A new method for image segmentation
01 Nov 2009-Vol. 2, pp 123-125
TL;DR: A new segmentation method which is based on the morphology method, fuzzy K-means algorithm and some parts operator of the Canny algorithm, and the course of Canny operator that calculating the value and direction of grads, non-maxima suppression to the grad value and lag threshold process into the post-treatment process is introduced.
Abstract: On the basis of analyzing the blur images with noise, this paper presents a new segmentation method which is based on the morphology method, fuzzy K-means algorithm and some parts operator of the Canny algorithm. Because of the Canny's good performance on good detection, good localization and only one response to a single edge, we introduce the course of Canny operator that calculating the value and direction of grads, non-maxima suppression to the grad value and lag threshold process into our post-treatment process. Through experiments, it is demonstrated that the image segmentation method in this paper is very effective.
Citations
More filters
16 Dec 2010
TL;DR: Analysis the characteristics of meter digital structure, considering the complexity of the meter digital images background, combines dynamic threshold and global threshold binary image on instrument digital image pre-processing and utilized the connected domain screening method to fulfill the Meter digital precision positioning.
Abstract: Analysis the characteristics of meter digital structure, considering the complexity of the meter digital images background, combines dynamic threshold and global threshold binary image on instrument digital image pre-processing. Locating the digital on the instrument, eliminated pattern noise by opening operation and removed small adhesions between the digital and the border, utilized the connected domain screening method to fulfill the meter digital precision positioning. Discussed recognition methods of meter digital based on eigenvector. The results showed that the recognition rate of this solution was 97.5%, and the recognition speed was extremely fast, which perfectly met the recognition requirements: accuracy and speed.
5 citations
26 Jul 2009
TL;DR: An original binarization method based on connected operators that enables to filter and/or segment an image by preserving its contours and showed good behavior in various contexts is proposed in this paper.
Abstract: An original binarization method based on connected operators is proposed in this paper. Connected operators enable to filter and/or segment an image by preserving its contours.The proposed binarization method enables to extract relevant document objects by means of the component-tree structure. This method was compared to other binarization methods and showed good behavior in various contexts.
4 citations
Cites methods from "A new method for image segmentation..."
...Other approaches are based on edge detection algorithms [5, 14, 15, 28, 39], on fuzzy classification [6] or on multi scale [34]....
[...]
TL;DR: This work forms the problem of assigning colours in the rendered image as an energy minimization, computed using graph cut on the image grid, and demonstrates that this approach produces more coherent images than simpler approaches that make local decisions when assigning colours, or that do not use geometry.
Abstract: In the style of binary shading, shape and illumination are depicted using two colours, typically black and white, which form coherent lines and regions in the image. We formulate the problem of assigning colours in the rendered image as an energy minimization, computed using graph cut on the image grid. The terms of this energy come from two sources: appearance (shading) and geometry (depth and curvature). Our contributions are in the use of geometric information in determining colours, and how this information is incorporated into a graph cut approach. This optimization yields boundaries between black and white regions that tend towards being shorter and to run along geometric features like creases. We show a range of results, and demonstrate that this approach produces more coherent images than simpler approaches that make local decisions when assigning colours, or that do not use geometry.
4 citations
TL;DR: An uneven-lighting image binarization technique using support vector machines (SVM) that can accurately binarize the grayscale image even with uneven lighting disturbance is proposed.
Abstract: An uneven-lighting image binarization technique using support vector machines (SVM) is proposed. High-pass filtering first transforms the grayscale image into a contour image, which categorizes some pixels as edge pixels. The grayscale image is partitioned into numerous blocks. In each block, the edge pixel with largest gradient is designated as the feature edge pixel of the block, and its feature white pixel is then synthesized based on the feature black pixel. The features of a feature pixel can include its coordinates, gray level and even gradient. The trained SVM can accurately binarize the grayscale image even with uneven lighting disturbance.
4 citations
Cites background or methods from "A new method for image segmentation..."
...4(c), the Yanowitz method [29] gets a skewed threshold surface, but the lower part of the resultant binary image is still poorly rendered....
[...]
...clustered-based methods [12][17] [20][28], entropy-based methods [14][21][24], attribute-based methods [9] [13] and local methods [4][22][26][29]....
[...]
...Yanowith and Bruckstein interpolated the gray levels at the points where the image gradient is high [29]....
[...]
22 Aug 2007
TL;DR: A new binarization algorithm based on the maximum gradient of the histogram, making the target object stand out in the binary image of Chinese cheque recognition preprocessing is developed.
Abstract: This paper studies several binarization algorithms in Chinese cheque recognition preprocessing. After analyzing the histograms of gray images of 2000 cheques, we found a clue, which can be used for segmenting image. With the clue, we developed a new binarization algorithm based on the maximum gradient of the histogram, making the target object stand out in the binary image. Comparing several other commonly used binarization algorithms, the algorithm proposed by the paper has been proven in the simulating tests to be more feasible and advanced.
4 citations
Cites methods from "A new method for image segmentation..."
...In reference [4], the author proved YanowitzBruckstein’s method in reference [8] is better than other local methods, but under the same condition, the processing time of Yanowitz-Bruckstein’s algorithm is about 327 times longer than Otsu’s method....
[...]
References
More filters
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Abstract: This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
28,073 citations
"A new method for image segmentation..." refers methods in this paper
...Canny operator[2] transforms the edge detection problem into the problem of unit function maximum detection....
[...]
TL;DR: This work presents a simple and efficient implementation of Lloyd's k-means clustering algorithm, which it calls the filtering algorithm, and establishes the practical efficiency of the algorithm's running time.
Abstract: In k-means clustering, we are given a set of n data points in d-dimensional space R/sup d/ and an integer k and the problem is to determine a set of k points in Rd, called centers, so as to minimize the mean squared distance from each data point to its nearest center. A popular heuristic for k-means clustering is Lloyd's (1982) algorithm. We present a simple and efficient implementation of Lloyd's k-means clustering algorithm, which we call the filtering algorithm. This algorithm is easy to implement, requiring a kd-tree as the only major data structure. We establish the practical efficiency of the filtering algorithm in two ways. First, we present a data-sensitive analysis of the algorithm's running time, which shows that the algorithm runs faster as the separation between clusters increases. Second, we present a number of empirical studies both on synthetically generated data and on real data sets from applications in color quantization, data compression, and image segmentation.
5,288 citations
"A new method for image segmentation..." refers methods in this paper
...Fuzzy K-means algorithm[3] that divides the samples on various categories of membership according to the data is a clustering method in more common use....
[...]
Book•
15 Sep 1994
TL;DR: The fundamental principles of Digital Image Processing are explained, as well as practical suggestions for improving the quality and efficiency of image processing.
Abstract: What Is Image Processing?. Fundamentals of Digital Image Processing. The Digital Image. PROCESSING CONCEPTS. Image Enhancement and Restoration. Image Analysis. Image Compression. Image Synthesis. PROCESSING SYSTEMS. Image Origination and Display. Image Data Handling. Image Data Processing. PROCESSING IN ACTION. Image Operation Studies. Appendices. Glossary. Index.
457 citations
12 May 1998
TL;DR: A novel method for measuring the orientation of an edge is introduced and it is shown that it is without error in the noise-free case, and the wreath product transform edge detection performance is shown to be superior to many standard edge detectors.
Abstract: Wreath product group based spectral analysis has led to the development of the wreath product transform, a new multiresolution transform closely related to the wavelet transform. We derive the filter bank implementation of a simple wreath product transform and show that it is in fact, a multiresolution Roberts (1965) Cross edge detector. We also derive the relationship between this transform and the two-dimensional Haar wavelet transform. We prove that, using a non-traditional metric for measuring edge amplitude with the wreath product transform, yields a rotation and translation invariant edge detector. We introduce a novel method for measuring the orientation of an edge and show that it is without error in the noise-free case. The wreath product transform edge detection performance is shown to be superior to many standard edge detectors.
19 citations