Human factor assessment of the legibility of five numeric visual displays

Experiments have been carried out designed to find on human factor considerations alone, which of five available displays would be most suitable for the next generation of Post Office telephone exchange switchboard.     

Applying CIM technology to image factories

Image processing allows the automation of the business transaction, turning “paper factories” into “image factories.” This burgeoning new area of computerization needs new paradigms, theories, and methods to maximize its effectiveness at cutting time and costs. This paper investigates what this new area of computerization can gain from CIM technology. It examines the similarities between the processing of computer images in a paperless business environment and the processing of materials into products in the manufacturing plant. These similarities will allow us to apply mature, well-tested CIM techniques to emerging image factories.     

改进的正则化模型在图像恢复中的应用

目的 由拟合项与正则项组成的海森矩阵,如果不具有特殊结构,其逆矩阵计算比较困难,为克服此缺点,提出一种海森矩阵可分块对角化的牛顿投影迭代算法。方法 首先,用L₂范数描述拟合项,用自变量是有界变差函数的复合函数刻画正则项,建立能量泛函正则化模型。其次,引入势函数,将正则化模型转化为增广能量泛函。再次,构造预条件矩阵,使得海森矩阵可分块对角化。最后,为防止牛顿投影迭代算法收敛到局部最优解,采用回溯线性搜索算法和改进的Barzilai-Borwein步长更新准则使得算法全局收敛。结果 针对图像去模糊正则化模型容易使边缘平滑和产生阶梯效应“两难”问题,提出一种新的正则化模型和牛顿投影迭代算法。仿真结果表明,“两难”问题通过本文算法得到了很好的解决。结论 与其他正则化图像去模糊模型相比,本文算法明显改善图像的质量,如有效地保护图像的边缘,抑制阶梯效应,相对偏差和误差较小,较高的峰值信噪比和结构相似测度。     

基于图形理解的汉字构形自动分析系统

汉字构形自动分析系统将计算机视觉,图像理解等领域中业已成熟的诸多技术,应用到汉字构形学研究的各主要环节。以GB2312 80汉字集合所生成的构件图片为基础对象,生成了汉字部件构形描述,有效率达90%以上。     

Evaluating dynamic texture descriptors to recognize human iris in video image sequence

Pattern Analysis and Applications - In the last decades, iris features have been widely used in biometric systems. Because iris features are virtually unique for each person, their usage is highly...     

The effect of picture element failure on the legibility of a matrix display image

A technique is described that enables an image processor to emulate both the spatial structure and contrast capabilities of a matrix display. It is possible to store a large number of precomputed spatial patterns to allow specific failure types to be added to text images. One could thus observe how defects in the matrix, created during the fabrication process, would effect legibility. It was revealed that certain failure types could be tolerated by the human operator much more than others. Display yield could be increased by devising techniques to convert intolerable failures into failure types which were more acceptable to the operator. Photographic images are presented to examplify the procedure.     

各向异性小波收缩用于图像分割

已经证明2维情况下一般各向异性扩散与HAAR小波收缩在一定条件下是等价的,基于此等价性的各向异性小波收缩结合了小波收缩与各向异性扩散两种方法的优势。将各向异性小波收缩用于多尺度图像分割,提出一种对多尺度各向异性扩散分割方法的改进方法——多尺度各向异性小波收缩图像分割算法。该算法利用各向异性小波收缩对图像中像素灰度值进行扩散,在尽可能保持边缘的情况下,使同质区域内相邻像素灰度随尺度数增加趋于相同,构造基于尺度的空间栈,从而完成对目标的分割,是一种非监督图像分割方法。对比实验结果表明,该算法在有效处理区域内部不一致性的同时,能够准确地定位目标边缘,实现同质区域的融合,完成分割任务,且该算法收敛速度高于多尺度各向异性扩散分割方法。     

Applying an XC6200 to real-time image processing

This implementation of a two-dimensional discrete cosine transform demonstrates the development of a suitable architectural style for a specific technology-in this case, the Xilinx XC6200 FPGA series. The design exploits distributed arithmetic, parallelism, and pipelining to achieve high-performance custom-computing implementation     

数字图像处理技术在瓶装液检测中的应用

对数字图像处理技术在瓶装液杂质检测中的应用进行了详细的研究,针对瓶装液检测的高速、高精度、实时性特点,提出了瓶身液体检测的实用算法,并通过VC 对含有杂质瓶装液被拍摄到的图象进行处理,运用合理的边缘点数统计方法准确的检测出瓶装液中是否含有杂质,很好的验证了算法的有效性。     

Applying image registration algorithm combined with CNN model to video image stitching

The Journal of Supercomputing - The purposes are to explore the video image stitching technique of Unmanned Aerial Vehicles (UAVs), expand the application of image registration algorithms and new...     

Applying logistic regression to relevance feedback in image retrieval systems

This paper deals with the problem of image retrieval from large image databases. A particularly interesting problem is the retrieval of all images which are similar to one in the user's mind, taking into account his/her feedback which is expressed as positive or negative preferences for the images that the system progressively shows during the search. Here we present a novel algorithm for the incorporation of user preferences in an image retrieval system based exclusively on the visual content of the image, which is stored as a vector of low-level features. The algorithm considers the probability of an image belonging to the set of those sought by the user, and models the logit of this probability as the output of a generalized linear model whose inputs are the low-level image features. The image database is ranked by the output of the model and shown to the user, who selects a few positive and negative samples, repeating the process in an iterative way until he/she is satisfied. The problem of the small sample size with respect to the number of features is solved by adjusting several partial generalized linear models and combining their relevance probabilities by means of an ordered averaged weighted operator. Experiments were made with 40 users and they exhibited good performance in finding a target image (4 iterations on average) in a database of about 4700 images. The mean number of positive and negative examples is of 4 and 6 per iteration. A clustering of users into sets also shows consistent patterns of behavior.     

Vectorial approximations of infinite-dimensional covariance descriptors for image classification

Computational Visual Media -     

小波的文本图像区分及其在文献信息数字化中的应用

目前,OCR技术对文本图像区域自动区分的效果还不够精确,进而影响了OCR技术在文献信息数字化过程中的工作效率.针对这一局限,提出了一种基于小波的文本图像区分方法.方法首先对扫描区域进行小波分解,然后使用分解系数构建分解能量,最后依据分解能量大小对文本图像进行自动区分.结果表明,该方法对文本图像的区分效果较好,减少了在使用OCR技术进行文献信息数字化时的人为干预,有利于提高文献信息数字化过程的自动化水平.最后通过实验仿真验证了该方法的有效性.