Lei-Jian Liu

On the evidence inference theory

The Dempster-Shafer theory of evidence reasoning (D-S theory) has been widely discussed and used recently, because it is a reasonable, convenient, and promising method to combine uncertain information from disparate sources with different levels of abstraction. On the other hand, the D-S theory has sparked considerable debate among statisticians and knowledge engineers. The theory has been criticized and debated upon its behavior and attributes, such as high computational complexity, evidence independency requirement in its combination rule, etc. some principal problems of the D-S theory are discussed in the paper. The relationship of the D-S theory and the classical probability theory is analyzed first, and then a generalized evidence combination formula relaxing the requirement of evidence independency is presented, which makes the D-S theory more realistic to applications.

Discriminant performance of the algebraic features of handwritten character images

One of the most important topics in handwritten character recognition is the extraction of features from character images. In this paper, an algebraic feature extraction technique is applied to recognize handwritten characters. The discriminant performance of the algebraic features extracted from both handprinted characters and totally unconstrained handwritten numerals is studied. Experimental results are provided.

Image processing system for particle distributions auto-analysis of in-line holograms

This presentation describes an on-line image analysis system for the automatic distribution analysis of holographic particles in 3D space. To obtain the 3D distribution parameters of particles, sequences of 2D cross-sectional retrieved images of the particle hologram are obtained using the in-line retrieval method, and the processing of the 2D retrieved images is discussed in this presentation. To segment the candidate particles, an entropy based automatic threshold selection method is adopted. In the process of out-of-focus particle removal, the radial intensity profile of the candidates in the original image and the clearness of the candidate neighboring areas in the Sobeled image are analyzed. Experimental results are presented to show the efficiency of the approach described in this presentation.

Efficient segmentation of nuclei in different color spaces

This presentation discusses the problem of segmentation of nuclei in cytological color images in different color spaces, namely RGB and HSI color spaces, for the detection of lung cancer cells. For the segmentation in each color space, the background and foreground of the images are first defined, and the chromatic mean values of the background and foreground are then extracted. In the learning phase, based on the chromatic mean values of the background and foreground of training samples, an adaptive threshold function is constructed for each color space using the B-Spline technique. The nuclei are then segmented by thresholding using the adaptive threshold function obtained in the learning phase. Comparisons between the segmentation in RGB color space and in HSI color space are carried out.

Terrain description and obstacle detection from range image

This paper studies range images of man-made objects in outdoor environments. Our objective is to give the description of terrain, separate man-made objects from background and localize it. With the aim of this, a slope surface fitting method is proposed and applied to homogeneous dense high images derived from the range images, then a terrain description is constructed and the object detection algorithm is proposed. The final results show that our method works effectively.

Face identification using algebraic features of images

This paper proposes a new technique for the identification of face images. The basis idea is that the front face images of a person are considered as the samples coming from multiple classes, each class corresponding to the face images of one head orientation. Therefore, for each person, we can take his front facial images from a number of head orientations as training data based on which an algebraic feature extractor and a classifier can be built for this person. The problems of feature extraction, classifier design, face verification and recognition are discussed in this paper. Experimental results are also provided.

Global optimal discriminant vectors under the global Fisher discriminant criterion

The Fisher linear discriminant vector has been used as the optimal linear method in solving pattern classification problems. This paper proposes an iterative algorithm to calculate a global optimal set of discriminant vectors under the global Fisher discriminant criterion. The main advantage of our algorithm is that the scatter matrices in the subspace spanned by all discriminant vectors in the proposed optimal set have the global minimum within-class scatter and global maximum between-class scatter as compared to the Foley-Sammon local optimal set.

Pattern classification by learning from example and extension matrix

Sometimes the classifiers based on the features extracted from patterns may not be robust, in this case, to obtain better classification results, mans interruption is needed, then subjectivity and uncertainty due to mans action are followed as a result. In this paper, an algorithm able to automatically create a classifier is provided by the technique of learning from examples, with which pattern recognition, such as the facial images recognition, are completed.

Method of 3D road model construction based on sensor fusion

In order for multisensor-based mobile robot to maneuver through its environment, it should be able to navigate based on the interpretation about world deduced from its multisensory information. This paper proposes a method to construct 3D road model based on images acquired by color camera and laser radar. In our method, the points of range image correspond to the points of road edges in color images will be decided directly by the transformation between the coordinate systems of color camera and laser radar. By this way, the parallel assumption of road edges, which was required by many conventional methods, is relaxed. From these correspondent points, not only 3D road edges but road region itself including all objects within it all can be decided.

Color road segmentation for autonomous land vehicle (ALV) road following

As the efficiency of road segmentation has a direct effect on the reliability of road following and planning -- and consequently the speed of the Autonomous Land Vehicle (ALV) -- road segmentation is one of the most preliminary and important tasks for the road following and planning of ALV, and a variety of methods for color road segmentation have been proposed. This presentation proposes a new data-fusion-based color road segmentation method in which a pyramid-based data structure and the corresponding region splitting and combination techniques for the classification of sensed areas are adopted. In the segmentation process, the roads are first segmented in two 1-D color spaces, and the data fusion technique is then used to combine the two classification results, improving the accuracy of the road segmentation.