Showing papers by "Kuo-Chin Fan published in 2004"

Biometric verification using thermal images of palm-dorsa vein patterns

Abstract: A novel approach to personal verification using the thermal images of palm-dorsa vein patterns is presented in this paper. The characteristics of the proposed method are that no prior knowledge about the objects is necessary and the parameters can be set automatically. In our work, an infrared (IR) camera is adopted as the input device to capture the thermal images of the palm-dorsa. In the proposed approach, two of the finger webs are automatically selected as the datum points to define the region of interest (ROI) on the thermal images. Within each ROI, feature points of the vein patterns (FPVPs) are extracted by modifying the basic tool of watershed transformation based on the properties of thermal images. According to the heat conduction law (the Fourier law), multiple features can be extracted from each FPVP for verification. Multiresolution representations of images with FPVPs are obtained using multiple multiresolution filters (MRFs) that extract the dominant points by filtering miscellaneous features for each FPVP. A hierarchical integrating function is then applied to integrate multiple features and multiresolution representations. The former is integrated by an inter-to-intra personal variation ratio and the latter is integrated by a positive Boolean function. We also introduce a logical and reasonable method to select a trained threshold for verification. Experiments were conducted using the thermal images of palm-dorsas and the results are satisfactory with an acceptable accuracy rate (FRR:2.3% and FAR:2.3%). The experimental results demonstrate that our proposed approach is valid and effective for vein-pattern verification.

Data fusion of hyperspectral and SAR images

Abstract: A novel technique is proposed for data fusion of earth remote sensing The method is developed for land cover classification based on fusion of remote sensing images of the same scene collected from multiple sources It presents a framework for fusion of multisource remote sensing images, which consists of two algorithms, referred to as the greedy modular eigenspace (GME) and the feature scale uniformity transformation (FSUT) The GME method is designed to extract features by a simple and efficient GME feature module, while the FSUT is performed to fuse most correlated features from different data sources Finally, an optimal positive Boolean function based multiclass classifier is further developed for classification It utilizes the positive and negative sample learning ability of the minimum classification error criteria to improve classification accuracy The performance of the proposed method is evaluated by fusing MODIS/ASTER airborne simulator (MASTER) images and the airborne synthetic aperture radar (SAR) images for land cover classification during the PacRim II campaign Experimental results demonstrate that the proposed fusion approach is an effective method for land cover classification in earth remote sensing, and improves the precision of image classification significantly compared to conventional single source classification

Reversible and lossless data hiding with application in digital library

Abstract: Recently, the development of data hiding techniques to hide annotations, confidential data, or side information into multimedia attracts the attention of researchers in various fields, especially in digital library. One of the essential tasks in digital library is the digitization of arts together with the corresponding textural descriptions. The purpose of data hiding is to embed relating textural description into the image to form an embedded image instead of two separate files (text file and image file). The hidden textural description and the original host image can be extracted and reconstructed from the embedded image in the reverse data extraction process. However, the reconstructed host image will more or less be distorted by utilizing traditional data hiding methods. In this paper, we propose a novel lossless data hiding method based on pixel decomposition and pair-wise logical computation. In addition to the lossless reconstruction of original host images, the results generated by the proposed method can also obtain high data hiding capacity and good visual quality. Furthermore, the task of tampering detection can also be achieved in the proposed method to ensure content authentication. Experimental results demonstrate the feasibility and validity of our proposed method.

Motion detection based on two-piece linear approximation for cumulative histograms of ratio images in intelligent transportation systems

Abstract: Motion detection is widely used as the key module for extracting moving objects from image sequences in intelligent transportation systems (ITS). In most of the motion detection methods, backgrounds are subtracted from the captured images. This category of methods is called background subtraction. Since standard intensity can be expressed as the multiplication of illumination and reflectance, illumination changes will produce a poor difference image from background subtraction and affect the accuracy of motion detection. In this paper, we use ratio images as the basis of motion detection. To suitably threshold the target images, two-piece linear approximation is proposed for cumulative histograms to prevent the problems in the searching of peaks and valleys in histograms. Experimental results demonstrate that two-piece linear approximation for cumulative histograms performs very well in thresholding the target images. Moreover, the superiority of motion detection based on ratio images over motion detection based on difference images is also depicted in the experiments.