A Sort of Gray-scale Morphological Dilations and Erosions

We introduce first a sort of gray-scale morphological dilations and erosions, which might have some further applications in image analysis. Then we show that the dilation and the erosion defined here form adjunctive pairs. The duality between the dilation and the erosion and some other properties, such as the commuting property with translation and homothety, of these operators are discussed as well.

New templates of CNN for extracting corners of objects in gray-scale images

A new cellular neural network (CNN) with nonlinear templates is presented forextracting convex corners of objects in gray-scale images. Application examples showed that the newCNN can even detect convex corner characteristics of objects in images with Gaussian noise.

Curve length estimation based on cubic spline interpolation in gray-scale images

This paper deals with a novel local arc length estimator for curves in gray-scale images.The method first estimates a cubic spline curve fit for the boundary points using the gray-level information of the nearby pixels,and then computes the sum of the spline segments’lengths.In this model,the second derivatives and y coordinates at the knots are required in the computation;the spline polynomial coefficients need not be computed explicitly.We provide the algorithm pseudo code for estimation and preprocessing,both taking linear time.Implementation shows that the proposed model gains a smaller relative error than other state-of-the-art methods.

Grey-scale sonography and sonoelastography for diagnosing carpal tunnel syndrome

Carpal tunnel syndrome(CTS) is a common peripheral entrapment neuropathy of the median nerve at wrist level, and is thought to be caused by compression of the median nerve in the carpal tunnel. There is no standard quantitative reference for the diagnosis of CTS. Greyscale sonography and sonoelastography(SEL) have been used as diagnostic tools. The most commonly agreed findings in grey-scale sonography for the diagnosis of CTS is enlargement of the median nerve cross-sectional area(CSA). Several authors have assessed additional parameters. "Delta CSA" is the difference between the proximal median nerve CSA at the pronator quadratus and the maximal CSA within the carpal tunnel. The "CSA ratio" is the ratio of CSA in the carpal tunnel to the CSA at the mid forearm. These additional parameters showed better diagnostic accuracy than CSA measurement alone. Recently, a number of studies have investigated the elasticity of the median nerve using SEL, and have shown that this also has diagnostic value, as it was significantly stiffer in CTS patients compared to healthy volunteers. In this review, we summarize the usefulness of grey-scale sonography and SEL in diagnosing CTS.

Multi-Valued Associative Memory Neural Network

A novel learning method for multi-valued associative memory network is introduced, which is based on Hebb rule, but utilizes more information. According to the current probe vector, the connection weights matrix could be chosen dynamically. Double-valued and multi-valued associative memory are all realized in our simulation experiment. The experimental results show that the method could enhance the associative success rate.

Scaling Properties of Feldspar and Quartz in Micro-images of Ideal Granites

The properties of feldspar and quartze are studied in this article from a fractal point of view using gray-scale micro-images of granite samples collected at the Fangshan （房山） granite body in Hebei （河北） Province, China, which can be regarded as an ideal granite in the sense of Vistelius. We found that there exist power-law relationships between the eigenvalues of the gray-scale matrices and their ranks for the feldspar and quartz. The fractal model used here is a λ-R model similar to the N-λ model proposed by Qiuming Cheng in 2005. Meanwhile, we found that average variances for the gray-scale matrices of feldspar are larger than those of quartz on the same sections, and this may be useful for auto-identification of feldspar and quartz as well as other minerals.

Multi-Level Halftoning by IGS Quantization

Improved gray-scale (IGS) quantization is a known method for re-quantizing digital gray-scale images for data compression while producing halftones by adding a level of randomness to improve visual quality of the resultant images. In this paper, first, analyzing the IGS quantizing operations reveals the capability of conserving a DC signal level of a source image through the quantization. Then, a complete procedure for producing a multi-level halftone image by IGS quantization that can achieve the DC conservation is presented. Also, the procedure uses the scanning of source pixels in an order such that geometric patterns can be prevented from occurring in the resulting halftone image. Next, the performance of the multi-level IGS halftoning is evaluated by experiments conducted on 8-bit gray-scale test images in comparison with the halftoning by error diffusion. The experimental result demonstrates that a signal level to be quantized in the IGS halftoning varies more randomly than that in the error diffusion halftoning, but not entirely randomly. Also, visual quality of the resulting halftone images was measured by subjective evaluations of viewers. The result indicates that for 3 or more-bit, in other words, 8 or more-level halftones, the IGS halftoning achieves image quality comparable to that by the error diffusion.

An Alternate Approach for Designing a Domain Specific Image Search Prototype Using Histogram

Everyone knows that thousand of words are represented by a single image. As a result, image search has become a very popular mechanism for the Web-searchers. Image search means, the search results are produced by the search engine should be a set of images along with their Web-page Unified Resource Locator (URL). Now Web-searcher can perform two types of image search, they are “Text to Image” and “Image to Image” search. In “Text to Image” search, search query should be a text. Based on the input text data, system will generate a set of images along with their Web-page URL as an output. On the other hand, in “Image to Image” search, search query should be an image and based on this image, system will generate a set of images along with their Web-page URL as an output. According to the current scenarios, “Text to Image” search mechanism always not returns perfect result. It matches the text data and then displays the corresponding images as an output, which is not always perfect. To resolve this problem, Web researchers have introduced the “Image to Image” search mechanism. In this paper, we have also proposed an alternate approach of “Image to Image” search mechanism using Histogram.

基于区间灰度的区域物流配送中心选址实证分析

结合区域物流配送中心选址评价中存在的不确定性和评价信息量获取不充足性,提出采用语言标度和灰度构成的有序对作为评价标度,并利用OWA算子获得评价指标权重和组合权重,给出一种区域物流配送中心选址方法,最后实证分析了该方法的可行性和科学性。