Neural architecture for robotic vision sensor that discounts uneven illumination in a manufacturing environment

Computer vision algorithms for inspection or pick-and-place operations often depend on spatially uniform illumination of a workplace. This necessitates expensive lighting fixtures. To discount effects of uneven illumination we designed and tested a neural network that can adaptively control light sensitivity at the photosensor level. Our neural network architecture consists of multiple layers with hexagonally arranged nodes. All nodes have partially overlapping receptive fields of different spatial frequencies. Feedforward connections are excitatory while feedback pathways subserve lateral inhibition. The outputs of these nodes are combined so as to maximize the signal-to-noise ratio while constantly resetting thresholds to maintain high sensitivity. Our connectionist architecture can account for many characteristics attributed to the lightness constancy phenomenon observed in biological systems. The results suggest that our module maintains high sensitivity over the whole domain of intensities without interfering with transmission of visual information embedded in spatial discontinuities of intensity.     

A geometry-based error estimation for cross-ratios

For choosing specific cross-ratios as 2D projective coordinates in various computer vision applications, a reasonable error analysis model is usually required. This investigation adopts the assumption of normal distribution for positioning errors of point features in an image to formulate the error variances of cross-ratios. Based on a geometry-based error analysis, a straightforward way of identifying the cross-ratios with minimum error variances is proposed. Simulation results show that the proposed approach, as well as a further simplified alternative, yield much better estimations of minimum error variances in terms of accuracy, cost, and stability compared with some other methods, e.g., the one based on the rule given by Georis et al. (IEEE Trans. Pattern Anal. Mach. Intell. 20 (4) (1998) 366). Some causes of the performance differences in the estimations are explained using a special configuration of point features.     

基于非接触精密视觉测量的硬盘磁头头偏测量系统

应用基于机器视觉的非接触测量技术对计算机硬盘磁头的头偏测量，不仅满足了磁头生产防污、防ESD的需要，而且实现了精密测量的需要；对测量数据的采集处理以及SPC实时监控，有效地实现了生产过程的控制和预报；与FIS系统的连接实现了生产数据的可追溯性，为生产管理现代化提供一个强有力的工具。系统已广泛应用于硬盘磁头生产线。     

基于轮廓线匹配的二维重迭物体的识别

本文提出一种基于轮廓线匹配的二维重迭物体的识别算法,并采用一种点模式匹配的快 速算法进行特征点序列的匹配,通过引进形状移位数的概念和利用问题中的各种约束条件,提 高了物体识别速度.     

Projection center calibration by motion

Camera calibration is the first step of three-dimensional machine vision. A fundamental parameter to be calibrated is the position of the camera projection center with respect to the image plane. This paper presents a method for the computation of the projection center position using images of a translating rigid object, taken by the camera itself.

Many works have been proposed in literature to solve the calibration problem, but this method has several desirable features. The projection center position is computed directly, independently of all other camera parameters. The dimensions and position of the object used for calibration can be completely unknown.

This method is based on a geometric relation between the projection center and the focus of expansion. The use of this property enables the problem to be split into two parts. First a suitable number of focuses of expansion are computed from the images of the translating object. Then the focuses of expansion are taken as landmarks to build a spatial back triangulation problem, the solution of which gives the projection center position.     

血管数字减影图象中的结构特征提取

基于Ｘ线数字减影图象的三维血管结构重建很大程度上依赖于图象中血管的有效检测和结构关系描述。本文给出一个在局部特征检测基础上的结构特征提取和组织方法，涉及结构分析之前的中间视觉处理层次，即将图象中主要结构分离出来供结构分析之用。首先用一个突出结构检测算法独立地组织和选择中轴曲线片断和边缘曲线片断，然后将两者信号相结合以验证突出结构算法获得的结果并滤除噪声结构。     

On the Yustova threshold plates

A response to criticism of threshold plates for the study of color vision developed at the Mendeleev All-Russia Research Institute of Metrology and published in 1994 is presented. The critics base their conclusions on colorimetric testing and the examination of the plates. In response to the article by M. V. Danilova and J. D. Mollon [4]. __________ Translated from Izmeritel’naya Tekhnika, No. 1, pp. 37–39, January, 2007.     

Color vision in horses (Equus caballus): Deficiencies identified using a pseudoisochromatic plate test.

In the past, equine color vision was tested with stimuli composed either of painted cards or photographic slides or through physiological testing using electroretinogram flicker photometry. Some studies produced similar results, but others did not, demonstrating that there was not yet a definitive answer regarding color vision in horses (Equus caballus). In this study, a pseudoisochromatic plate test--which is highly effective in testing color vision both in small children and in adult humans--was used for the first time on a nonhuman animal. Stimuli consisted of different colored dotted circles set against backgrounds of varying dots. The coloration of the circles corresponded to the visual capabilities of different types of color deficiencies (anomalous trichromacy and dichromacy). Four horses were tested on a 2-choice discrimination task. All horses successfully reached criterion for gray circles and demonstration circles. None of the horses were able to discriminate the protan-deutan plate or the individual protan or deutan plates. However, all were able to discriminate the tritan plate. The results suggest that horses are dichromats with color vision capabilities similar to those of humans with red-green color deficiencies. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

采用激光光刀的叶片三维面形测量方法

提出一种采用激光光刀的叶片三维面形测量方法。介绍了方法原理、系统结构、信息获取与处理方案,并给出了对实际飞机发动机叶片的面形测量结果。     

Color changes in cyanosis and the significance of congenital dichromasy and lighting

There are anecdotal reports of color vision deficient medical practitioners (particularly deuteranopes) having difficulty in recognizing cyanosis. An understanding of the color changes in oxygenated blood has led to a better understanding of the lighting needs for hospitals. Using the same database, this article investigates the propensity for color vision deficient observers to make mistakes with cyanotic patients. The possibilities for helping the observer with appropriate color of lighting are considered. The spectral reflectances of blood at varying oxygenation levels previously reported were used 7 ; 8 to calculate chromaticity and lightness. The direction of the chromaticity change was compared with the protanopic and deuteranopic confusion lines. An attempt was made to identify sources that enhanced color changes for the color deficient. The color change of blood oxygenation is closely aligned with the confusion lines of congenital dichromats (particularly protanopia) showing the potential for difficulty in making this decision. No source could be demonstrated to solve the problem or even reduce it significantly. © 2007 Wiley Periodicals, Inc. Col Res Appl, 32, 428–432, 2007