scispace - formally typeset
Search or ask a question
Author

Zhenzhou Wang

Bio: Zhenzhou Wang is an academic researcher from Shandong University of Technology. The author has contributed to research in topics: Image segmentation & Segmentation. The author has an hindex of 16, co-authored 62 publications receiving 689 citations. Previous affiliations of Zhenzhou Wang include Chinese Academy of Sciences & University of Kentucky.


Papers
More filters
Journal ArticleDOI
TL;DR: By better understanding how Genetic Algorithms are used in composite structures and comparing to evolutionary computational literature, recommendations are provided to help increase the use of Genetic Algorithmms in solving composite optimisation problems in the future.

81 citations

Journal ArticleDOI
TL;DR: A novel imaging and measurement system makes use of the strong penetrability of the laser to avoid the interference of arc light and obtain the surface information of the weld pool and is significantly better than all the other methods in measuring the 3-D weld pool shapes.
Abstract: Robust measurement of the specular weld pool surface can help better understand the complex welding processes and provide feedback for robotic welding. The strong arc light and the specular surface of the weld pool make it difficult for the direct sensing measurement. In this paper, a novel imaging and measurement system is proposed, and it makes use of the strong penetrability of the laser to avoid the interference of arc light and obtain the surface information of the weld pool. By intercepting the reflection of a projected laser pattern twice, the proposed system gives a closed-form solution for each reflected ray and a closed-form solution for the corresponding point on the weld pool surface. The weld pool surface can be thus reconstructed by one-shot structured light projection. To increase the robustness of the measurement system, the least deformation principle is proposed to rectify the coefficient errors of the computed plane equation. Finally, a sequence of 3-D weld pools is reconstructed and compared with state-of-art literature. The comparison verifies that our method is significantly better than all the other methods in measuring the 3-D weld pool shapes.

76 citations

Journal ArticleDOI
TL;DR: A more versatile approach that is capable of segmenting a variety of cells or nanoparticles and tested with different types of cell and nanoparticle images verified its effectiveness.
Abstract: With the rapid development of microscopy imaging technology, the requirement for robust segmentation and quantification of cells or nanoparticles increases greatly. It remains challenging due to the diversity of the cell or nanoparticle types, the arbitrary shapes, and the large numbers of cells or nanoparticles. The most existing methods are only capable of segmenting some specific types of cells or nanoparticles. In this paper, we propose a more versatile approach that is capable of segmenting a variety of cells or nanoparticles. It consists of five parts: 1) automatic gradient image formation; 2) automatic threshold selection; 3) manual calibration of the threshold selection method for each specific type of cell or nanoparticle images; 4) manual determination of the segmentation cases for each specific type of cell or nanoparticle images; and 5) automatic quantification by iterative morphological erosion. After the parameter, N is calibrated and the segmentation case is determined manually for each specific type of cell or nanoparticle images with one or several typical images; only parts 1), 2), and 5) are needed for the rest of processing and they are automatic. The proposed approach is tested with different types of cell and nanoparticle images. Experimental results verified its effectiveness.

76 citations

Journal ArticleDOI
TL;DR: This review paper reviews the state-of-the-art real-time three-dimensional shape measurement techniques that are capable of reconstructing the dynamic objects and divides them into three classes: structured light, stereo vision and time of flight.

59 citations

Journal ArticleDOI
TL;DR: This paper proposes a monitoring system to infer the P-gas metal arc welding (GMAW) weld pool geometry from the reflected laser lines, which are projected onto the specular weld pool and reflected onto a diffusive plane.
Abstract: Controlling the welding process by monitoring the weld pool surface becomes more and more popular in robotic arc welding. In this paper, we propose a monitoring system to infer the P-gas metal arc welding (GMAW) weld pool geometry from the reflected laser lines, which are projected onto the specular weld pool and reflected onto a diffusive plane. The parallel straight lines are distorted according to the shape of the weld pool and thus contain the weld pool's shape information. Accurately computing the equations of the imaged laser lines in the world coordinate system is critical for the subsequent weld pool shape estimation. This paper focuses on accurately segmenting and identifying the reflected laser lines and novel image processing algorithms are proposed to fulfill this specific task. Experimental results verified the effectiveness of the proposed algorithms.

58 citations


Cited by
More filters
Book ChapterDOI
31 Jan 1963

2,885 citations

Journal ArticleDOI
TL;DR: Simulation results show that this proposed DR algorithm, can promote SP profitability, reduce energy costs for CUs, balance energy supply and demand in the electricity market, and improve the reliability of electric power systems, which can be regarded as a win-win strategy for both SP and CUs.

312 citations

Journal ArticleDOI
TL;DR: Simulation results show that this proposed incentive-based demand response algorithm induces demand side participation, promotes service provider and customers profitabilities, and improves system reliability by balancing energy resources, which can be regarded as a win-win strategy for both service providers and customers.

253 citations

Journal ArticleDOI
TL;DR: This paper proposes how a motivational psychology framework can be used effectively to design peer-to-peer energy trading to increase user participation, and how the outcomes of the scheme satisfy all the motivational psychology models shows its potential to attract users to participate in energy trading.

235 citations

Journal ArticleDOI
TL;DR: A novel model to enhance the recognition accuracy of the short utterance speaker recognition system is proposed using a convolutional neural network to process spectrograms, which can describe speakers better and gains the considerable accuracy as well as the reasonable convergence speed.
Abstract: During the last few years, the speaker recognition technique has been widely attractive for its extensive application in many fields, such as speech communications, domestics services, and smart terminals. As a critical method, the Gaussian mixture model (GMM) makes it possible to achieve the recognition capability that is close to the hearing ability of human in a long speech. However, the GMM is failing to recognize a short utterance speaker with a high accuracy. Aiming at solving this problem, in this paper, we propose a novel model to enhance the recognition accuracy of the short utterance speaker recognition system. Different from traditional models based on the GMM, we design a method to train a convolutional neural network to process spectrograms, which can describe speakers better. Thus, the recognition system gains the considerable accuracy as well as the reasonable convergence speed. The experiment results show that our model can help to decrease the equal error rate of the recognition from 4.9% to 2.5%.

123 citations