Yen-Ching Chang

A simple histogram modification scheme for contrast enhancement

Histogram equalization (HE) is a widely used contrast enhancement (CE) method in image processing applications. The algorithm can be easily implemented; however, it tends to transform the average brightness of an image toward the middle of the gray scale. In addition, unpleasant artifacts often appear in the enhanced images. In order to overcome these drawbacks, various HE-based methods which aim at specific issues were proposed. Some of them might overlook the problems inherent in the implementations of histogram equalization and histogram specification (HS). This paper presents a simple histogram modification scheme to solve those problems according to the characteristic of implementation. Two boundary values of the support of histogram are found and set to corresponding values, respectively. The probability density function of an image is then recomputed and the updated mapping function is used to perform histogram equalization. Experimental results show that the proposed approach can effectively improve the quality of images enhanced by histogram equalization and specification methods, and even histogram redistribution methods such as gray-level grouping (GLG).

An interactive game-based shoulder wheel system for rehabilitation

Background: Increases in the aging population and in the number of accidents have resulted in more people suffering from physical impairments or disabilities. Rehabilitation therapy thus attracts greater attention as a means of helping patients recover and return to a normal life. With the extremely long and tedious nature of traditional rehabilitation, patients are reluctant to continue the entire process, thus the expected effects of the therapy cannot be obtained. Games are well known to help patients improve their concentration and shift their attention away from the discomfort of their injuries during rehabilitation. Thus, incorporating game technology into a rehabilitation program may be a promising approach. Methods: In this study, a gaming system used for shoulder rehabilitation was developed. The mechanical parts and electric circuits were integrated to mimic the functionalities of a shoulder wheel. Several games were also designed to suit the rehabilitation needs of the patients based on the age and gender differences among the individual users, enabling individuals to undergo the rehabilitation process by playing games. Two surveys were conducted to evaluate the satisfaction of the participants regarding the gaming system. Results: The results of the online survey among a larger population coincide with the responses of the hands-on participants through a paper-and-pencil survey. Statistical results suggest that the participants are willing to accept this novel approach. Conclusion: This gaming system can distract a patient from the sensation of pain or anxiety, and increase their motivation to participate in the therapeutic program. Advantages in terms of low-cost and easy setup increase the attractiveness of this new equipment for various potential users.

Efficiently Implementing the Maximum Likelihood Estimator for Hurst Exponent

This paper aims to efficiently implement the maximum likelihood estimator (MLE) for Hurst exponent, a vital parameter embedded in the process of fractional Brownian motion (FBM) or fractional Gaussian noise (FGN), via a combination of the Levinson algorithm and Cholesky decomposition. Many natural and biomedical signals can often be modeled as one of these two processes. It is necessary for users to estimate the Hurst exponent to differentiate one physical signal from another. Among all estimators for estimating the Hurst exponent, the maximum likelihood estimator (MLE) is optimal, whereas its computational cost is also the highest. Consequently, a faster but slightly less accurate estimator is often adopted. Analysis discovers that the combination of the Levinson algorithm and Cholesky decomposition can avoid storing any matrix and performing any matrix multiplication and thus save a great deal of computer memory and computational time. In addition, the first proposed MLE for the Hurst exponent was based on the assumptions that the mean is known as zero and the variance is unknown. In this paper, all four possible situations are considered: known mean, unknown mean, known variance, and unknown variance. Experimental results show that the MLE through efficiently implementing numerical computation can greatly enhance the computational performance.

Bare bones particle swarm optimization with considering more local best particles

Recently, a study of particle swarm optimization (PSO) with considering more local best particles has been proposed to improve the performance of optimization. Better performance of considering some local best particles shows that the proposed two types of variants of PSO have potential advantages over the standard PSO. The basic logic is to exploit all existing resources as fully as possible. Taking the same line, we further study how other local best particles work on bare bones PSO (BBPSO) in this paper. Experimental results show that the adopted idea does effectively raise the overall performance of optimization in most cases.

A Hurst exponent estimator based on autoregressive power spectrum estimation with order selection

The discrete-time fractional Gaussian noise (DFGN) has been proven to be a regular process. According to Wold and Kolmogorov theorems, this process can be described as an autoregressive (AR) model of an infinite order. An estimator for the Hurst exponent based on autoregressive power spectrum estimation has been proposed, but without considering order selection. In this paper, six common order selection methods for the AR model were used to select appropriate orders of the AR model in order to raise the accuracy of estimating the Hurst exponent. Experimental results show that these six AR methods with considering order selection are more accurate than the original AR method without considering order selection.

Position estimation of a mobile robot by PSO algorithm using a laser range finder

This paper shows that a laser range finder and four artificial reflectors can be used to determine the position of a mobile robot in a three-dimensional (3D) working space provided that the four reflectors are not installed in the same plane. Moreover, a particle swarm optimization (PSO) algorithm is used to filter possible measuring errors. To show the feasibility and accuracy of the proposed method, experimental results are included for illustration.

CONTRAST ENHANCEMENT AND VISUAL EFFECTS BASED ON GRAY-LEVEL GROUPING

Contrast enhancement plays a crucial role in the field of image processing. Histogram equalization is a simple and automatic method for contrast enhancement. Conventional contrast-enhancement techniques, such as histogram specification and contrast stretching, require manual parameters to achieve satisfactory results. To automatically produce enhanced results for low-contrast images, a new histogram-based optimized contrast-enhancement technique, called gray-level grouping (GLG), was proposed. GLG performs satisfactorily in dark and low-contrast images and always increases the contrast values to a maximum. Extravagant contrast enhancement typically means sacrificing the visual effects of an image. Through scrutinizing the GLG procedure, we discovered potential limitations and observed that an extra constraint on GLG enabled effective production of satisfying appearances while preserving contrast at a maximum. Experimental results showed that a simple idea led to a considerable difference in visual effects.

An efficient estimator of Hurst exponent through an autoregressive model with an order selected by data induction

The discrete-time fractional Gaussian noise (DFGN) has been proven to be a regular process. Therefore, an autoregressive (AR) model of an infinite order can describe DFGN based on Wold and Kolmogorov theorems. A fast estimation algorithm on the Hurst exponent of DFGN or discrete-time fractional Brownian motion (DFBM) has been proposed, but the algorithm did not consider the order selection of AR model. Recently, a Hurst exponent estimator based on an AR model with six existing methods of order selection has been proposed to raise the accuracy of estimating the Hurst exponent. Although the estimation accuracy has been confirmed to be better than the one without order selection, the estimator still requires computing all parameter sets through the Levinson algorithm. In order to lower computational cost, this paper proposes an efficient method of order selection, simply called data induction, which uses simulation data to induce an appropriate threshold of terminating the Levinson algorithm before computing all parameter sets. Experimental results show that the proposed data-induction method has a competitive advantage over six existing methods of order selection in terms of lowering computational cost and raising the accuracy.

INTRODUCING AN INTERPOLATION METHOD TO EFFICIENTLY IMPLEMENT AN APPROXIMATE MAXIMUM LIKELIHOOD ESTIMATOR FOR THE HURST EXPONENT

The efficiency and accuracy of estimating the Hurst exponent have been two inevitable considerations. Recently, an efficient implementation of the maximum likelihood estimator (MLE) (simply called the fast MLE) for the Hurst exponent was proposed based on a combination of the Levinson algorithm and Cholesky decomposition, and furthermore the fast MLE has also considered all four possible cases, including known mean, unknown mean, known variance, and unknown variance. In this paper, four cases of an approximate MLE (AMLE) were obtained based on two approximations of the logarithmic determinant and the inverse of a covariance matrix. The computational cost of the AMLE is much lower than that of the MLE, but a little higher than that of the fast MLE. To raise the computational efficiency of the proposed AMLE, a required power spectral density (PSD) was indirectly calculated by interpolating two suitable PSDs chosen from a set of established PSDs. Experimental results show that the AMLE through interpolation (simply called the interpolating AMLE) can speed up computation. The computational speed of the interpolating AMLE is on average over 24 times quicker than that of the fast MLE while remaining the accuracy very close to that of the MLE or the fast MLE.

Evaluating image quality using consistent grey relational grade

Purpose – Assessing image quality is a difficult task. Different demands need distinct criteria, so it is not realistic to decide which contrast enhancement method is better only through one criterion. The main purpose is to propose an efficient scheme to effectively evaluate image quality. Furthermore, the idea can be applied in other fields. Design/methodology/approach – To objectively and quantitatively assess image quality, the authors integrate four criteria into one composite criterion and use it to evaluate seven existing contrast enhancement methods. The mechanism of integration is through a newly proposed way of computing a grey relational grade (GRGd), called the consistent grey relational grade (CGRGd). Findings – In this paper, the authors propose the CGRGd, which is more efficient and consistent than other existing GRGds. When applied to image quality evaluation, the proposed CGRGd can effectively choose the best method than others. The results also indicate that the proposed CGRGd combined w...