Jingqi Yan

An Algorithm for License Plate Recognition Applied to Intelligent Transportation System

An algorithm for license plate recognition (LPR) applied to the intelligent transportation system is proposed on the basis of a novel shadow removal technique and character recognition algorithms. This paper has two major contributions. One contribution is a new binary method, i.e., the shadow removal method, which is based on the improved Bernsen algorithm combined with the Gaussian filter. Our second contribution is a character recognition algorithm known as support vector machine (SVM) integration. In SVM integration, character features are extracted from the elastic mesh, and the entire address character string is taken as the object of study, as opposed to a single character. This paper also presents improved techniques for image tilt correction and image gray enhancement. Our algorithm is robust to the variance of illumination, view angle, position, size, and color of the license plates when working in a complex environment. The algorithm was tested with 9026 images, such as natural-scene vehicle images using different backgrounds and ambient illumination particularly for low-resolution images. The license plates were properly located and segmented as 97.16% and 98.34%, respectively. The optical character recognition system is the SVM integration with different character features, whose performance for numerals, Kana, and address recognition reached 99.5%, 98.6%, and 97.8%, respectively. Combining the preceding tests, the overall performance of success for the license plate achieves 93.54% when the system is used for LPR in various complex conditions.

Classification of hyperspectral medical tongue images for tongue diagnosis

Human tongue is one of the important organs of the body, which carries abound of information of the health status. The images of the human tongue that are used in computerized tongue diagnosis of traditional Chinese medicine (TCM) are all RGB color images captured with color CCD cameras currently. However, this conversional method impedes the accurate analysis on the subjects of tongue surface because of the influence of illumination and tongue pose. To address this problem, this paper presents a novel approach to analyze the tongue surface information based on hyperspectral medical tongue images with support vector machines. The experimental results based on chronic Cholecystitis patients and healthy volunteers illustrate its effectiveness.

Automated tongue segmentation in hyperspectral images for medicine

Automatic tongue area segmentation is crucial for computer aided tongue diagnosis, but traditional intensity-based segmentation methods that make use of monochromatic images cannot provide accurate and robust results. We propose a novel tongue segmentation method that uses hyperspectral images and the support vector machine. This method combines spatial and spectral information to analyze the medical tongue image and can provide much better tongue segmentation results. The promising experimental results and quantitative evaluations demonstrate that our method can provide much better performance than the traditional method.

Efficient joint 2D and 3D palmprint matching with alignment refinement

Palmprint verification is a relatively new but promising personal authentication technique for its high accuracy and fast matching speed. Two dimensional (2D) palmprint recognition has been well studied in the past decade, and recently three dimensional (3D) palmprint recognition techniques were also proposed. The 2D and 3D palmprint data can be captured simultaneously and they provide different and complementary information. 3D palmprint contains the depth information of the palm surface, while 2D palmprint contains plenty of textures. How to efficiently extract and fuse the 2D and 3D palmprint features to improve the recognition performance is a critical issue for practical palmprint systems. In this paper, an efficient joint 2D and 3D palmprint matching scheme is proposed. The principal line features and palm shape features are extracted and used to accurately align the palmprint, and a couple of matching rules are defined to efficiently use the 2D and 3D features for recognition. The experiments on a 2D+3D palmprint database which contains 8000 samples show that the proposed scheme can greatly improve the performance of palmprint verification.

3-D Palmprint Recognition With Joint Line and Orientation Features

2-D palmprint has been recognized as an effective biometric identifier in the past decade. Recently, 3-D palmprint recognition was proposed to further improve the performance of palmprint systems. This paper presents a simple yet efficient scheme for 3-D palmprint recognition. After calculating and enhancing the mean-curvature image of the 3-D palmprint data, we extract both line and orientation features from it. The two types of features are then fused at either score level or feature level for the final 3-D palmprint recognition. The experiments on The Hong Kong Polytechnic University 3-D palmprint database, which contains 8000 samples from 400 palms show that the proposed feature extraction and fusion methods lead to promising performance.

A fusion-based method for 3D facial gender classification

In this paper, we propose a novel fusion-based gender classification method for 3D frontal neutral expression facial shape. Face landmarks, extracted from 3D face shape based on profiles and curvature, are separated as four regions. Experimental investigation to evaluate the significance of different facial regions in the task of gender classification is performed. The classification is performed by using Support Vector Machines (SVMs) based on the feature of regions. Classification results show that the upper region of face contains the highest amount of gender information. Matcher weighting fusion method is also applied to fusion the classification result of four regions. Experimental results demonstrate that fusing multiple facial features can achieve highest correct classification rate to 94.3%.

Contactless Autofeedback Iris Capture Design

Automated iris recognition is one of the most reliable biometrics in terms of identification and verification performance. One of the major challenges for automated iris recognition is to capture a high-quality image of the iris since system performance is greatly affected by poor-quality imaging. This paper describes the design and implementation of a high-quality imaging device for iris acquisition, which consists of the following four parts: 1) capture unit; 2) illumination unit; 3) feedback unit; and 4) pitching outfit. Using the proposed device for iris acquisition, it is feasible to obtain real-time, high-quality iris images, given the fact that it is also user friendly. Recognition experiments in an iris database that contains 6550 images captured by the new device are also presented in this paper.

Principal Line-Based Alignment Refinement for Palmprint Recognition

Image alignment is an important step in various biometric authentication applications such as palmprint recognition. Most of the existing palmprint alignment methods make use of some key points between fingers or in palm boundary to establish the local coordinate system for region of interest (ROI) extraction. The ROI is consequently used for feature extraction and matching. Such alignment methods usually yield a coarse alignment of the palmprint images, while many missed and false matches are actually caused by inaccurate image alignments. To improve the palmprint verification accuracy, in this paper, we present an efficient palmprint alignment refinement method. After extracting the principal lines from the palmprint image, we apply the iterative closest point method to them to estimate the translation and rotation parameters between two images. The estimated parameters are then used to refine the alignment of palmprint feature maps for a more accurate palmprint matching. The experimental results show that the proposed method greatly improves the palmprint recognition accuracy and it works in real time.

A novel hyperspectral medical sensor for tongue diagnosis

Purpose – Tongue diagnosis is a standard expert technique of traditional Chinese medicine (TCM). Computerized tongue diagnosis promises to automate the process of tongue diagnosis yet the tongue images segmentation upon which it depends is made difficult by the fact that the tongue is non‐rigid and varies greatly in size, shape, color, and texture. This paper presents a novel medical sensor system for TCM tongue diagnosis, which makes use of hyperspectral imaging technology.Design/methodology/approach – The tongue image capturing sensor device for Chinese medical is based on the theory of the pushbroom hyperspectral imager. The paper illustrates its advantages by detecting the tongue contour in the hyperspectral images.Findings – The experiments from 1,522 clinical tongue images show the validity of the system.Practical implications – In this paper, the authors propose to use hyperspectral technology for tongue diagnosis for the first time in the literature and obtain promising results.Originality/value –...

Three-dimensional surface registration: A neural network strategy

Abstract Three-dimensional surface registration is a necessary step and widely used in shape analysis, surface representation, and medical image-aided surgery. Traditional methods to fulfill such task are extremely computation complex and sometimes will obtain bad results if configured with unstructured mass data. In this paper, we propose a novel neural network strategy for efficient surface registration. Before surface registration, we use mesh PCA to normalize 3D model coordinate directions. The results and comparisons show that such neural network method is a promising approach for 3D surface registration.