Wyniki wyszukiwania - Biblioteka Nauki

1

Pseudo Bayesian and Linear Regresssion Global Thresholding

100%

Aboura K.

|

tom Vol. 56, No. 1

63-72

EN

Classification is an important task in image analysis. Simply recognizing an object in an image can be a daunting step for a computer algorithm. The methodologies are often simple but rely heavily on the thresholding of the image. The operation of turning a color or gray-scale image into a black and white image is a determining step in the effectiveness of a solution. Thresholding methods perform differently in various problems where they are often used locally. Global thresholding is a difficult task in most problems. We highlight a pseudo Bayesian and a linear regression global thresholding methods that performed well in an engineering problem. The same approaches can be used in biomedical applications where the environment is better controlled.

2

Fuzzy clustering with spatial constraints for image thresholding

100%

Yang Y. , Zheng C. , Lin P.

Optica Applicata

|

2005

|

tom Vol. 35, nr 4

943-954

EN

Image thresholding plays an important role in image segmentation. This paper presents a novel fuzzy clustering based image thresholding technique, which incorporates the spatial neighborhood information into the standard fuzzy c-means (FCM) clustering algorithm. The prior spatial constraint, which is defined as weight in this paper, is inspired by the k-nearest neighbor (k-NN) algorithm and is modified from two aspects in order to improve the performance of image thresholding. The algorithm is initialized by a fast FCM algorithm, in which the iteration is carried out with the statistical gray level histogram of image instead of the conventional whole data of image; therefore its convergence is fast. Extensive experiment results and both qualitative and quantitative comparative studies with several existing methods on the thresholding of some synthetic and real images illustrate the effectiveness and robustness of the proposed algorithm.

3

Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses

63%

Gocławski J. , Sekulska-Nalewajko J. , Kuźniak E.

|

nr 3

669-684

EN

The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.

4

Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses

51%

Gocławski J. , Sekulska-Nalewajko J. , Kuźniak E.

International Journal of Applied Mathematics and Computer Science

|

2012

|

tom Vol. 22, no. 3

669-684

EN

The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.