Sook Yoon

An available database for the research of finger vein recognition

Finger vein biometric has received considerable attentions in recent years. However, there is no approved and benchmark finger vein database for researchers to evaluate their algorithms. Furthermore, few public finger vein databases are available online. Aiming to support a benchmark database, in this paper, we introduce a representative finger vein database captured by a portable device, which is named MMCBNU_6000. Our research is novel in four aspects. First, MMCBNU_6000 is established with participation of 100 volunteers, coming from 20 countries. It contains images acquired from different persons with different skin colors. Second, statistical information of the nationality, age, gender, and blood type is recorded for further analysis on finger vein images. Third, similar to the real application, influences from translation, rotation, scale, uneven illumination, scattering, collection posture, finger tissue and finger pressure are taken into account in the imaging process. Fourth, according to the evaluation of average image gray value, image contrast and entropy on the images from the available databases, the acquired images in MMCBNU_6000 have comparable image quality.

Robust Finger Vein ROI Localization Based on Flexible Segmentation

Finger veins have been proved to be an effective biometric for personal identification in the recent years. However, finger vein images are easily affected by influences such as image translation, orientation, scale, scattering, finger structure, complicated background, uneven illumination, and collection posture. All these factors may contribute to inaccurate region of interest (ROI) definition, and so degrade the performance of finger vein identification system. To improve this problem, in this paper, we propose a finger vein ROI localization method that has high effectiveness and robustness against the above factors. The proposed method consists of a set of steps to localize ROIs accurately, namely segmentation, orientation correction, and ROI detection. Accurate finger region segmentation and correct calculated orientation can support each other to produce higher accuracy in localizing ROIs. Extensive experiments have been performed on the finger vein image database, MMCBNU_6000, to verify the robustness of the proposed method. The proposed method shows the segmentation accuracy of 100%. Furthermore, the average processing time of the proposed method is 22 ms for an acquired image, which satisfies the criterion of a real-time finger vein identification system.

A Fingerprint Recognition Scheme Based on Assembling Invariant Moments for Cloud Computing Communications

In cloud computing communications, information security entails the protection of information elements (e.g., multimedia data), only authorized users are allowed to access the available contents. Fingerprint recognition is one of the popular and effective approaches for priori authorizing the users and protecting the information elements during the communications. However, traditional fingerprint recognition approaches have demerits of easy losing rich information and poor performances due to the complex inputs, such as image rotation, incomplete input image, poor quality image enrollment, and so on. In order to overcome these shortcomings, in this paper, a new fingerprint recognition scheme based on a set of assembled invariant moment (geometric moment and Zernike moment) features to ensure the secure communications is proposed. And the proposed scheme is also based on an effective preprocessing, the extraction of local and global features and a powerful classification tool, thus it is able to handle the various input conditions encountered in the cloud computing communication. The experimental results show that the proposed method has a higher matching accuracy comparing with traditional or individual feature based methods on public databases.

Fingerprint matching based on extreme learning machine

Considering fingerprint matching as a classification problem, the extreme learning machine (ELM) is a powerful classifier for assigning inputs to their corresponding classes, which offers better generalization performance, much faster learning speed, and minimal human intervention, and is therefore able to overcome the disadvantages of other gradient-based, standard optimization-based, and least squares-based learning techniques, such as high computational complexity, difficult parameter tuning, and so on. This paper proposes a novel fingerprint recognition system by first applying the ELM and Regularized ELM (R-ELM) to fingerprint matching to overcome the demerits of traditional learning methods. The proposed method includes the following steps: effective preprocessing, extraction of invariant moment features, and PCA for feature selection. Finally, ELM and R-ELM are used for fingerprint matching. Experimental results show that the proposed methods have a higher matching accuracy and are less time-consuming; thus, they are suitable for real-time processing. Other comparative studies involving traditional methods also show that the proposed methods with ELM and R-ELM outperform the traditional ones.

Guided Gabor Filter for Finger Vein Pattern Extraction

In this paper, a novel explicit image filter, called Guided Gabor filter, is proposed to extract the finger vein pattern without any segmentation processing, and lower performance reduction for poor quality images which result from low contrast, illumination, or noise effects, etc. The proposed filter is contributed for finger vein enhancement, noise reduction, and haze removal without being affected by the brightness of the vein. It performs well not only on ridge detection like the Gabor filter, but on image enhancement as an edge-preserving smoothing operator without the gradient reversal artifacts. The experimental results show that the proposed method is able to get vein pattern more clearly and faster than the existing methods, and improve the matching performance with higher recognition rate.

Applying learning vector quantization neural network for fingerprint matching

A novel method for fingerprint matching using Learning Vector Quantization (LVQ) Neural Network (NN) is proposed. A fingerprint image is preprocessed to remove the background and to enhance the image by eliminating the LL4 sub-band component of a hierarchical Discrete Wavelet Transform (DWT). Seven invariant moment features, called as a fingerCode, are extracted from only a certain region of interest (ROI) of the enhanced fingerprint. Then an LVQ NN is trained with the feature vectors for matching. Experimental results show the proposed method has better performance with faster speed and higher accuracy comparing to the Gabor feature-based fingerCode method.

A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition

Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called “deep learning meta-architectures”. We combine each of these meta-architectures with “deep feature extractors” such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant’s surrounding area.

Intelligent fingerprint quality analysis using online sequential extreme learning machine

Because the quality of fingerprints can be degraded by diverse factors, recognizing the quality of fingerprints in advance can be beneficial for improving the performance of fingerprint authentication systems. This paper proposes an effective fingerprint quality analysis approach based on the online sequential extreme learning machine (OS-ELM). The proposed method is based not only on basic fingerprint properties, but also on the physical properties of the various sensors. Instead of splitting a fingerprint image into traditional small blocks, direction-based segmentation using the Gabor filter is used. From the segmented image, a feature set which consists of four selected independent local or global features: orientation certainty, local orientation quality, consistency, and ridge distance, is extracted. The selected feature set is robust against various factors responsible for quality degradation and can satisfy the requirements of different types of capture sensors. With the contribution of the OS-ELM classifier, the extracted feature set is used to determine whether or not a fingerprint image should be accepted as an input to the recognition system. Experimental results show that the proposed method performs better in terms of accuracy and time consumed than BPNN-based and SVM-based methods. An obvious improvement to the fingerprint recognition system is achieved by adding a quality analysis system. Other comparisons to traditional methods also show that the proposed method outperforms others.

Fingerprint Matching Using Global Minutiae and Invariant Moments

In this paper, a fingerprint matching algorithm based on global minutiae and invariant moments is proposed. Although minutiae features based method is popular in most case of fingerprint matching, minutiae are difficult to be extracted robustly in low quality image and easy to deduce false recognition. Combination of other discriminatory features can effectively strengthen the performance of the matching. A fingerprint image is first preprocessed for minutiae and reference point determination. Then, the reference point is used to align the template fingerprint and input fingerprint. Based on the aligned fingerprints, combined features are constructed from all the minutiae and their invariant moments, and a global matching algorithm is proposed to match the template and input fingerprint. The experimental results show higher performance comparing with a public algorithm over FVC2004 databases.

An Optimal Orientation Certainty Level Approach for Fingerprint Quality Estimation

Analyzing the quality of fingerprints in advance can be benefit for a fingerprint recognition system to improve its performance. Representative features for the quality assessment of fingerprint images from two existed types of capture devices are different. Orientation certainty level (OCL) is an effective method to extract image orientation feature. However it is not an effective estimation system to cooperate with the extracted features. In this paper, we explore the application of optimization theory, and support vector machine (SVM) in the field of image processing. Our proposed optimal orientation certainty level (OOCL) approach calculates the OCL for each block, extracts features from the optimal OCL system and uses the SVM classifier to determine whether an image should be accepted as an input to the recognition system. Experimental results show that the proposed OOCL method can improve the recognition rate than OCL method.