Background Machine learning-based beer bottle-defect detection is a complex technology that runs automatically;however,it consumes considerable memory,is expensive,and poses a certain danger when training novice opera...Background Machine learning-based beer bottle-defect detection is a complex technology that runs automatically;however,it consumes considerable memory,is expensive,and poses a certain danger when training novice operators.Moreover,some topics are difficult to learn from experimental lectures,such as digital image processing and computer vision.However,virtual simulation experiments have been widely used to good effect within education.A virtual simulation of the design and manufacture of a beer bottle-defect detection system will not only help the students to increase their image-processing knowledge,but also improve their ability to solve complex engineering problems and design complex systems.Methods The hardware models for the experiment(camera,light source,conveyor belt,power supply,manipulator,and computer)were built using the 3DS MAX modeling and animation software.The Unreal Engine 4(UE4)game engine was utilized to build a virtual design room,design the interactive operations,and simulate the system operation.Results The results showed that the virtual-simulation system received much better experimental feedback,which facilitated the design and manufacture of a beer bottle-defect detection system.The specialized functions of the functional modules in the detection system,including a basic experimental operation menu,power switch,image shooting,image processing,and manipulator grasping,allowed students(or virtual designers)to easily build a detection system by retrieving basic models from the model library,and creating the beer-bottle transportation,image shooting,image processing,defect detection,and defective-product removal.The virtual simulation experiment was completed with image processing as the main body.Conclusions By mainly focusing on bottle mouth defect detection,the detection system dedicates more attention to the user and the task.With more detailed tasks available,the virtual system will eventually yield much better results as a training tool for image processing education.In addition,a novel visual perception-thinking pedagogical framework enables better comprehension than the traditional lecture-tutorial style.展开更多
Liquid crystal thermography is a high-resolution, non-intrusive optical technique for full-field temperaturemeasurement. We present the detailed calibration data for the thermochromic liquid crystal (TLC) with auseful...Liquid crystal thermography is a high-resolution, non-intrusive optical technique for full-field temperaturemeasurement. We present the detailed calibration data for the thermochromic liquid crystal (TLC) with auseful range of 41—60 ℃. The calibration is done with true color image processing by using an isothermalcalibrator. The hue-temperature curve of the TLC is obtained, and the measurement uncertainty isanalyzed. Combined with the image noise reduction technique of a 5×5 median filter, the measurementaccuracy of the liquid crystal thermography can be significantly improved by approximately 57.1%.展开更多
Complex surface shape measurement has been a focus topic in the CAD/CAM field. A popular method for measuring dimensional information is using a 3D coordinate measuring machine (CMM)with a touch trigger probe. The mea...Complex surface shape measurement has been a focus topic in the CAD/CAM field. A popular method for measuring dimensional information is using a 3D coordinate measuring machine (CMM)with a touch trigger probe. The measurement set up with CMM, however, is a time consuming task and the accuracy of the measurement deteriorates as the speed of measurement increase. Non-contact measurement is favored since high speed measurement can be achieved and problems with vibration and friction can be eliminated. Although much research has been conducted in non-contact measurement using image capturing and processing schemes, accuracy is poor and measurement is limited. Some optical technologies developed provide a good accuracy but the dynamic range and versatility is very limited. A novel fiber-optic sensor used for the inspection of complex internal contours is presented in this paper, which is able to measure a surface shape in a non-contact manner with high accuracy and high speed, and is compact and flexible to be incorporated into a CMM. Modulation functions for tilted surface shape measurement, based on the Gaussian distribution of the emitting beam from single-mode fiber (SMF), were derived for specular reflection. The feasibility of the proposed measurement principle was verified by simulations.展开更多
The colorimetric method for real-time measurement of temperature field using ICCD as sensor was developed. In order to ensure the accuracy and sensitivity, the relationship between the ratio response of two-color imag...The colorimetric method for real-time measurement of temperature field using ICCD as sensor was developed. In order to ensure the accuracy and sensitivity, the relationship between the ratio response of two-color images and radiant property of body, transmission property of filter, spectral response of ICCD is discussed. The analysis is based on computer calculation of the established mathematical model. On the basis of the analysis, optimum wavelengths are obtained for a given sensor system. Experimental work was carried out to check the correctness of the theoretical results. The method is useful for general purpose of study and design of the developed system.展开更多
基金Project"863":Physical Model-based Dynamic Evolution Technology of a Complex Scene(2015AA016404)the SDUST Excellent Teaching Team Construction Plan.
文摘Background Machine learning-based beer bottle-defect detection is a complex technology that runs automatically;however,it consumes considerable memory,is expensive,and poses a certain danger when training novice operators.Moreover,some topics are difficult to learn from experimental lectures,such as digital image processing and computer vision.However,virtual simulation experiments have been widely used to good effect within education.A virtual simulation of the design and manufacture of a beer bottle-defect detection system will not only help the students to increase their image-processing knowledge,but also improve their ability to solve complex engineering problems and design complex systems.Methods The hardware models for the experiment(camera,light source,conveyor belt,power supply,manipulator,and computer)were built using the 3DS MAX modeling and animation software.The Unreal Engine 4(UE4)game engine was utilized to build a virtual design room,design the interactive operations,and simulate the system operation.Results The results showed that the virtual-simulation system received much better experimental feedback,which facilitated the design and manufacture of a beer bottle-defect detection system.The specialized functions of the functional modules in the detection system,including a basic experimental operation menu,power switch,image shooting,image processing,and manipulator grasping,allowed students(or virtual designers)to easily build a detection system by retrieving basic models from the model library,and creating the beer-bottle transportation,image shooting,image processing,defect detection,and defective-product removal.The virtual simulation experiment was completed with image processing as the main body.Conclusions By mainly focusing on bottle mouth defect detection,the detection system dedicates more attention to the user and the task.With more detailed tasks available,the virtual system will eventually yield much better results as a training tool for image processing education.In addition,a novel visual perception-thinking pedagogical framework enables better comprehension than the traditional lecture-tutorial style.
基金supported by the National Natural Science Foundation of China under Grant No.50806045.
文摘Liquid crystal thermography is a high-resolution, non-intrusive optical technique for full-field temperaturemeasurement. We present the detailed calibration data for the thermochromic liquid crystal (TLC) with auseful range of 41—60 ℃. The calibration is done with true color image processing by using an isothermalcalibrator. The hue-temperature curve of the TLC is obtained, and the measurement uncertainty isanalyzed. Combined with the image noise reduction technique of a 5×5 median filter, the measurementaccuracy of the liquid crystal thermography can be significantly improved by approximately 57.1%.
文摘Complex surface shape measurement has been a focus topic in the CAD/CAM field. A popular method for measuring dimensional information is using a 3D coordinate measuring machine (CMM)with a touch trigger probe. The measurement set up with CMM, however, is a time consuming task and the accuracy of the measurement deteriorates as the speed of measurement increase. Non-contact measurement is favored since high speed measurement can be achieved and problems with vibration and friction can be eliminated. Although much research has been conducted in non-contact measurement using image capturing and processing schemes, accuracy is poor and measurement is limited. Some optical technologies developed provide a good accuracy but the dynamic range and versatility is very limited. A novel fiber-optic sensor used for the inspection of complex internal contours is presented in this paper, which is able to measure a surface shape in a non-contact manner with high accuracy and high speed, and is compact and flexible to be incorporated into a CMM. Modulation functions for tilted surface shape measurement, based on the Gaussian distribution of the emitting beam from single-mode fiber (SMF), were derived for specular reflection. The feasibility of the proposed measurement principle was verified by simulations.
文摘The colorimetric method for real-time measurement of temperature field using ICCD as sensor was developed. In order to ensure the accuracy and sensitivity, the relationship between the ratio response of two-color images and radiant property of body, transmission property of filter, spectral response of ICCD is discussed. The analysis is based on computer calculation of the established mathematical model. On the basis of the analysis, optimum wavelengths are obtained for a given sensor system. Experimental work was carried out to check the correctness of the theoretical results. The method is useful for general purpose of study and design of the developed system.