VanderLugt Correlator Research Articles

Driver Drowsiness Detection Based on Drivers’ Physical Behaviours: A Systematic Literature Review

One of the most common causes of traffic accidents is human error. One such factor involves the drowsy drivers that do not focus on the road before them. Driver drowsiness often occurs due to fatigue in long distances or long durations of driving. The signs of a drowsy driver may be detected based on one out of three types of tests; i.e., performance test, physiological test, and behavioural test. Since the physiological and performance tests are quite difficult and expensive to implement, the behavioural test is a good choice to use for detecting early drowsiness. Behaviour-based driver drowsiness detection has been one of the hot research topics in recent years and is still increasingly developing. There are many approaches for behavioural driver drowsiness detection, such as Neural Networks, Multi Layer Perceptron, Support Vector Machine, Vander Lugt Correlator, Haar Cascade, and Eye Aspect Ratio. Therefore, this study aims to conduct a systematic literature review to elaborate on the development and research trends regarding driver drowsiness detection. We hope to provide a good overview of the current state of research and offer the research potential in the future.

Structured light based optical pattern recognition:Principle and technical progress

<p indent=0mm>Optical image recognition technology has attracted considerable attention due to its advantages, such as extensive information processing capacity, high-speed calculation, and advanced parallel processing. This technology also has various applications in security systems, remote sensing imaging, biomedical technology, and military scenarios. With the development of structured optical engineering technology, optical image recognition has gained new vitality in recent years. This paper describes two major optical image recognition correlators, the Vander Lugt Correlator and Joint Transform Correlator. We describe the progress of research on optical pattern recognition in the framework of linear optics, nonlinear optics, and quantum correlation. Our study also emphasizes how structured light engineering technologies can be incorporated into all-optical pattern recognition systems to accelerate technological developments.

Optical face detection and recognition system on low-end-low-cost Xilinx Zynq SoC

Optical face detection and recognition system (FDRS) is widely used in modern biometric security systems. In this paper, we implement a new model of FDRS to identify human faces under different poses. Particularly, we propose the Viola-Jones detector to locate and detect human faces and the VanderLugt correlator (VLC) technique for identification. Despite its extensive use, the VLC technique still requires design implementation efforts. This disadvantage is primarily due to the intensive computation required by the VLC technique. In our work, we propose three implementations (the first one is software and the last both are Hw/Sw co-design) on low-end-low-cost Xilinx Zync SOC that integrates both an ARM Cortex-A9 processor and an FPGA into a single device. In the software approach, we propose an implementation based on the ARM Cortex-A9 processor using OpenCV library. For the first Hw/Sw approach, we propose a co-design based on a hybrid ARM-FPGA platform, where the traditional hardware VLC architecture processed on FPGA. To respect real-time constraints, we developed an optimized hardware VLC architecture processed on FPGA to realize the second Hw/Sw co-design. A set of experiments has been considered using the PHPID database where the faces ranging from -30° to +30°. The experimental result showed that the optimized hardware VLC architecture provides a speedup of 4.4x compared to the non-optimized traditional hardware VLC architecture, and a speed-up of 39.22x compared to the software implementation. Finally, from a functional point-of-view, the recognition ratios obtained from both Hw/Sw co-designs are comparable to those obtained using software implementation.

Optical correlator based algorithm for driver drowsiness detection

The human eye and its characteristics (texture, gaze, and movement) have shown to be reliable in expressing human emotional states. A non-invasive eye tracking and state (open/close) estimation system is, consequently, fundamental for developing human-machine interaction systems, hands-off process control, and fatigue detection.In the current work, a novel and fast method based on an optical correlator is proposed for eye detection first, followed by eye state estimation. The second aim of this work was to investigate the simulated optical correlator on a real world driving videos for driver drowsiness detection. For the first time, a numerical simulation of the Vander Lugt Correlator (VLC) was used for automatically detecting the eye center. Further, correlation filters tailored to all the eye states were proposed and their design, to recognize eyes in cluttering and noisy environments, was investigated. Besides, the correlation peak amplitude returned by the VLC based algorithm was investigated to detect the driver drowsiness.Results reported on four international databases reveal that the proposed method improves over the recently published methods in eye tracking. Evaluations of the simulated VLC on real world driving videos from the SHRP2 database demonstrate its good performance on the driver's eye tracking and closure detection.

Hybrid Approach for Face Recognition from a Single Sample per Person by Combining VLC and GOM

Abstract This paper proposes a new face recognition system based on combining two feature extraction techniques: the Vander Lugt correlator (VLC) and Gabor ordinal measures (GOM). The proposed system relies on the execution speed of VLC and the robustness of GOM. In this system, we applied the Tan and Triggs and retina modeling enhancement techniques, which are well suited for VLC and GOM, respectively. We evaluated our system on the standard FERET probe data sets and on extended YaleB database. The obtained results exhibited better face recognition rates in a shorter execution time compared to the GOM technique.

Brain tumor segmentation with Vander Lugt correlator based active contour

Background and objectiveThe manual segmentation of brain tumors from medical images is an error-prone, sensitive, and time-absorbing process. This paper presents an automatic and fast method of brain tumor segmentation. MethodsIn the proposed method, a numerical simulation of the optical Vander Lugt correlator is used for automatically detecting the abnormal tissue region. The tumor filter, used in the simulated optical correlation, is tailored to all the brain tumor types and especially to the Glioblastoma, which considered to be the most aggressive cancer. The simulated optical correlation, computed between Magnetic Resonance Images (MRI) and this filter, estimates precisely and automatically the initial contour inside the tumorous tissue. Further, in the segmentation part, the detected initial contour is used to define an active contour model and presenting the problematic as an energy minimization problem. As a result, this initial contour assists the algorithm to evolve an active contour model towards the exact tumor boundaries. Equally important, for a comparison purposes, we considered different active contour models and investigated their impact on the performance of the segmentation task. Several images from BRATS database with tumors anywhere in images and having different sizes, contrast, and shape, are used to test the proposed system. Furthermore, several performance metrics are computed to present an aggregate overview of the proposed method advantages. ResultsThe proposed method achieves a high accuracy in detecting the tumorous tissue by a parameter returned by the simulated optical correlation. In addition, the proposed method yields better performance compared to the active contour based methods with the averages of Sensitivity=0.9733, Dice coefficient = 0.9663, Hausdroff distance = 2.6540, Specificity = 0.9994, and faster with a computational time average of 0.4119 s per image. ConclusionsResults reported on BRATS database reveal that our proposed system improves over the recently published state-of-the-art methods in brain tumor detection and segmentation.

Automated segmentation of ophthalmological images by an optical based approach for early detection of eye tumor growing

PurposeIris neoplasm is a non-symptom cancer that causes a gradual loss of sight. The first purpose of this study was to present a novel and automatic method for segmenting the iris tumors and detecting the corresponding areas changing along time. The second aim of this work was to investigate several recently published methods after being applied for the iris tumors segmentation. MethodsOur approach consists firstly in segmenting the iris region by using the Vander Lugt correlator based active contour method. Secondly, by treating only the iris region, a K-means clustering model was used to assign the tumorous tissue to one pixel-cluster. This model is quite sensitive to the center initialization and to the choice of the distance measure. To solve these problems, a proportional probability based approach was introduced for the cluster center initialization, and the impact of several distance measure was investigated. The proposed method and the different comparative methods were evaluated on two databases: the Eye Cancer and the Miles Research. ResultsResults reported using several performance metrics reveal that the first step assures the detection of all iris tumors with an accuracy of 100%. Additionally, the proposed method yields better performance compared to the recently published methods.

One lens optical correlation: application to face recognition.

Despite its extensive use, the traditional 4f Vander Lugt Correlator optical setup can be further simplified. We propose a lightweight correlation scheme where the decision is taken in the Fourier plane. For this purpose, the Fourier plane is adapted and used as a decision plane. Then, the offline phase and the decision metric are re-examined in order to keep a reasonable recognition rate. The benefits of the proposed approach are numerous: (1)it overcomes the constraints related to the use of a second lens; (2)the optical correlation setup is simplified; (3)the multiplication with the correlation filter can be done digitally, which offers a higher adaptability according to the application. Moreover, the digital counterpart of the correlation scheme is lightened since with the proposed scheme we get rid of the inverse Fourier transform (IFT) calculation (i.e., decision directly in the Fourier domain without resorting to IFT). To assess the performance of the proposed approach, an insight into digital hardware resources saving is provided. The proposed method involves nearly 100 times fewer arithmetic operators. Moreover, from experimental results in the context of face verification-based correlation, we demonstrate that the proposed scheme provides comparable or better accuracy than the traditional method. One interesting feature of the proposed scheme is that it could greatly outperform the traditional scheme for face identification application in terms of sensitivity to face orientation. The proposed method is found to be digital/optical implementation-friendly, which facilitates its integration on a very broad range of scenarios.

Misalignment influence of components on the performance of an integrated zigzag Vander Lugt correlator

The idea of integrating a zigzag Vander Lugt correlator with spatial light modulators (IZVLC) is rather flexible as a means of applying the parallelism of optics and rapid processing speed to a wider range of applications. The alignment of components poses an important impact on the performance of hybrid-optical architecture IZVLC. Based on planar optical and transfer function theory, we establish a simulation model of IZVLC system, systematically analyze the impact of components misalignment on the system performance, and demonstrate that the system is more sensitive to transversal misalignment of components than longitudinal misalignment of those. This analysis method of components misalignment can be important and useful for the designers, manufacturers and users of the IZVLC system to improve the robustness.

Vander Lugt Correlator based active contours for iris segmentation and tracking

Iris segmentation using active contours approaches is receiving increasing attention. In this paper, a self-ruling active contour approach based on the optical correlation algorithm is proposed. The novelty of this research effort is to apply the Optical Correlation based Active Contours (OCAC) on iris segmentation and tracking and highlight the advantages of its small computation time and better accuracy performance. Optical correlation computed with a numerical simulation of the Vander Lugt correlator is used to detect iris and pupil areas which used as an initial contours. As a result, these initial contours assists the method to calculate terms in an energy expression. In the proposed method, several references images called filters of iris and pupil have been introduced. Images from four iris datasets as CASIA v4, WVU non-ideal, MMU2, UBIRIS v2, and a motion video were used in the experiments phase. To present an aggregate overview of the proposed method advantages, we computed several parameters as iris and pupil centers localization errors, iris and pupil rays errors, three performance metrics (as Jaccard coefficient, Dice coefficient, Hausdroff distance), average segmentation error, and average execution time. We compare these segmentation performance parameters with several leading techniques demonstrating significantly improved results with the proposed OCAC technique.

Pose invariant face recognition: 3D model from single photo

Face recognition is widely studied in the literature for its possibilities in surveillance and security. In this paper, we report a novel algorithm for the identification task. This technique is based on an optimized 3D modeling allowing to reconstruct faces in different poses from a limited number of references (i.e. one image by class/person). Particularly, we propose to use an active shape model to detect a set of keypoints on the face necessary to deform our synthetic model with our optimized finite element method. Indeed, in order to improve our deformation, we propose a regularization by distances on graph. To perform the identification we use the VanderLugt correlator well know to effectively address this task. On the other hand we add a difference of Gaussian filtering step to highlight the edges and a description step based on the local binary patterns. The experiments are performed on the PHPID database enhanced with our 3D reconstructed faces of each person with an azimuth and an elevation ranging from −30° to +30°. The obtained results prove the robustness of our new method with 88.76% of good identification when the classic 2D approach (based on the VLC) obtains just 44.97%.

Advanced driver assistance system: Road sign identification using VIAPIX system and a correlation technique

We present a three-step approach based on the commercial VIAPIX® module for road traffic sign recognition and identification. Firstly, detection in a scene of all objects having characteristics of traffic signs is performed. This is followed by a first-level recognition based on correlation which consists in making a comparison between each detected object with a set of reference images of a database. Finally, a second level of identification allows us to confirm or correct the previous identification. In this study, we perform a correlation-based analysis by combining and adapting the Vander Lugt correlator with the nonlinear joint transformation correlator (JTC). Of particular significance, this approach permits to make a reliable decision on road traffic sign identification. We further discuss a robust scheme allowing us to track a detected road traffic sign in a video sequence for the purpose of increasing the decision performance of our system. This approach can have broad practical applications in the maintenance and rehabilitation of transportation infrastructure, or for drive assistance.

Optimization of the performances of correlation filters by pre-processing the input plane

We report findings on the optimization of the performances of correlation filters. First, we propound and validate an optimization of ROC curves adapted to correlation technique. Then, analysis suggests that a pre-processing of the input plane leads to a compromise between the robustness of the adapted filter and the discrimination of the inverse filter for face recognition applications. Rewardingly, our technical results demonstrate that this method is remarkably efficient to increase the performances of a VanderLugt correlator.

Processing of 1D signals with raster input in 2D optical correlators

The feasibility of Vander-Lugt and joint-transform optical correlators for the correlation processing of large-base 1D signals is demonstrated. The results of experiments with a joint-transform correlator with a liquid-crystal input device and raster input of a signal are presented.

Assessing the performance of a motion tracking system based on optical joint transform correlation

We present an optimized system specially designed for the tracking and recognition of moving subjects in a confined environment (such as an elderly remaining at home). In the first step of our study, we use a VanderLugt correlator (VLC) with an adapted pre-processing treatment of the input plane and a postprocessing of the correlation plane via a nonlinear function allowing us to make a robust decision. The second step is based on an optical joint transform correlation (JTC)-based system (NZ-NL-correlation JTC) for achieving improved detection and tracking of moving persons in a confined space. The proposed system has been found to have significantly superior discrimination and robustness capabilities allowing to detect an unknown target in an input scene and to determine the target’s trajectory when this target is in motion. This system offers robust tracking performance of a moving target in several scenarios, such as rotational variation of input faces. Test results obtained using various real life video sequences show that the proposed system is particularly suitable for real-time detection and tracking of moving objects.

Optimization of decision making for face recognition based on nonlinear correlation plane

We report on a specific procedure in the correlation plane which allows us to make more robust and discriminating decision for face recognition applications. In this scheme, we multiply the correlation plane by a nonlinear function which is chosen to increase the correlation peak, reduce the autocorrelation noise, and increase the inter-correlation noise. In our work we present tests using a VanderLugt correlator (VLC) fabricated with different filters (phase-only filter (POF), composite POF) and we also discuss the efficiency of the protocol using peak-to-correlation-energy measures. Rewardingly, our technical results demonstrate that this method is remarkably efficient to increase both robustness and discrimination performances of a VLC.

Integrated zigzag Vander Lugt correlators incorporating an optimal trade-off synthetic discriminant filter for invariant pattern recognition

Optical correlators (OCs) have a wide range of applications in the field of pattern recognition. We present a type of integrated zigzag Vander Lugt correlator (IZVLC). The IZVLC incorporates two Fourier transform lenses and one spatial light modulator (SLM) as a programmable filter, which can effectively miniaturize the volume of OCs and hence achieve better optical pattern recognition. In order to precisely recognize distortion targets, an optimal trade-off synthetic discriminant filter (OTSDF) is programmed on the SLM of the IZVLC. Both the simulative and experimental results have shown that the IZVLC can effectively identify distortion targets within a rotation angle of ±π/3 and a scaling range of 0.6–1.6.

Correlation based efficient face recognition and color change detection

Identifying the human face via correlation is a topic attracting widespread interest. At the heart of this technique lies the comparison of an unknown target image to a known reference database of images. However, the color information in the target image remains notoriously difficult to interpret. In this paper, we report a new technique which: (i) is robust against illumination change, (ii) offers discrimination ability to detect color change between faces having similar shape, and (iii) is specifically designed to detect red colored stains (i.e. facial bleeding). We adopt the Vanderlugt correlator (VLC) architecture with a segmented phase filter and we decompose the color target image using normalized red, green, and blue (RGB), and hue, saturation, and value (HSV) scales. We propose a new strategy to effectively utilize color information in signatures for further increasing the discrimination ability. The proposed algorithm has been found to be very efficient for discriminating face subjects with different skin colors, and those having color stains in different areas of the facial image.

Spectral optimized asymmetric segmented phase-only correlation filter

We suggest a new type of optimized composite filter, i.e., the asymmetric segmented phase-only filter (ASPOF), for improving the effectiveness of a VanderLugt correlator (VLC) when used for face identification. Basically, it consists in merging several reference images after application of a specific spectral optimization method. After segmentation of the spectral filter plane to several areas, each area is assigned to a single winner reference according to a new optimized criterion. The point of the paper is to show that this method offers a significant performance improvement on standard composite filters for face identification. We first briefly revisit composite filters [adapted, phase-only, inverse, compromise optimal, segmented, minimum average correlation energy, optimal trade-off maximum average correlation, and amplitude-modulated phase-only (AMPOF)], which are tools of choice for face recognition based on correlation techniques, and compare their performances with those of the ASPOF. We illustrate some of the drawbacks of current filters for several binary and grayscale image identifications. Next, we describe the optimization steps and introduce the ASPOF that can overcome these technical issues to improve the quality and the reliability of the correlation-based decision. We derive performance measures, i.e., PCE values and receiver operating characteristic curves, to confirm consistency of the results. We numerically find that this filter increases the recognition rate and decreases the false alarm rate. The results show that the discrimination of the ASPOF is comparable to that of the AMPOF, but the ASPOF is more robust than the trade-off maximum average correlation height against rotation and various types of noise sources. Our method has several features that make it amenable to experimental implementation using a VLC.

Decision optimization for face recognition based on an alternate correlation plane quantification metric

We consider a new approach for enhancing the discrimination performance of the VanderLugt correlator. Instead of trying to optimize the correlation filter, or propose a new decision correlation peak detection criterion, we propose herein to denoise the correlation plane before applying the peak-to-correlation energy (PCE) criterion. For that purpose, we use a linear functional model to express a given correlation plane as a linear combination of the correlation peak, noise, and residual components. The correlation peak is modeled using an orthonormalized function and the singular value decomposition method. A set of training correlation planes is then selected to create the correlation noise components. Finally, an optimized correlation plane is reconstructed while discarding the noise components. Independently of the filter correlation used, this technique denoises the correlation plane by lowering the correlation noise magnitude in case of true correlation and decreases the false alarm rate when the target image does not belong to the desired class. Test results are presented, using a composite filter and a face recognition application, to verify the effectiveness of the proposed technique.