Ridler, T.W., Calvard, S.: Picture thresholding using an iterative selection method. IEEE transactions on Systems, Man and Cybernetics (1978)  Home/Search   Document Not in Database   Summary   Related Articles   Check

....character extraction can be performed. Since characters of a text line are usually monochrome, either darker or brighter than the background, an optimal threshold value can be found to separate the characters from the background. The iterative selection method developed by Ridler and Calvard [RC78] is used to find an adaptive optimal threshold for each text line region. This method assumes that an image region has two main levels (background and foreground) in terms of pixel intensity values. However, background in video can contain more than one intensity level. As a result, we extend the ....

T. Ridler and S. Calvard. Picture thresholding using an iterative selection method. IEEE Transactions on Systems, Man, and Cybernetics, SMC--8(8):630--632, 1978.

....for image segmentation [12] An iterative form of Otsu s method was suggested by Reddi et al. 13] to generalize the method to multilevel thresholding. This method, which is called the iterative threshold selection method, is fast, but its performance depends on the initial value of thresholds [14] For getting a good performance, it is suggested to evenly distribute the initial thresholds in the histogram space. The most difficult task is to determine the appropriate number of the thresholds automatically. Unfortunately, many thresholding algorithms, in spite of their fame, are not able ....

....the number of neurons may increase. The training data are the gray levels of the image to be segmented. The gray levels are used to train one dimensional weight vectors of the neural network. The authors are with the Computer Engineering Department, Amirkabir University of Technology, Tehran 15914, Iran. E mail: haamed, safa ce.aut.ac.ir. Manuscript received 17 Jan. 2001; revised 14 Aug. 2001; accepted 19 Mar. 2002. Recommended for acceptance by A. Khotanzad. For information on obtaining reprints of this article, please send e mail to: tpami computer.org, and reference IEEECS Log ....

[Article contains additional citation context not shown here]

T.W. Ridler and S. Calvard, "Picture Thresholding Using an Iterative Selection Method," IEEE Trans. Systems, Man, and Cybernetics, vol. 8, no. 8, pp. 630-632, 1978.

....noises (fig: 2.a) Thresholding: This step transforms the original gray level image in a binary image where pixels labeled 1 represents a possible fragment part. Thresholding simplifies the following steps and removes background noise. This is obtained through optimal threshold computation [2]. We assume that regions of two main gray levels are present in the image. The segmentation into background and fragments is defined by the optimal threshold value found iteratively as midpoint between the mean background and fragment gray level (fig: 2.b) Thinning: In this step we implemented ....

T. W. Ridler, S. Calvard, "Picture thresholding using an iterative selection method", IEEE Trans. on Systems, Man, and Cybernetics, 8(8): 630-632, August 1978

....The holes inside the rock region are the only problem, they get cleaned up using morphology as described in the next section. The thresholding operation has two free parameters: threshold value and polarity. The former is automatically determined via iterative histogram analysis of the image [11]. Images such as these tend to have bimodal histograms, with one peak for the range of rock colored gray values and another peak for the sand colored values. This algorithm tends to balance bimodal histograms evenly, placing the threshold midway between the peaks. That turns out to be generally ....

Ridler and Calvard, "Picture Thresholding Using an Iterative Selection Method," IEEE transactions on Systems, Man and Cybernetics, 1978.

....by biologists, we have created a new set of 22 features derived from morphological and geometric analysis that correspond better to the terms used by biologists. Thirteen of these features are derived from object finding and edge detection in combination with an automated thresholding method (Ridler and Calvard 1978). These include the number of objects, the ratio of the size of the largest object to the smallest object, the average distance of an object from the center of fluorescence, and the fraction of above threshold pixels along an edge. Three features are derived from the convex hull of the ....

Ridler, T. W., and Calvard, S. 1978. Picture thresholding using an iterative selection method. IEEE Transactions on Systems, Man and Cybernetics, SMC-8:630-632.

....and note head may be solid or hollow. 3 Pre processing and sub segmentation The pre processing flow of this system is shown in Figure 2. Firstly, the continuous tone image from the scanner is converted into a binary image using the iterative threshold selection method of Ridler and Calvard [8] with Lloyd s modification [5] After that, the skew of the image is detected and it is rotated to de skew. A more detailed description of the pre processing and sub segmentation process can be found in [6] 3 Begin Digitised music score Iterative Thresholding Skew correction Iterative ....

T W Ridler and S Calvard. Picture thresholding using an iterative selection method. IEEE Transactions SMC, 8(8):630--632, August 1978.

....; N Gamma 1. Assuming the prior probabilities, P (R i ) are equal, equation (10) reduces to A Probabilistic Neural Network Framework 13 T i = R i R i 1 2 : 11) A simple iterative scheme based on equation (11) for estimating the N Gamma 1 optimal thresholds and the N luminance means is [15] 1. Initialize thresholds, so that T 1 T 2 : TN Gamma1 . 2. At time step t, compute the luminance region means (t) R i = P (m;n)2R (t) i z(m; n) N (t) R i ; 12) where N (t) R i is the number of pixels in region R i at time step t and i = 1; 2; N . 3. The ....

T.W. Ridler and S. Calvard. Picture Thresholding using an Iterative Selection Method. IEEE Transactions on Systems, Man and Cybernetics, 8(8):630--632, 1978.

.... is generated, conditioning to a given set of measured field data can be done using kriging. When 0 (x ff ) ff = 1; n are given, the desired realization c should share the same second order moment with and the same data c (x ff ) 0 (x ff ) ff = 1; n. We write [24] c = K 0 ( Gamma K ) 3.9) where is the unconditioned realization, K is the kriged surface through values sampled from at the data locations x ff , and K 0 is the kriged surface through the field data. The kriged surface K 0 has all the large scale variability ....

.... has only small scale variability and precisely the amount of small scale variability that must be added back to the kriged surface K 0 to produce a distribution that satisfies the variogram [25] Since (x ff ) K (x ff ) it is obvious that c (x ff ) 0 (x ff ) It is also proved in [24] that c shares the same semivariogram with 0 . To construct the conditioned realization, we need to have an unconditioned realization which has the same first and second order moments as the given data 0 . Those unconditioned realizations can be generated by methods, for example, described ....

[Article contains additional citation context not shown here]

T. W. Ridler and S. Clavard, "Picture thresholding using an iterative selection method," IEEE Trans. Syst., Man, Cybern., vol. SMC-8, pp. 630--632, 1978.

....filtering and segmentation algorithms. Figs. 2 and 3 show two examples of this process. In Fig. 2 we have used morphological filtering ( 27] and in Fig. 3 median filtering( 22] More precisely, in the first case, we apply iteratively to the binary image I obtained using the method proposed in [24] the operator T defined as: T [I] I Omega K 1 ) fi K) I Omega K 2 ) fi K) where K is the basic structuring element of the rectangular grid and K 1 , K 2 its horizontal 1 Theta 3 and vertical 3 Theta 1 components respectively. Omega and fi denote the closing and opening operations ....

T.N. Ridler and S. Calvard. Picture thresholding using an iterative selection method, IEEE Trans. on Systems, Man and Cybernetics, Vol. 8. pp. 630-632. (1978)

....2.1.2 Adaptive Thresholding for Region Splitting What follows describes an adaptive thresholding algorithm used for choosing the partitioning lines, T v and T h , in the vertical and horizontal directions, respectively. The algorithm draws upon earlier attempts of optimal thresholding [28, 29] in a sense that it utilizes an iterative selection process to search for optimal partition indices from the orthogonal projection profiles of a region. Algorithm PARTITIONING 1. Initially for each of the two directions, k and j , set the partitioning line near the middle points denoted as T ....

T. W. Ridler and S. Calvard. "Picture thresholding using an iterative selection method," IEEE Trans. on Systems, Man, and Cybernetics, Vol. 8, No. 8, pp. 630-632, 1978.

....correlation functions of the populations in the image. Additionally, the score function is based upon an underlying assumption of Gaussian statistics. If prior information of these parameters is available, the MH algorithm is single pass; if prior information is unavailable, an iterative method [26] is used until a self consistent solution is obtained. Our algorithm, based upon indicator kriging, is a nonparametric formulation, requiring only the estimation of the spatial covariance function for an indicator variable. In practice, information of the covariance function only over a limited ....

....(18) which incorporates the spatial correlation structure only in the computation of oe i and not in i . When prior knowledge of the statistical variables OE i , i , oe i ; i = 0; 1 and ae(jx p Gamma x q j) for an image is unknown (the usual case) MH adopt an iterative scheme based on [26]. In each iteration, estimates for OE i , i , oe i and ae(jx p Gamma x q j) are generated based on current population assignments. While the iterative method of [26] converges [32] it can generate different solutions for different initial conditions. This presumably also holds for the MH ....

[Article contains additional citation context not shown here]

T.W. Ridler and S. Clavard, "Picture thresholding using an iterative selection method," IEEE Trans. Syst., Man, Cybern., vol. SMC-8, pp. 630--632, 1978.

....1979) 2. Edge detection techniques (Marr and Hildreth, 1980) 3. Region growing techniques (e.g. Fu and Mui, 1981) Global image segmentation belongs to the first category and is widely used as a simple segmentation technique, especially for binarization of images (Otsu, 1978; Weszka, 1978; Ridler and Calvard, 1978; Johanssen and Bille, 1982) It is very useful as a first stage in recognition and characterization systems or as an image compression technique. Also, the smaller amount of gray levels allows for a crude representation of the image and hence makes it easy to display or print. It can also be used ....

Ridler T.W. and S. Calvard (1978). Picture thresholding using an iterative selection method.

....correlation functions of the populations in the image. Additionally, the score function is based upon an underlying assumption of Gaussian statistics. If prior information of these parameters is available, the MH algorithm is single pass; if prior information is unavailable, an iterative method [24] is used until a self consistent solution is obtained. Our algorithm, based upon indicator kriging, is a nonparametric formulation, requiring only the estimation of the spatial covariance function for an indicator variable. In practice, information of the covariance function only over a limited ....

....(19) which incorporates the spatial correlation structure only in the computation of oe i and not in i . When prior knowledge of the statistical variables OE i , i , oe i ; i = 0; 1 and ae(jx p Gamma x q j) for an image is unknown (the usual case) MH adopt an iterative scheme based on [24]. In each iteration, estimates for these variables are generated based on current population assignments. While the iterative method of [24] converges [28] it can generate different solutions for different initial conditions. This presumably also holds for the MH method. IV. Indicator Kriging ....

[Article contains additional citation context not shown here]

T.W. Ridler and S. Clavard, "Picture thresholding using an iterative selection method," IEEE Trans. Syst., Man, Cybern., vol. SMC-8, pp. 630--632, 1978.

No context found.

Ridler, T.W., Calvard, S.: Picture thresholding using an iterative selection method. IEEE transactions on Systems, Man and Cybernetics (1978)

No context found.

T. W. Ridler and S. Calvard, "Picture thresholding using an iterative selection method," IEEE Trans. Syst. Man Cybern. SMC-8, 630--632 #1978#.

No context found.

Ridler, T.W. and S. Calvard, Picture thresholding using an iterative selection method. IEEE Trans. on Systems, Man, and Cybernetics, 1978. SMC-8(8): p. 630-632.

No context found.

T. Ridler and S. Calvard, "Picture thresholding using an iterative selection method," IEEE Trans. Systems, Man and Cybernetics 8(8), pp. 630--632, 1978.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC