Hongkun Wu

Watershed-Based Morphological Separation of Wear Debris Chains for On-Line Ferrograph Analysis

Abstract Separation and characterization of wear debris from ferrograph images are demanded for on-line analysis. However, particle overlapping issue associated with wear debris chains has markedly limited this technique due to the difficulty in effectively segmenting individual particles from the chains. To solve this bottleneck problem, studies were conducted in this paper to establish a practical method for wear debris separation for on-line analysis. Two conventional watershed approaches were attempted. Accordingly, distance-based transformation had a problem with oversegmentation, which led to overcounting of wear debris. Another method, by integrating the ultimate corrosion and condition expansion (UCCE), introduced boundary-offset errors that unavoidably affected the boundary identification between particles, while varying the corrosion scales and adopting a low-pass filtering method improved the UCCE with satisfactory results. Finally, together with a termination criterion, an automatic identification process was applied with real on-line wear debris images sampled from a mineral scraper gearbox. With the satisfactory separation result, several parameters for characterization were extracted and some statistics were constructed to obtain an overall evaluation of existing particles. The proposed method shows a promising prospect in on-line wear monitoring with deep insight into wear mechanism.

Image de-hazing from the perspective of noise filtering

Abstract Digital images captured in outdoor environment are easily polluted by haze, which will degrade the conveyed information. To overcome this problem, a large number of researches have been conducted for image haze removal, among which the approach based on the dark channel prior assumption is in recent years considered as the state-of-the-art. This method is primarily dependent on consolidation of observations. However, in the proposed method, a theoretical perspective is adopted for image, which considers the degraded image as a product contaminated by noise. Two maps are constructed to label the noise severity and atmospheric light. The parameters involved are optimized via Particle Swarm Optimization with a penalty function in terms of hue change. Experimental results were compared with seven available approaches, along with an analysis on algorithm complexity. These analyses verify the effectiveness, efficiency, wide adaptability and theoretical soundness of the proposed approach.

Modeling Wear State Evolution Using Real-Time Wear Debris Features

ABSTRACT Because wear is one of the most typical causes of decreasing performance in running machines, monitoring wear is regarded as a crucial technology in maintaining the health of machines. However, monitoring wear is not a fully mature process because quantifying the development of wear in real time is a challenging task because there is no universal indicator. To meet this need, wear-oriented dynamic modeling with online ferrographic images was used to investigate and then describe a real-time wear state. This investigation was carried out by combining three wear indices to describe the wear rate, the wear mechanism, and the severity of wear. A binary classifier method is also proposed to classify these wear stages in the three extracted indices. A strategy to identify the dynamic transition of wear states with adaptive parameters is also developed and then a four-ball wear test is carried out to verify the method. The results indicate that this modeling strategy can accurately identify a developing wear state that is characterized by stages. This proposed method is better at monitoring the health evolution of a machine system than just detecting faults.

Three dimensional shape measurement of wear particle by iterative volume intersection

The morphology of wear particle is a fundamental indicator where wear oriented machine health can be assessed. Previous research proved that thorough measurement of the particle shape allows more reliable explanation of the occurred wear mechanism. However, most of current particle measurement techniques are focused on extraction of the two-dimensional (2-D) morphology, while other critical particle features including volume and thickness are not available. As a result, a three-dimensional (3-D) shape measurement method is developed to enable a more comprehensive particle feature description. The developed method is implemented in three steps: (1) particle profiles in multiple views are captured via a camera mounted above a micro fluid channel; (2) a preliminary reconstruction is accomplished by the shape-from-silhouette approach with the collected particle contours; (3) an iterative re-projection process follows to obtain the final 3-D measurement by minimizing the difference between the original and the re-projected contours. Results from real data are presented, demonstrating the feasibility of the proposed method.

Single-scale center-surround Retinex based restoration of low-illumination images with edge enhancement

Restoring images captured under low-illuminations is an essential front-end process for most image based applications. The Center-Surround Retinex algorithm has been a popular approach employed to improve image brightness. However, this algorithm in its basic form, is known to produce color degradations. In order to mitigate this problem, here the Single-Scale Retinex algorithm is modified as an edge extractor while illumination is recovered through a non-linear intensity mapping stage. The derived edges are then integrated with the mapped image to produce the enhanced output. Furthermore, in reducing color distortion, the process is conducted in the magnitude sorted domain instead of the conventional Red-Green-Blue (RGB) color channels. Experimental results had shown that improvements with regard to mean brightness, colorfulness, saturation, and information content can be obtained.

A review on brightness preserving contrast enhancement methods for digital image

Image enhancement is an imperative step for many vision based applications. For image contrast enhancement, popular methods adopt the principle of spreading the captured intensities throughout the allowed dynamic range according to predefined distributions. However, these algorithms take little or no consideration into account of maintaining the mean brightness of the original scene, which is of paramount importance to carry the true scene illumination characteristics to the viewer. Though there have been significant amount of reviews on contrast enhancement methods published, updated review on overall brightness preserving image enhancement methods is still scarce. In this paper, a detailed survey is performed on those particular methods that specifically aims to maintain the overall scene illumination characteristics while enhancing the digital image.

Image Edge Tracking via Ant Colony Optimization

A good edge plot should use continuous thin lines to describe the complete contour of the captured object. However, the detection of weak edges is a challenging task because of the associated low pixel intensities. Ant Colony Optimization (ACO) has been employed by many researchers to address this problem. The algorithm is a meta-heuristic method developed by mimicking the natural behaviour of ants. It uses iterative searches to find the optimal solution that cannot be found via traditional optimization approaches. In this work, ACO is employed to track and repair broken edges obtained via conventional Sobel edge detector to produced a result with more connected edges.

Oscillatory Particle Swarm Optimizer

Abstract The Particle Swarm Optimization (PSO) algorithm is an attractive meta-heuristic approach for difficult optimization problems. It is able to produce satisfactory results when classical analytic methods cannot be applied. However, the design of PSO was usually based on ad-hoc attempts and its behavior could not be exactly specified. In this work, we propose to drive particle into oscillatory trajectories such that the search space can be covered more completely. A difference equation based analysis is conducted to reveal conditions that guarantee trajectory oscillation and solution convergence. The settings of cognitive and social learning factors and the inertia weight are then determined. In addition, a new strategy in directing these parameters to follow a linearly decreasing profile with a perturbation is formulated. Experiments on function optimizations are conducted and compared to currently available methods. Results have confirmed that the proposed Oscillatory Particle Swarm Optimizer (OSC-PSO) outperforms other recent PSO algorithms using adaptive inertia weights.

Enhancement of Low Illumination Images based on an Optimal Hyperbolic Tangent Profile

Abstract Contrast enhancement is a critical pre-processing stage for many image based applications. It is frequently encountered that the illumination condition, while capturing the image, is imperfect. Specific algorithms have to be applied to restore these images from, for instance, the degradation due to low illumination. An adaptive enhancement method is developed here that tackles the image quality enhancement problem from an optimization perspective. In particular, the input image intensity is mapped to the output based on a weighted hybrid of a hyperbolic tangent and a linear profile. The mapping parameters are optimized, with regard to maximizing the image global entropy, by using the Golden Section Search algorithm for its implementation efficiency. Moreover, user interventions are not necessary. Better qualitative and comparable quantitative performances are obtained from experiments, with regard to the increase of brightness, information content and suppression of unwanted artifacts, as compared to recent profile mapping based methods.

Image De-hazing Based on Polynomial Estimation and Steepest Descent Concept

Digital images captured in hazy conditions suffer from colour distortion and loss of contrast, posing difficulties in being applied for further applications. Due to the existed challenge and its great significance, a large amount of research has been conducted for image de-hazing. Among the image haze removal methods, the algorithm based on dark channel prior is proved to be the most effective. Furthermore, the introduction of guided filter has boosted its efficiency to a large extent. However, the requirement for transmission refinement and the assumption that the transmission is the same in each colour channel still make the DCP concept based methods time consuming and suffer from colour distortion. To solve this problem, an approach named as Image De-hazing Based on Polynomial Estimation and Steepest Descent Concept (IDBPESDC) is proposed, which derives the pixel-wised transmission that does not require any further refinement. Additionally, image de-hazing procedures based on the steepest descent concept are adopted so that the objective of saturation enhancement under the minimum hue change constraint is achieved. Experiments are conducted on one hundred hazy images, processed by the proposed method and four other available approaches. Results are analysed qualitatively and quantitatively, which verified the effectiveness and efficiency of the proposed algorithm.