Wyniki wyszukiwania - BazTech

1

An improved neural networks for stereo-camera calibration

Xing Y. J., Xing J., Sun J., Hu L.

Journal of Achievements in Materials and Manufacturing Engineering

|

2007

|

Vol. 20, nr 1-2

315-318

EN

Purpose: Improve the generalization capability and speed of back-propagation neural network (BPNN). Design/methodology/approach: In this paper, CCD cameras are calibrated implicitly using BP neural network by means of its ability to fit the complicated nonlinear mapping relation. Conventional BP algorithms easily fall into part-infinitesimal, slowing speed of convergence and exorbitance training that will influence the training result, delay convergence time and debase generalization capability. During our experiments, dense sample data are acquired by using high precisely numerical control platform, and the variances error (PVE) is adopted during training the neural network. Findings: Experiments indicate that the neural network used PVE has great generalization. The error percentages obtained from our set-up are limitedly better than those obtained through Mean Square Error (MSE). The system is generalization enough for most machine-vision applications and the calibrated system can reach acceptable precision of 3D measurement standard. Research limitations/implications: The value needs to be decided by experiments, and the reconstruction images will be distorted if the value is more than 6. Originality/value: The variances error is be adopted in BPNN first.

2

An improved region-growth algorithm for dense matching

Xing Y. J., Meng J. J., Sun J., Wang Z. Q.

Journal of Achievements in Materials and Manufacturing Engineering

|

2006

|

Vol. 18, nr 1-2

323--326

EN

Purpose: Improve the accuracy and speed of the region-growth algorithm between two 2D images. Design/methodology/approach: The algorithm includes two parts: the selection of seeds points and propagation. Some improvements are made in each one. For the first part, the best-first strategy is used to assure the accuracy of seeds. The epipolar line constraint and continuity constraint reduce the double phase matching course into single phase matching. For the second one, a dynamic and adaptive window is adopted instead of the large window. Findings: In the first section, the process of searching and the computational duties are decreased in large extent. And in the second one, the adaptive window makes the searching course more efficient in time and space. It is really difficult to get the most suitable window to search for the points as soon as possible. If it can be easily got, it will advance the efficiency of search. It is the future work. Practical implications: The method can be used in many different images, such as the structural images and the facial images. Originality/value: The original value is the region-growth algorithm, and in this paper I made some betterments to advance the efficiency and accuracy.

3

A multi-objective fuzzy genetic algorithm for job-shop scheduling problems

Xing Y. J., Wang Z. Q., Sun J., Meng J. J.

Journal of Achievements in Materials and Manufacturing Engineering

|

2006

|

Vol. 17, nr 1-2

297--300

EN

Purpose: Many uncertain factors in job shop scheduling problems are critical for the scheduling procedures. There are not genetic algorithms to solve this problem drastically. A new genetic algorithm is proposed for fuzzy job shop scheduling problems. Design/methodology/approach: The imprecise processing times are modeled as triangular fuzzy numbers (TFNs) and the due dates are modeled as trapezium fuzzy numbers in this paper. A multi-objective genetic algorithm is proposed to solve fuzzy job shop scheduling problems, in which the objective functions are conflicting. Agreement index (AI) is used to show the satisfaction of client which is defined as value of the area of processing time membership function intersection divided by the area of the due date membership function. The multi-objective function is composed of maximize both the minimum agreement and maximize the average agreement index. Findings: Two benchmark problems were used to show the effectiveness of the proposed approach. Experimental results demonstrate that the multi-objective genetic algorithm does not get stuck at a local optimum easily, and it can solve job-shop scheduling problems with fuzzy processing time and fuzzy due date effectively. Research limitations/implications: In this paper only two objective functions of genetic algorithm are taken into consideration. Many other objective functions are not applied to this genetic algorithm. Originality/value: A new multi-objective fuzzy genetic algorithm is proposed for fuzzy genetic algorithm. The genetic operations can search the optimization circularly.