Vein Image Quality Research Articles

IIS-FVIQA: Finger Vein Image Quality Assessment with intra-class and inter-class similarity

In recent years, Finger Vein Image Quality Assessment (FVIQA) has been recognized as an effective solution to the problem of erroneous recognition resulting from low image quality due to false and missing information in finger vein images, and has become an important part of finger vein recognition systems. Compared to traditional FVIQA methods that rely on domain knowledge, newer methods that reject low-quality images have been favored for their independence from human interference. However, these methods only consider intra-class similarity information and ignore valuable information from inter-class distribution, which is also an important factor in evaluating the performance of recognition systems. In this work, we propose a novel FVIQA approach, named IIS-FVIQA, which concurrently takes into account the intra-class similarity density and inter-class similarity distribution distance within recognition systems. Specifically, our method generates quality scores for finger vein images by combining the information entropy of intra-class similarity distribution and Wasserstein distance of inter-class distribution. Then, we train a regression network for quality prediction using training images and corresponding quality scores. When a new image enters the recognition system, the trained regression network directly predicts the quality score of the image, making it easier for the system to select the corresponding operation based on the quality score of the image. Extensive experiments conducted on benchmark datasets demonstrate that the IIS-FVIQA method proposed in this paper consistently achieves top performance across multiple public datasets. After filtering out 10% of low-quality images predicted by the quality regression network, the recognition system’s performance improves by 43.96% (SDUMLA), 32.23% (MMCBNU_6000), and 21.20% (FV-USM), respectively. Furthermore, the method exhibits strong generalizability across different recognition algorithms (e.g., LBP, MC, and Inception V3) and datasets (e.g., SDUMLA, MMCBNU_6000, and FV-USM).

Dual-energy CT Portal Venography: Clinical Application Values and Future Opportunities.

Standard multidetector computed tomography (MDCT) uses a single X-ray tube to emit a mixed energy X-ray beam, which is received by a single detector. The difference is that dual-energy CT (DECT), a new equipment in recent years, employs a single X-ray tube or two X-ray tubes to emit two single-energy X-ray beams, which are received by a single or two detectors. The application of dual-energy technology to portal venography has become one of the research hotspots. This paper will elaborate on the clinical application values of DECT portal venography in improving portal vein image quality, distinguishing the nature of portal vein thrombus, reducing contrast agent dose and radiation dose, and will discuss the possibility of its movement from research to routine practice and future development opportunities.

Reverse Attention-Based Multi-Feature Interaction Network for Finger Vein Image Quality Evaluation

Reverse Attention-Based Multi-Feature Interaction Network for Finger Vein Image Quality Evaluation

A high compatibility finger vein image quality assessment system based on deep learning

Finger vein feature recognition has been widely studied due to its high security and stability. However, the systematic errors caused by false and missing information in low-quality finger vein images are still concerns. Recently, researchers have proposed a finger vein image quality assessment scheme to eliminate low-quality images. The major drawback of this strategy is the dependence on limited domain knowledge as the strategy cannot effectively filter out low-quality images and is only adapted to a certain recognition method or database. In this paper, we design a new finger vein image quality evaluation method driven by improving the recognition performance of the recognition system and based on the possibility of the false rejection of low-quality images. The method uses statistical knowledge to analyse the matching of different samples between fingers so as to automatically determine the image quality and classify it. Then, we further design a lightweight convolutional neural network to train the high-quality and low-quality images obtained by the above evaluation criteria and mine the common attributes between low-quality images so as to ensure that the prediction system can judge the image quality quickly and accurately in practical use. The proposed scheme is validated on multiple public datasets and compared with current recognition algorithms. The experimental results show that the quality evaluation standard proposed in this paper has good universality and can be combined with different types of recognition methods and acquisition equipment to well screen out the existing low-quality images. Furthermore, the prediction method proposed in this paper has achieved excellent prediction performance on three public datasets, showing that the proposed method can effectively improve the performance of the original recognition system. Taking the local binary pattern (LBP) algorithm as an example, after using the prediction algorithm proposed in this paper to eliminate low-quality images, the recognition system improves the original recognition performance on the three datasets by 12.670% (SDUMLA), 11.923% (MMCBNU_6000) and 9.940% (FV-USM).

A highly-verified biometric recognition system using an ultra-speed specifically-developed finger vein sensor

Currently, Biometrics has been utilized the top five modality of face, voice, IRIs, fingerprint, and palm to identify individuals. Comparatively, these Biometrics systems need complex computation to be slow and an easy target to hack. Alternatively, this work proposes a novel biometrics system of highly secured recognition with low computation time using specifically designed biometrics sensor. Consequently, finger vein recognition has been developed. Although, this recognition requires high point of safety measures comes with its individual experiments. The most prominent one being the vein pattern is very difficult to extract because finger vein images are constantly low in quality, seriously hampering the feature extraction and classification stages. Sophisticated algorithms need to be designed with the conventional hardware for capturing finger-vein images is modified by using red Surface Mounted Diode (SMD) leds. For capturing images, Canon 750D camera is used with micro lens. The integrated micro lens gives better quality images, and with some adjustments it can also capture finger print. Results have been comparatively improvement for SDUMLA-HMT database and extensively evaluated with k-nearest neighbors (KNN) algorithm. The (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm that can be used to solve both classification and regression problems. KNN calculations are highly accurate in test data. Using stratified 6- fold analysis on all fingers of all hands in collected database, a maximum accuracy of 100% was achieved with an EER of 0% when select right hand and middle finger, based on the analysis of the 106 persons present in the data set. Many approaches have been used to optimize vein image quality. The proposed system has optimum results as compared to existing related works. The work novelty is due to the hardware design of the sensor within the finger-vein recognition system to obtain, simultaneously, finger vein and finger print at low cost, unlimited users for one device and open source.

Finger-Vein Quality Assessment Based on Deep Features From Grayscale and Binary Images

Finger-vein verification is a highly secure biometric authentication that has been widely investigated over the last years. One of its challenges, however, is the possible degradation of image quality, that results in spurious and missing vein patterns, which increases the verification error. Despite recent advances in finger-vein quality assessment, the proposed solutions are limited as they depend on human expertise and domain knowledge to extract handcrafted features for assessing quality. We have proposed, recently, the first deep neural network (DNN) framework for assessing finger-vein quality, that does not require manual labeling of high and low quality images, as is the case for state of the art methods, but infers such annotations automatically based on an objective indicator, the biometric verification decision. This framework has significantly outperformed the existing methods, whether the input image is in grayscale or is binary. Motivated by these performances, we propose, in this work, a representation learning of finger vein image quality, where a DNN takes as input conjointly the grayscale and binary versions of the input image to predict vein quality. Our model allows to learn the joint representation from grayscale and binary images, for quality assessment. The experimental results, obtained on a large public dataset, demonstrates that our proposed method accurately identifies high and low quality images, and outperforms other techniques in terms of equal error rate (EER) minimization, including our previous DNN models, based either on grayscale or binary input.

Perancangan Sistem Deteksi Vena Pada Punggung Tangan Berbasis Inframerah Untuk Sistem Biometrik

AbstractVein detection is one of the imaging techniques required for biometric authentication purposes. The vein is chosen as an object because of its strength in terms of universality and uniqueness especially in adults because the venous pattern will only change slightly with age and each person has a different pattern, besides from the object side, the veins have no influence from temperature and humidity, and physical contactless with the other user. The purpose of this research is to create design that can visualize the veins as well and determine the optimum parameters to produce a better quality of vein image than the original image. The data for this research were obtained from 10 naracoba people who were varied of Boddy Mass Index and skin pigment. From the research, dorsal hand vein visualization tool for biometric system has been successfully designed using 726 nm infrared LED and image processing by convert of image to grayscale, image sharpening, histogram equalisation until segmentation by local thresholding method and the optimum parameters obtained to obtain a good image based on contrast analysis in this study is with a distance of 6 cm exposure.Keyword : Vein Detection, Biometrik, Near Infrared, Segmentation

Quality-Specific Hand Vein Recognition System

Vein images generally appear darker with low contrast, which require contrast enhancement during preprocessing to design satisfactory hand vein recognition system. However, the modification introduced by contrast enhancement (CE) is reported to bring side effects through pixel intensity distribution adjustments. Furthermore, the inevitable results of fake vein generation or information loss occur and make nearly all vein recognition systems unconvinced. In this paper, a “CE-free” quality-specific vein recognition system is proposed, and three improvements are involved. First, a high-quality lab-vein capturing device is designed to solve the problem of low contrast from the view of hardware improvement. Then, a high quality lab-made database is established. Second, CFISH score, a fast and effective measurement for vein image quality evaluation, is proposed to obtain quality index of lab-made vein images. Then, unsupervised $K$ -means with optimized initialization and convergence condition is designed with the quality index to obtain the grouping results of the database, namely, low quality (LQ) and high quality (HQ). Finally, discriminative local binary pattern (DLBP) is adopted as the basis for feature extraction. For the HQ image, DLBP is adopted directly for feature extraction, and for the LQ one. CE_DLBP could be utilized for discriminative feature extraction for LQ images. Based on the lab-made database, rigorous experiments are conducted to demonstrate the effectiveness and feasibility of the proposed system. What is more, an additional experiment with PolyU database illustrates its generalization ability and robustness.

Hand Vein Image Enhancement Based on Multi-Scale Top-Hat Transform

Abstract Traditional image contrast enhancement methods originally cannot improve the quality of vein images and may also import some unknown noise resulting in low recognition rate. To overcome the abovementioned disadvantages, the paper proposes an enhancement method based on the morphological filtering theory including three main procedures. Firstly, the algorithm extract the vein Region Of Interest (ROI), and then adopting the improved White Top-Hat transform (WTH) and Black Top-Hat transform (BTH) methods to get the features of vein in detail in both white and black pattern (vein information and background information); Secondly, to construct the filtering function with the self-designed controlling operator, representing the gradient changes of the vein edges, which well reflects the importance of local detail in multi-scale pattern; Finally, traditional nonlinear gray-level transformation function is imported with modality to the parameters to realize the gray normalization. We perform rigorous experiments with the proposed method and other state-of-the-art enhancement methods on the self-built dorsal vein image databases, and the experimental results illustrate that the multiscale top-hat theory-based enhancement methods improve the contrast of hand vein images with restrictions on the possibility of enhancement on existing noise information.

Variation in Cardiac Vein System is Associated with Coronary Artery Calcium - A Venous-Atherosclerosis Paradox?

The factors that determine the different patterns of venous anatomy are not well understood. This study was designed to evaluate the relationship between variation in the cardiac vein system and the extent of coronary artery calcium score (CACS). We reviewed the results of 64-slice CTs of 226 subjects (age 57.2 ± 11.2; 133M) enrolled in our study. The subjects were divided into 3 groups based on coronary artery calcium: 92 patients. with CACS = 0 AU (Agatston Unit, AU); 56 with CACS = 1-100 AU; and 78 patients with CACS > than 100 AU. The cardiac venous system was reconstructed during the optimal phase of the cardiac cycle in each subject. Subjects with a higher CACS had a better quality of vein images (p < 0.01). The number of visible veins differed between the groups. Eight subjects (8.7%) in the group with CACS = 0 AU, 7 (12.5%) in the group with CACS = 1-100 AU, and 23 (29.5%) in the group with CACS > 100 AU had five or more visible veins (p < 0.001), whereas the proportion of subjects with less than three visible veins was 56 (60.8%), 31 (55.4%) and 30 (38.4%), respectively (p < 0.05). The number of visible veins correlated with CACS (r = 0.28; p < 0.05). In a multivariate regression analysis, which included age, gender, CACS, LV ejection fraction, myocardial volume and heart rate, the CACS was found to be an independent determinant of the number of visible veins (p < 0.05). The results of our study suggested that there is a link between a variation in the cardiac venous system and the extent of atherosclerosis. Coronary artery calcium score (CACS); Computed tomography; Coronary veins.

Finger Vein Image Quality Evaluation based on Support Vector Regression

It has been found that poor quality images decrease the performance of finger vein recognition system, due to missing, vague or spurious features. Therefore, it is important for a finger vein recognition system to evaluate the quality of finger vein images. In this paper, a new method based on Support Vector Regression (SVR) is proposed for finger vein image quality evaluation. In our method, we first manually annotate quality scores for finger vein images in training set and extract five quality features of these images. Then quality scores and quality features are used to build a SVR model, which will be applied to evaluate quality for testing images. In addition, we explore the use of quality score and ascertain that quality score can be used as ancillary information to enhance recognition accuracy for finger vein. Experimental results show that our proposed method is effective for finger vein image quality evaluation.

Finger Vein Recognition based on Matching Score-Level Fusion of Gabor Features

Most methods for fusion-based finger vein recognition were to fuse different features or matching scores from more than one trait to improve performance. To overcome the shortcomings of "the curse of dimensionality" and additional running time in feature extraction, in this paper, we propose a finger vein recognition technology based on matching score-level fusion of a single trait. To enhance the quality of finger vein image, the contrast-limited adaptive histogram equalization (CLAHE) method is utilized and it improves the local contrast of normalized image after ROI detection. Gabor features are then extracted from eight channels based on a bank of Gabor filters. Instead of using the features for the recognition directly, we analyze the contributions of Gabor feature from each channel and apply a weighted matching score-level fusion rule to get the final matching score, which will be used for the last recognition. Experimental results demonstrate the CLAHE method is effective to enhance the finger vein image quality and the proposed matching score-level fusion shows better recognition performance.

Finger vein image quality evaluation using support vector machines

In an automatic finger-vein recognition system, finger-vein image quality is significant for segmentation, enhancement, and matching processes. In this paper, we propose a finger-vein image quality evaluation method using support vector machines (SVMs). We extract three features including the gradient, image contrast, and information capacity from the input image. An SVM model is built on the training images with annotated quality labels (i.e., high/low) and then applied to unseen images for quality evaluation. To resolve the class-imbalance problem in the training data, we perform oversampling for the minority class with random-synthetic minority oversampling technique. Cross-validation is also employed to verify the reliability and stability of the learned model. Our experimental results show the effectiveness of our method in evaluating the quality of finger-vein images, and by discarding low-quality images detected by our method, the overall finger-vein recognition performance is considerably improved.

A Non-Contact Finger Vein Image Quality Assessment Method

A finger vein image quality assessment method is based on both the human visual characteristics and finger vein image characteristics captured by the use of contactless and near infrared rays. We present an HSNR (signal to Noise ratio based on human visual system) finger vein image quality evaluation index by simulating the human visual system, and integrating the HSNR with effective area score, finger shifting score and contrast score to obtain the total image quality score of the finger vein image. Experimental results demonstrate that the proposed method is consistent with subjective assessment by humans, and thus can be used to describe the visual perception of the image effectively.

Study of Finger Vein Authentication Algorithms for Physical Access Control

In this study problems of using biometric authentication methods for physical access systems are analyzed. Possibilities for applying biometric authentication methods are also examined. It is suggested that fingerprint recognition methods could be applied to finger vein recognition. The experiment shows that method for fingerprint matching using hybrid shape and orientation descriptor finger vein recognition could be used in finger vein based physical access systems. Finger vein image quality has low impact for this method. Ill. 6, bibl. 21, tabl. 3 (in English; abstracts in English and Lithuanian). DOI: http://dx.doi.org/10.5755/j01.eee.121.5.1660

Sufficient pulmonary vein image quality of non-enhanced multi-detector row computed tomography for pulmonary vein isolation by catheter ablation

We evaluated the quality of non-enhanced multi-detector row computed tomography (MDCT) images of the pulmonary vein (PV) and the clinical results of catheter ablation to isolate the PV for treatment of atrial fibrillation (AF) without the use of contrast medium in patients with chronic kidney disease (CKD). We compared PV images quantitatively and qualitatively between non-enhanced and enhanced images (n = 50). Procedural parameters and clinical outcomes were compared between catheter ablation for AF referring solely to non-enhanced MDCT in CKD patients (n = 20) and using enhanced MDCT images integrated with electroanatomic mapping in non-CKD patients (n = 30). In gross anatomy, complete agreement was obtained between non-enhanced and enhanced MDCT images. Bland-Altman plots and cumulative coefficient variation showed good agreement in PV diameter determination between non-enhanced and enhanced MDCT images. There were no statistically significant differences in procedural or fluoroscopic times between PV isolation only referring to non-enhanced MDCT images and that using enhanced MDCT images integrated with electroanatomic mapping. Similarly, the ablation success rate and AF-free status at 3 months after PV isolation did not differ between PV isolation referring only to non-enhanced MDCT images and that using an electroanatomic integration system. No complications occurred in PV isolation with or without enhanced MDCT. Non-enhanced MDCT provides adequate PV image quality both quantitatively and qualitatively. The present study suggests that catheter ablation referring solely to non-enhanced MDCT images for AF could be performed with clinically acceptable results. These findings warrant further studies involving a much larger number of patients to confirm the present results.

Gadoxetic acid disodium‐enhanced magnetic resonance imaging for biliary and vascular evaluations in preoperative living liver donors: Comparison with gadobenate dimeglumine‐enhanced MRI

To compare gadoxetic acid disodium (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) with gadobenate dimeglumine (Gd-BOPTA)-enhanced MRI in preoperative living liver donors for the evaluation of vascular and biliary variations. Sixty-two living liver donors who underwent preoperative MRI were included in this study. Thirty-one patients underwent MRI with Gd-EOB-DTPA enhancement, and the other 31 underwent MRI with Gd-BOPTA enhancement. Two abdominal radiologists retrospectively reviewed dynamic T1-weighted and T1-weighted MR cholangiography images and ranked overall image qualities for the depiction of the hepatic artery, portal vein, hepatic vein, and bile duct on a 5-point scale and determined the presence and types of normal variations in each dynamic phase. Semiquantitative analysis for bile duct visualization was also conducted by calculating bile duct-to-liver contrast ratios. No statistical differences were found between the two contrast media in terms of hepatic artery or bile duct image quality by the two reviewers, or in terms of portal vein image quality by one reviewer (P > 0.05). Gd-BOPTA provided better image qualities than Gd-EOB-DTPA for the depiction of hepatic veins by both reviewers, and for the depiction of portal veins by one reviewer (P < 0.01). The two contrast media-enhanced images had similar bile duct-to-liver contrast ratios (P > 0.05). Regarding diagnostic accuracies with hepatic vascular/biliary branching types, no significant differences were observed between the two contrast media (P > 0.05). Gd-EOB-DTPA could be as useful as Gd-BOPTA for the preoperative evaluation of living liver donors, and has the advantage of early hepatobiliary phase image acquisition.