Two-dimensional Digital Halftoning Based on Weighted Least-squares for Laser Carving Gravure Cylinder Technology and Detecting System of Ink Cells via Neural Network

Laser carving technology has the advantages of higher resolution, focusing precision and digital modulation. It has been widely used in laser engraving gravure plate and laser plate processing. However, the switching of the laser has only two states, so the halftoning processing plays a vary important role in the laser plate. In this paper, we present a 2-dimensional digital halftoning method based on weighted leastsquares(WLS) which can significantly gain high quality image during the processing of laser plate. Two main strategies were made. The first is adding a procedure to partition into several finite regions using Kmeans image segmentation and least squares to reduce the total quantizing error. The second is that the statistics of the mean and variance of the gray-scale pixel of each clustering are calculated and the new energy function is constructed using the weighted least squares method, which the reciprocal of the variance of the segmented regions are referred to as the weighting operator. The analysis and simulation results show that the proposed algorithm produces better gray-scale halftone image quality when we increase the number of clustering with a certain range. A performance measure for halftone image is used to evaluate our method. We apply neural network to build up a detecting system of ink cells in gravure cylinder.We use different thresholds and experimental sigma values that compare to experimental results. Binarization images are obtained through adaptive threshold segmentation, which regards the value of gaps and dark tone as the characteristic value when they start to detecting. We extract size and surface defects of ink cells for grading. The areas of ink cells are deemed to size characteristics. Then we classify the ink cells into two classes by using of neural network. The experimental results consider neural network model that produce consequences.