- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Analyzing Covariate Influence on Gender and Race Prediction from Near-Infrared Ocular Images
摘要： Recent research has explored the possibility of automatically deducing information such as gender, age and race of an individual from their biometric data. While the face modality has been extensively studied in this regard, the iris modality less so. In this paper, we first review the medical literature to establish a biological basis for extracting gender and race cues from the iris. Then, we demonstrate that it is possible to use simple texture descriptors, like BSIF (Binarized Statistical Image Feature) and LBP (Local Binary Patterns), to extract gender and race attributes from an NIR ocular image used in a typical iris recognition system. The proposed method predicts gender and race from a single eye image with an accuracy of 86% and 90%, respectively. In addition, the following analysis are conducted: (a) the role of different parts of the ocular region on attribute prediction; (b) the influence of gender on race prediction, and vice-versa; (c) the impact of eye color on gender and race prediction; (d) the impact of image blur on gender and race prediction; (e) the generalizability of the method across different datasets; and (f) the consistency of prediction performance across the left and right eyes.
关键词： ethnicity,periocular,Biometrics,NIR,iris,covariate analysis,gender,attribute prediction
更新于2025-09-09 09:28:46
-
[IEEE 2018 26th European Signal Processing Conference (EUSIPCO) - Roma, Italy (2018.9.3-2018.9.7)] 2018 26th European Signal Processing Conference (EUSIPCO) - Light Field Compression of HDCA Images Combining Linear Prediction and JPEG 2000
摘要： We have proposed under JPEG Pleno standardization activities a scheme for lenslet image compression, where the regularities and similarities existing between neighbor angular views were successfully exploited, achieving competitive results in the JPEG Pleno core experiments using lenslet data. This paper proposes improvements on our previous scheme of light field compression, making our approach more suitable for compression of light fields acquired with dense camera arrays, where the disparities between farthest views can reach several hundreds of pixels. We review the functional blocks of the compression algorithm, replacing and modifying some of the functionality with more advanced and efficient solutions. Based on our submission to the JPEG Pleno core experiments, we present and discuss our results obtained on the Fraunhofer HDCA dataset. Additionally, we present a new view merging algorithm which substantially increases the PSNR at all bit rates.
关键词： HDCA images,JPEG 2000,Linear Prediction,Light field compression
更新于2025-09-04 15:30:14
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Confidence-Driven Network for Point-to-Set Matching
摘要： The goal of point-to-set matching is to match a single image with a set of images from a subject. Within an image set, different images contain various levels of discriminative information and thus should contribute differently to the results. However, the discriminative level is not accessible directly. To this end, we propose a confidence driven network to perform point-to-set matching. The proposed system comprises a feature extraction network (FEN) and a performance prediction network (PPN). Given an input image, the FEN generates a template, while the PPN generates a confidence score which measures the discriminative level of the template. At matching time, the template is used to compute a point-to-point similarity. The similarity scores from different samples in the set are integrated at a score level, weighted by the predicted confidence scores. Extensive multi-probe face recognition experiments on the IJB-A and UHDB-31 datasets demonstrate performance improvements over state of the art algorithms.
关键词： feature extraction network,performance prediction network,multi-probe face recognition,confidence driven network,point-to-set matching
更新于2025-09-04 15:30:14
-
Smart Plant Factory (The Next Generation Indoor Vertical Farms) || Detection and Utilization of Biological Rhythms in Plant Factories
摘要： Biological rhythms with a period of about 24 h, called “circadian rhythms,” are generated by the expressions of clock genes. In plants, circadian rhythms increase the growth rate through the daily coordination of photosynthesis and metabolism. Therefore, the detection and utilization of circadian rhythms is required to improve the plant production in plant factories. In this chapter, recently developed technologies based on circadian rhythms are described. Section 22.1 focuses on seedling diagnosis using the circadian rhythm of chlorophyll ?uorescence (CF). Section 22.2 describes high-throughput growth prediction systems based on the circadian rhythm of CF. Section 22.3 provides examples of global analysis of acquired gene expression as biological information and methods for analyzing internal time (i.e., the phases of circadian rhythms) using that data. We describe how circadian rhythms can be observed by comprehensive analyses and the methods used for such analyses. Finally, Sect. 22.4 describes a basic theory for controlling circadian rhythms by environmental stimuli. Methods that enable basic control of circadian rhythms are important, as they are applicable to a variety of research questions and industrial problems.
关键词： Molecular timetable method,Circadian rhythms,Phase response curves,Growth prediction,Chlorophyll ?uorescence,Transcriptome analysis
更新于2025-09-04 15:30:14
-
[ACM Press the 24th ACM Symposium - Tokyo, Japan (2018.11.28-2018.12.01)] Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology - VRST '18 - Real-time human motion forecasting using a RGB camera
摘要： We propose a real-time human motion forecasting system which visualize the future pose in virtual reality using a RGB camera. Our system consists of three parts: 2D pose estimation from RGB frames using a residual neural network, 2D pose forecasting using a recurrent neural network, and 3D recovery from the predicted 2D pose using a residual linear network. To improve the prediction learning quantity of temporal feature, we propose a special method using lattice optical flow for the joints movement estimation. After fitting the skeleton, a predicted 3d model of target human will be built 0.5s in advance in a 30-fps video.
关键词： Deep neural network,Real-time pose prediction,Motion forecasting
更新于2025-09-04 15:30:14
-
A Review Burst Assembly Techniques in Optical Burst Switching (OBS)
摘要： Optical Burst Switching (OBS) is perceived as the most favorable switching method for the next generation all optical networks to support the growth of the number of Internet users and to satisfy bandwidth demands for greedy-bandwidth applications which are in continuous growth. OBS consists of an edge node and a core node. The edge node is responsible for burst assembly which is the first process in an OBS network. Currently, there is only one review paper for burst assembly; the paper is limited in number of techniques reviewed. In this paper, we have undertaken a comprehensive review of burst assembly techniques proposed for OBS where techniques are reviewed by category. The aim is to identify strengths and weaknesses of these techniques. The analysis of the paper will assist researchers in finding problems; thus, a significant amount of time will be saved which can be used in developing appropriate solutions for OBS networks.
关键词： traffic prediction,delay,OBS,QoS,loss,burst assembly
更新于2025-09-04 15:30:14
-
Assessing the Reliability of Thermal and Optical Imaging Techniques for Detecting Crop Water Status under Different Nitrogen Levels
摘要： Efficient management of irrigation water is fundamental in agriculture to reduce the environmental impacts and to increase the sustainability of crop production. The availability of adequate tools and methodologies to easily identify the crop water status in operating conditions is therefore crucial. This work aimed to assess the reliability of indices derived from imaging techniques—thermal indices (Ig (stomatal conductance index) and CWSI (Crop Water Stress Index)) and optical indices (NDVI (Normalized Difference Vegetation Index) and PRI (Photochemical Reflectance Index))—as operational tools to detect the crop water status, regardless the eventual presence of nitrogen stress. In particular, two separate experiments were carried out in a greenhouse, on two spinach varieties (Verdi F1 and SV2157VB), with different microclimatic conditions and under different levels of water and nitrogen application. Statistical analysis based on ANOVA test was carried out to assess the independence of thermal and optical indices from the crop nitrogen status. These imaging indices were successively compared through correlation analysis with reference destructive and non-destructive measurements of crop water status (stomatal conductance, chlorophyll a fluorescence, and leaf and soil water content), and linear regression models of thermal and optical indices versus reference measurements were calibrated. All models were significant (Fisher p-value lower than 0.05), and the highest R2 values (greater than 0.6) were found for the regression models between CWSI and the soil water content, NDVI and the leaf water content, and PRI and the stomatal conductance. Further analysis showed that imaging indices acquired by thermal cameras (especially CWSI) can be used as operational tools to detect the crop water status, since no dependence on plant nitrogen conditions was observed, even when the soil water depletion was very limited. Our results confirmed that imaging indices such as CWSI, NDVI and PRI can be used as operational tools to predict soil water status and to detect drought stress under different soil nitrogen conditions.
关键词： crop water status,crop water stress prediction,optical imaging sensor,thermal camera,spectral imaging index
更新于2025-09-04 15:30:14
-
External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy
摘要： Purpose The aim of this study was to validate previously developed radiomics models relying on just two radiomics features from 18F-fluorodeoxyglucose positron emission tomography (PET) and magnetic resonance imaging (MRI) images for prediction of disease free survival (DFS) and locoregional control (LRC) in locally advanced cervical cancer (LACC). Methods Patients with LACC receiving chemoradiotherapy were enrolled in two French and one Canadian center. Pre-treatment imaging was performed for each patient. Multicentric harmonization of the two radiomics features was performed with the ComBat method. The models for DFS (using the feature from apparent diffusion coefficient (ADC) MRI) and LRC (adding one PET feature to the DFS model) were tuned using one of the French cohorts (n = 112) and applied to the other French (n = 50) and the Canadian (n = 28) external validation cohorts. Results The DFS model reached an accuracy of 90% (95% CI [79–98%]) (sensitivity 92–93%, specificity 87–89%) in both the French and the Canadian cohorts. The LRC model reached an accuracy of 98% (95% CI [90–99%]) (sensitivity 86%, specificity 100%) in the French cohort and 96% (95% CI [80–99%]) (sensitivity 83%, specificity 100%) in the Canadian cohort. Accuracy was significantly lower without ComBat harmonization (82–85% and 71–86% for DFS and LRC, respectively). The best prediction using standard clinical variables was 56–60% only. Conclusions The previously developed PET/MRI radiomics predictive models were successfully validated in two independent external cohorts. A proposed flowchart for improved management of patients based on these models should now be confirmed in future larger prospective studies.
关键词： External validation,Prediction,Cervical cancer,Chemoradiotherapy,Radiomics
更新于2025-09-04 15:30:14
-
Online weld pool contour extraction and seam width prediction based on mixing spectral vision
摘要： In this paper, based on gas–metal–arc welding (GMAW), we used a passive vision sensing system and proposed a double-path imaging method to capture weld pool images, and empirically and theoretically demonstrated the optimal bands. According to the mixed spectra of self-emitted radiation of the weld pool and the arc spectra, we selected 660-nm narrowband and 850-nm long-pass as the system’s working bands. Two cameras with 660-nm narrowband filter and 850-nm long-pass filter were used to capture weld pool images at the background level through a synchronous acquisition equation and weld pool images with high signal-to-noise ratio were obtained. After image registration, we used Gradient and Gray-based Neighbor Superpixel Merging (GNSM) method to extract the contour of weld pool image. Comparing with other algorithms, the proposed algorithm can obtain an effective and accurate contour of the weld pool image. Then we proposed an online seam width prediction method before seam formation which is based on the contour of the weld pool image. We used Gaussian distribution to fit the pixel width of the contour and the corresponding seam width measured by three-dimensional reconstruction. By comparatively analyzing the fitting deviation and the actual measurement results, we concluded that the deviation of weld seam width prediction was within 0.20 mm.
关键词： Three-dimensional reconstruction,Superpixel segmentation,Seam width prediction,Vision sensing system,Double-band imaging,Contour of weld pool
更新于2025-09-04 15:30:14
-
Framework for predicting the photodegradation of adhesion of silicone encapsulants
摘要： We developed a framework to predict and model the photodegradation of adhesion and cohesion of a silicone encapsulant for concentrator photovoltaic applications. Silicone encapsulant specimens were artificially weathered under narrow band UV filters to determine the effects of individual wavelengths within the UV spectrum on the photodegradation of the cohesion of encapsulant material and its adhesion with adjacent interfaces. The threshold wavelength, signifying the upper bound of the damaging action spectrum for the silicone, was identified from the results. In addition, specimens were artificially weathered with different relative humidities to understand the effects of moisture on the rate of photodegradation. The adhesion energy was measured using a fracture mechanics approach. The complementary delaminated surfaces were characterized to determine the failure pathway and chemistry changes resulting from photodegradation. A previously developed model was modified to account for the effects of damaging wavelengths in the terrestrial solar spectrum and reciprocity law failure due to varying UV intensity during weathering. With these modifications, the model showed good agreement with the behavior of the silicone encapsulant exposed in an outdoor solar concentrator simulating concentrator photovoltaics operating conditions. Similar studies can be adopted to develop models that can have high predictive accuracies based on accelerated aging studies.
关键词： Accelerated aging,Concentrator photovoltaics,Photodegradation,Encapsulant,Lifetime prediction,Silicone
更新于2025-09-04 15:30:14