Ling Guan

Velocity and pressure-based partitions of horizontal and vertical trajectories for on-line signature verification

In general, shape of an on-line signature is used as a single discriminating feature. Sometimes shape of signature is used alone for verification purposes and sometimes it is used in combination with some other dynamic features such as velocity, pressure and acceleration. The shape of an on-line signature is basically formed due to the wrist and fingers movements where the wrist movement is represented by the horizontal trajectory and the movement of the fingers is represented by vertical trajectory. As the on-line signature is formed due to the combination of two movements that are essentially independent of each other, it will be more effective to use them as two separate discriminating features. Based on this observation, we propose to use these trajectories in isolation by first decomposing the pressure and velocity profiles into two partitions and then extracting the underlying horizontal and vertical trajectories. So the overall process can be thought as the process which exploits the inter-feature dependencies by decomposing signature trajectories depending upon pressure and velocity information and performs verification on each partition separately. As a result, we are able to extract eight discriminating features and among them the most stable discriminating feature is used in verification process. Further Principal Component Analysis (PCA) has been proposed to make the signatures rotation invariant. Experimental results demonstrate superiority of our approach in on-line signature verification in comparison with other techniques.

Toward natural and efficient human computer interaction

Effective detection, recognition, interpretation, and analysis of human physiological and behavioral characteristics are of fundamental importance in the design and development of intelligent human computer interaction (HCI) systems. This paper illustrates the issues and challenges in the design of such systems through two real examples, emotion recognition and face detection. In particular, we focus on audiovisual based bimodal emotion recognition, face detection in crowded scene, and facial fiducial points detection. The integration of these systems is expected to produce more robust and stronger performance, and provide more natural and friendly manmachine interaction.

Content-based image retrieval using a Gaussian mixture model in the wavelet domain

The research on Content-based Image Retrieval (CBIR) has been very active in recent years. The performance of a CBIR system can be significantly improved by selecting a good indexing feature space to represent image characteristics. In this paper, we introduce a statistical-model based technique for analyzing and extracting image features in the wavelet domain. The images are decomposed into a set of wavelet subspaces in the wavelet domain and for each wavelet subspace, a two component Gaussian mixture model is developed to describe the statistical characteristics of the wavelet coefficients. The model parameters, which are a good reflection of image features in the wavelet subspaces, are obtained by an EM (Expectation-Maximization) algorithm and employed to construct the indexing feature space for a CBIR system. We apply the new method on the Brodatz image database to demonstrate its performance. The experimental results indicate that our indexing feature space is very effective in representing image characteristics and provides a high retrieval rate in the CBIR system. When compared with some other conventional feature extraction methods, the new method achieves comparable retrieval performance with less number of features in the feature space, which means it is more computationally efficient.

Distributed video coding and transmission over wireless fading channel

Distributed video coding (DVC) has been featured by exploiting the video statistics, partially or totally at the decoder. Wireless sensor networks are supposed to have lesser complexity encoders at the expense of higher decoder complexity. Therefore DVC is more suitable to video transmission over wireless sensor networks compared to conventional video coding. Current research work on DVC is conducted for lossless channel, i.e, parity bit stream is not influenced by noise or distortion and further correlation noise due to the residual between input video frame and side information is not estimated effectively. In other words , noisy environment is not analyzed with DVC codec in recent research works. In this paper, DVC codec is enabled with the effect of AWGN noise and further a single wireless fading channel (SISO) is considered. The correlation noise is analyzed for Foreman and Carphone video sequences and relationship of correlation of adjacent key frames are discussed.

Wavelet-Based Texture Retrieval using Independent Component Analysis

In this paper, a novel approach to texture retrieval using independent component analysis (ICA) in wavelet domain is proposed. It is well recognized that the wavelet coefficients in different subbands are statistically correlated, resulting in the fact that the product of the marginal distributions of wavelet coefficients is not accurate enough to characterize the stochastic properties of texture images. To tackle this problem, we employ (ICA) in feature extraction to decorrelate the analysis coefficients in different subbands, followed by modeling the marginal distributions of the separated sources using generalized Gaussian density (GGD), and perform similarity measure based on the maximum likelihood criterion. It is demonstrated by simulation results on a database consisting of 1776 texture images that the proposed method improve the accuracy of texture image retrieval in terms of average retrieval rate, compared with the traditional method using GGD for feature extraction and Kullback-Leibler divergence for similarity measure.

A statistical approach for image feature extraction in the wavelet domain

In this paper, a new image feature extraction method based on the statistical analysis in the wavelet domain is developed for content-based image retrieval (CBIR). A two component Gaussian mixture model is developed to describe the statistical characteristics of images in the wavelet domain. The model parameters are obtained by an EM (expectation-maximization) algorithm and then employed to construct the indexing feature space for CBIR. The new method is applied on the Brodatz image database to demonstrate its performance. The preliminary experimental results indicate that the composed indexing feature space through the statistical approach is very effective in representing image features and provides a high retrieval rate in CBIR. Compared with other CBIR feature extraction methods, the new method achieves comparable retrieval performance with less number of features in the feature space, which means the new method is more computationally efficient.

On-Line Signature Verification: Directional Analysis of a Signature Using Weighted Relative Angle Partitions for Exploitation of Inter-Feature Dependencies

In this paper, we propose a new directional analysis tool for On-line signatures that decomposes the given input signature into directional bands on the basis of relative angles. Our directional analysis tool takes the independent trajectories (horizontal and vertical) as an input and then decomposes them into directional bands on the basis of relative angles. We have used both user-dependent and user-independent thresholds for selecting an optimal number of partitions for each signer. By decomposing signature trajectories based upon relative angles of an individual’s signature, the resulting process can be thought of as one that exploits inter-feature dependencies . In the verification phase, distances of each partitioned trajectory of a test signature are calculated against a similarly partitioned template trajectory for a known signer. Each partition is then weighted based on its quality and quantity. Experimental results demonstrate the superiority of our approach to On-line signature verification in comparison with other techniques.

DiStributed video coding over MIMO wireless fading channels

Distributed video coding (DVC) promises good quality with low complexity transmitters. However, previous research on DVC mostly focusses lossless channel, i.e., parity bit stream is not influenced by channel noise or distortion. This paper considers DVC over realistic wireless channel with noise and multipath fading. Note, errors in the parity bit will severely impair the system performance. We consider multiple input multiple output (MIMO) based diversity scheme to overcome the channel fading. BER and PSNR performance show that with MIMO, DVC can suitably overcome wireless channel impairments. We also determine the best transmit-receive antenna ratio for the DVC codec with more complexity at the receiver.

On-Line Signature Verification Using 1-D Velocity-Based Directional Analysis

In this paper, we propose a novel approach for identity verification based on the directional analysis of velocity-based partitions of an on-line signature. First, inter-feature dependencies in a signature are exploited by decomposing the shape (horizontal trajectory, vertical trajectory) into two partitions based on the velocity profile of the base-signature for each signer, which offers the flexibility of analyzing both low and high-curvature portions of the trajectory independently. Further, these velocity-based shape partitions are analyzed directionally on the basis of relative angles. Support Vector Machine (SVM) is then used to find the decision boundary between the genuine and forgery class. Experimental results demonstrate the superiority of our approach in on-line signature verification in comparison with other techniques.

Multimedia multimodal methodologies

This paper outlines several multimedia systems that utilize a multimodal approach. These systems include audiovisual based emotion recognition, image and video retrieval, and face and head tracking. Data collected from diverse sources/sensors are employed to improve the accuracy of correctly detecting, classifying, identifying, and tracking of a desired object or target. It is shown that the integration of multimodality data will be more efficient and potentially more accurate than if the data was acquired from a single source. A number of cutting-edge applications for multimodal systems will be discussed. An advanced assistance robot using the multimodal systems will be presented.