As relics of history, ancient copper inscriptions are found in many countries. Information in the image or letter forms contained on copper ancient inscription has a very high value. The age and environmental factors caused damage to the surface of the inscription and also reduced the appearances of the image and letter. In this paper, we describe a novel segmentation methodology based on multi-texture features for ancient copper inscriptions which were severely damaged. The segmentation results of letters on ancient copper inscriptions by using the proposed method have an average accuracy of 90%. Based on these results, the proposed method is suitable for letter segmentation of the ancient copper inscriptions.

Worldwide Health Organization (WHO) has reported that cancer is a major cause of death around the world. The most common cancer in female is breast cancer. Radiologists typically diagnose breast abnormalities and indicate their regions from mammography. However, they might sometimes fail to detect the abnormalities or miss to correctly indicate their regions. To assist them and address the issues, a computer-aided diagnosis (CAD) is generally adopted to confirm the diagnosis results and increase the diagnosis accuracy. This study focused on precise detection of mass boundary from mammography. We adapted and applied a gray-level co-occurrence matrix (GLCM) with statistical features and edge detection which were originally used for color edges extraction. We also improved the method using pre-processing and GLCM iterations with six features: mean, diagonal moment, contrast, energy, inverse difference moment, and variance to distinguish breast mass region from other breast area (background), remove breast tissue, and detect masses. Our method was evaluated with a mini-MIAS database of mammograms (MIAS). The results indicated that the improved method was more suitable for detection of well-defined, circumscribed, ill-defined and other mass types. However, our method needed to improve to detect masses that infiltrated into high dense breast area with unclear boundary such as spiculated masses. This case would be taken into account as our future works.

In order to design a color quantization method that addresses total luminance for digital light processing (DLP) projectors, we propose a framework for optimizing color quantization and light emitted diode (LED) luminance. We evaluate the proposed method and a system using a DLP projector and a CMOS camera. Experimental results indicate that our method improves the total luminance of a projected image approximately 120% when compared with results achieved using previous models and produces better image quality.

In optical motion capture systems, it is difficult to correctly recognize markers based on their unique identifiers (IDs) in a single frame. In this paper, we propose two types of light-emitting diodes (LEDs) and cameras, infrared (IR) and RGB, in order to correctly detect and identify all markers tracking objects in a given system. To detect and estimate the three-dimensional (3D) position of the marker, we measure IR LEDs using IR stereo cameras. Furthermore, in order to identify each marker, we calculate and compare the RGB color descriptor in the vicinity of its center. Our system consists of general IR and RGB cameras, and is easy to extend by increasing the number of cameras. We implemented an IR/RGB LED marker circuit and constructed a simple motion capture system to test the effectiveness of our system. The results show that our system can detect the 3D positions and unique IDs of markers in one frame.

In this study, we propose the application of principal components analysis (PCA) to scale-spaces. PCA is a standard method used in computer vision. The translation of an input image into scale-space is a continuous operation, which requires the extension of conventional finite matrix- based PCA to an infinite number of dimensions. In this study, we use spectral decomposition to resolve this infinite eigenproblem by integration and we propose an approximate solution based on polynomial equations. To clarify its eigensolutions, we apply spectral decomposition to the Gaussian scale-space and scale-normalized Laplacian of Gaussian (LoG) space. As an application of this proposed method, we introduce a method for generating Gaussian blur images and scale-normalized LoG images, where we demonstrate that the accuracy of these images can be very high when calculating an arbitrary scale using a simple linear combination. We also propose a new Scale Invariant Feature Transform (SIFT) detector as a more practical example.

Scale-space image processing is a basic technique used for object recognition and low-level feature extraction in computer vision. Many Gaussian filtering techniques have been proposed. Recently, the spectral decomposition method was proposed, which is an infinite version of principal components analysis. Using this method, Gaussian blurred images can be represented as polynomials with a scale parameter and a Gaussian blurred image with an arbitrary scale can be obtained from simple linear combinations of the convolved eigenimages. However, the scale is limited to a small range in this method. In this study, we propose an improvement to the spectral decomposition of a Gaussian kernel by widening the scale using a piecewise polynomial representation. We present an analysis of the continuous spectral decompositions of a Gaussian kernel and their eigensolutions. Experimental results show that the proposed method can generate accurate Gaussian blurred images with an arbitrary scale and a wide scale range.

In this paper, we propose the application of principal component analysis (PCA) to scale-spaces. PCA is a standard method used in computer vision tasks such as recognition of eigenfaces. Because the translation of an input image into scale-space is a continuous operation, it requires the extension of conventional finite matrix based PCA to an infinite number of dimensions. Here, we use spectral theory to resolve this infinite eigenproblem through the use of integration, and we propose an approximate solution based on polynomial equations. In order to clarify its eigensolutions, we apply spectral decomposition to gaussian scale-space. As an application of this proposed method we introduce a method for generating gaussian blur images, demonstrating that the accuracy of such an image can be made very high by using an arbitrary scale calculated through simple linear combination.

In this paper, we review the state-of-the-art technologies for driver inattention monitoring, which can be classified into the following two main categories: 1) distraction and 2) fatigue. Driver inattention is a major factor in most traffic accidents. Research and development has actively been carried out for decades, with the goal of precisely determining the drivers' state of mind. In this paper, we summarize these approaches by dividing them into the following five different types of measures: 1) subjective report measures; 2) driver biological measures; 3) driver physical measures; 4) driving performance measures; and 5) hybrid measures. Among these approaches, subjective report measures and driver biological measures are not suitable under real driving conditions but could serve as some rough ground-truth indicators. The hybrid measures are believed to give more reliable solutions compared with single driver physical measures or driving performance measures, because the hybrid measures minimize the number of false alarms and maintain a high recognition rate, which promote the acceptance of the system. We also discuss some nonlinear modeling techniques commonly used in the literature.

For the application of Driver Inattention Monitoring System this paper propose a zero-order binocular face tracking kernel and an efficient face shape registration approach. This kernel tracks such parameters as the face position & orientation, the eyeball yaw & pitch, the eyelids animation and the mouth & jaw animation. From the view of computational cost, accuracy and robustness against registration error, camera calibration error and measurement noise, the proposed zero-order binocular face tracking kernel has shown robustness and efficiency.

In this paper we describe a multi-camera traffic monitoring system relying on the concept of probability fusion maps (PFM) to detect vehicles in a traffic scene. In the PFM, traffic images from multiple cameras are inverse perspective-mapped and registered onto a common reference frame, combining the multiple camera information to reduce the impact of occlusions. Although the unconstrained perspective projection is non-invertible, imposing the condition that the image points be co-planar allows inversion. However, in a traffic scene, the co-planarity of image points is not strictly true, so the PFM are subject to distortions. We present a new approach that reduces these distortions by projecting the camera images onto planes at different offsets from the road plane. These PFM are combined to generate a multi-level (ML) PFM. We show that the distortions in the various projection planes offset and the ML PFM thus improves vehicle detection in the presence of occlusions.

We describe an adaptive metric learning model combining the generative and the discriminative models for the face recognition. The asymptotic model based on the MDL measure is formulated for each class to estimate the variance by using small training examples. The feature fusion method is introduced to assume the missing patterns between the classes and to deal with the k-th nearest neighbor classification. The metric parameters obtained from the asymptotic MDL estimation are refined by using the synthesized feature patterns. We demonstrate an improved recognition performance on the ORL and UMIST face databases.

This paper proposes a new concept of direct visual navigation, (DVN), which superimposes virtual direction indicators and traffic information into the real road scene to give drivers efficient and direct visual navigation guidance. To align the virtual objects properly with respect to the real world, we need to solve the so-called Registration Problem in Augmented Reality (AR) context. Traditional solutions always employ a fixed and known-structure model as well as the object depth information to obtain the 3D-2D correlations, which is not possible in the case of on-road driving navigation. With the constraints of road structure and on-road vehicle motion features, this paper presents a dynamical multi-lane road shape modeling method as well as a road model matching method to simplify the 3D-2D correlation problem to the 2D-2D road model matching on projective image. Additional road shape lookup table (RSL) concept is also presented in this paper to calculate the road model matching score. The algorithms proposed in this paper are validated with the experimental results from real road test under different conditions and types of road.