多维直方图联合概率分布的掩模矩阵降维算法

彩色图像的分量独立处理或感知彩色空间的强度分量处理,都能达到增强图像对比度的效果,但由于没有考虑各个分量之间的联系,不能开发完全的RGB色域。多通道直方图建模技术可以改善上述缺陷,就是通过求取多个分量的直方图联合概率密度函数和累积分布函数,从而得到彩色图像的像素灰度值映射函数,但计算联合直方图的过程也导致了过高的运算复杂度。为了降低计算量,提出了掩模降维的方法,将计算多维直方图的过程转化为了计算一维直方图,从而大大降低了运算复杂度,提高运算速度,增强对比度的效果。     

无掩模光刻技术的前景

介绍了无掩模光刻技术的现状、存在的问题和前景展望;说明了无掩模光刻技术的最大优点即是降低掩模成本;同时还介绍了电子束光刻技术及其改进。     

神秘的图层蒙版

本文主要探讨了photoshop中快速蒙版和图层蒙版的几种使用技巧和使用场合，并结合多个教学实例进行深入浅出的讲解分析。目的在于抛砖引玉，以激发起同行教师及学生对Photoshop中蒙版的兴趣，并发掘出越来越多的图层蒙版的使用技巧及方法。     

The impact of new hardware on OCR designs

This paper describes the opportunities available to radically improve the performance cost ratio of OCR machines by taking advantage of new hardware which is either here, or can be made available by inter industry cooperation. Major discussions center around:(1) The page width self-scanned-array (1872 photodiodes) which can be used to greatly reduce the number of mechanical operations needed to scan a multi-line document: (2) The much reduced cost of semiconductor memory (particularly the charge coupled devices) which allows the use of memory to eliminate double scanning as well as other awkward and embarrassing operations: (3) A proposal for an LSI correlator which can provide substantial gains in all performance and cost categories, as well as providing prospects for the modest application of developments in learning theory. The leadership to provide such a correlator may have to spring from the OCR industry, including agreement on certain standards.     

Acetylcholine receptor at neuromuscular junctions by EM autoradiography using mask analysis and linear sources

Several methods of analyzing EM autoradiograms are now available. Two such procedures, the grain density distribution (or histogram) method and the mask method use the resolution of the EM autoradiographic technique to generate grain distributions expected from postulated sources, and compare these with the observed grains in the autoradiograms. These two methods are here compared in the analysis of label on linear sources: the distribution of labeled acetylcholine receptor (AChR) down the postjunctional folds of lizard and frog neuromuscular junctions. The receptors were labeled with I-25-α-bungarotoxin and the autoradiograms coated with the high resolution Kodak emulsion 129–01. We found that both methods gave similar results in confirming that the bulk of the AChR is concentrated on the thickened region of the membrane at the top ∼2000 A of the junctional folds, and that there may be a gradient of receptor concentration down the folds. The grain density distribution method is simpler, but does not lend itself easily to quantifying the extent of deviation from simple models. Although computer graphics is not necessary for either method, its use allows the expected grains from linear sources to be generated quickly, making the mask analysis a feasible routine method for assigning the extent of label in different membrane regions.     

Coverless Image Steganography Based on Image Segmentation

To resist the risk of the stego-image being maliciously altered during transmission, we propose a coverless image steganography method based on image segmentation. Most existing coverless steganography methods are based on whole feature mapping, which has poor robustness when facing geometric attacks, because the contents in the image are easy to lost. To solve this problem, we use ResNet to extract semantic features, and segment the object areas from the image through Mask RCNN for information hiding. These selected object areas have ethical structural integrity and are not located in the visual center of the image, reducing the information loss of malicious attacks. Then, these object areas will be binarized to generate hash sequences for information mapping. In transmission, only a set of stego-images unrelated to the secret information are transmitted, so it can fundamentally resist steganalysis. At the same time, since both Mask RCNN and ResNet have excellent robustness, pre-training the model through supervised learning can achieve good performance. The robust hash algorithm can also resist attacks during transmission. Although image segmentation will reduce the capacity, multiple object areas can be extracted from an image to ensure the capacity to a certain extent. Experimental results show that compared with other coverless image steganography methods, our method is more robust when facing geometric attacks.     

基于Mask R-CNN改进的遥感图像舰船检测

遥感图像中舰船朝向不确定性,舰船种类的多样性以及和其他海上及港口物体之间的相似性,使舰船检测的性能下降严重。针对这一问题,使用一种简单且有效的方法来训练有旋转不变性和Fisher判别的Mask R-CNN舰船检测模型,通过优化模型的目标函数以提高舰船检测性能,在保持原有检测模型结构不变的基础上引入两个正则化器,第一个正则化器加强训练样本旋转之前和之后的特征联系,第二个正则化器限制卷积神经网络有小的类内散度和大的类间散度。实验中,在Kaggle遥感图像船只检测数据集上验证了所提出的方法提高了检测遥感图像中舰船目标的性能。     

基于Mask RCNN的滤袋开口检测方法

滤袋开口的检测与定位在滤袋智能生产过程中占据着至关重要的地位。但由于滤袋具有柔性的特点,常规检测方法很难有效进行,且定位精度也不能满足生产要求。本文提出一种结合可变形卷积与掩码信息的多尺度目标检测器,该检测器使用可变形卷积改进主干网络高层中的固定卷积,结合特征金字塔技术实现多尺度信息融合。然后将所得多尺度信息通过区域提议网络生成候选区域,采用改进的Soft-NMS方法进行筛选,最终送入检测头进行识别与分割。本文在滤袋图像数据集上进行了实验。结果表明,提出的算法实现了滤袋开口的准确识别与高精度定位。     

基于卷积神经网络的改进机械臂抓取方法

为了提高机械臂抓取的精度,提出一种基于Mask R-CNN的机械臂抓取最佳位置检测框架。基于RGB-D图像,所提框架通过精确的实例分割确定抓取对象的类别、位置和掩码信息,由反距离加权法在去噪后的深度图上获取中心点的加权深度坐标,构成目标对象的三维目标位置,经坐标系转换得到最终的最优抓取位置。建议的框架考虑到目标对象的姿态与边缘信息,可以有效地提高抓取性能。最后,基于UR3机械臂上的抓取实验结果验证了该框架的有效性。     

实例分割和边缘优化算法的研究与实现

摘 要：近年来,实例分割技术正受到越来越多的关注。Mask R-CNN 实例分割方法是实 例分割领域中的重要方法,但是用 Mask R-CNN 方法得到的结果中,每个分割出的实例的边缘 往往不够理想,无法与真正的边缘完全吻合。针对此问题,提出了一种用显著性目标提取方法 得到的结果与 Mask R-CNN 实例分割结果相结合的方法,从而得到更好的实例分割边缘。首先, 利用 Mask R-CNN 对图片进行识别,得到实例分割的结果。然后用 PoolNet 对待检测图片进行 处理,得到图片中的显著物体信息。最后用 PoolNet 的结果对实例分割的掩码图边缘进行优化, 从而得到边缘更好的实例分割结果。经过测试,该方法可以对绝大多数待检测目标较为显著的 图片在一些重要指标上得到比 Mask R-CNN 更好的分割结果。