observed by the Fly's Eye detector.

We discuss the potential implications of the recent results of the Fly's Eye detector on the ultrahigh-energy cosmic-ray spectrum. The data suggest that the observed slope flattening immediately prior to the cutoff appears to be a recoil-proton pileup associated with an ${E}^{\mathrm{\ensuremath{-}}2.5\ifmmode\pm\else\textpm\fi{}.3}$ injection spectrum. We discuss the induced neutrino spectrum and its detectability in Fly's Eye and DUMAND detectors.