Papers by Keyword: Auto-Focusing

Abstract: The image definition identification method based on the composite model of wavelet transform and neural networks is stronger in image edge character extraction, nonlinear process, self-adapted study and pattern recognition. The paper puts forward an evaluation method of image definition based on the focusing mechanism of simulating persons eyes by neural networks and on the composite model of wavelet transformation and neural networks. The wavelet component statistics obtained by the wavelet transform are taken as the inputs of the 5 layer RBF neural network model. The model identifies the image definition applying the steepest descent method of the additional momentum in a variable step size to adjust the network weights. The compound model is first trained by 75 images from the training set, and then is tested by 102 images from the testing set. The results show that this is a very effective identification method which can obtain a higher recognition rate.

Abstract: This paper introduces a micro-assembly system based on image processing and focuses on some key technologies. The system employed some orthogonal wavelet functions to filter images and the suitible filtering effects were obtained by Symlets wavelet basis. The auto-focusing method adopted in the micro-assembly system was the combination of coarse adjustment and fine adjustment. The resolution evaluation function for coarse adjustment was based on Krisch operator and the resolution evaluation function for fine one was based on high frequency component. Experimental results show that the focusing accuracy can reach ±4.0μm. A wavelet multiscale method based on variogram function was used in the edge detection, which can eliminate noise with more details retained. Generally the system can meet the requirements of micro-assembly.

Abstract: When large-scale images acquisition conducted on an Integrated Circuit (IC) chip by using an optical microscope, multi-layer routing structure and transparent inter-layer dielectric of IC chips can interfere with auto-focusing of an optical microscope, which significantly increases the images’ acquisition time. To solve the forementioned problems, a fast acquisition system is proposed based on surface fitting. First of all, we obtain focus plane height of multiple scattered points through pre-acquisition. Then, the surface fitting method, with Thin Plate Spline (TPS) model is applied, to get the height of the rest points. Thus the system can acquire correct surface-layer images of an IC chip without background interference. The experimental results suggest that the proposed technology is highly superior to manual acquisition system and auto-focusing based acquisition system in acquisition accuracy and speed, and it also decreases the amount of manual workload by 70%-80%.

Abstract: In order to improve the test accuracy of light weapons sights optical performance parameters, designed a set of photoelectric automatic focusing system which based on image processing, and made a detailed introduction of the automatic focusing system software and hardware systems design. Experiments have repeatedly established that this auto-focusing system has stable performance and high precision. The precision of the optical sighting performance parameter testing of small weapons are improved greatly. So this system has high practice value.

Abstract: A low-lost, easily-use, non-contact three-coordinate measuring machine was researched and designed by using a laser head of CD-ROM as its detecting element, which could measure the micro-displacement of surface precisely. Researching and taking full advantage of the auto-focusing detecting principle and process circuit of CD-ROM, the machine simulated the action of disk read by using the MCU AT89S52, and read the voltage value of voice coil motor as the Z-coordinate’s value of this point. The system could work in 0.1 μm of the range of 20μm, which might be used to measure the figure of super smooth surface.

Abstract: The design of a kind of video processor with the function of auto-focusing is introduced in this paper. The video processor receives digital 8-bit YCbCr video signal. With a piece of DDR2 SDRAM as frame buffer, the video processor realizes the function of format conversion, frame up-scaling and color space conversion. The paper proposes an improved gray scale differential auto-focus algorithm and calculates the focus value of the current image real-timely. Applying the mountain climbing searching strategy to control the moving of the focus motor, and realize the function of auto-focusing. The whole design is realized in VHDL and verified with Xilinx XUPV5-LX110T FPGA developing board.