FEATURE EXTRACTION BY RANK-ORDER FILTERING FOR IMAGE SEGMENTATION

1988 ◽  
Vol 02 (02) ◽  
pp. 301-319 ◽  
Author(s):  
P. ZAMPERONI
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Image Segmentation ◽  
Density Function ◽  
Rank Order ◽  
Experimental Results ◽  
Textural Features ◽  
Segmentation Method ◽  
Unified Approach

The aim of this paper is to outline a unified approach to feature extraction for segmentation purposes by means of the rank-order filtering of grey values in a neighbourhood of each pixel of a digitized image. In the first section an overview of rank-order filtering for image processing is given, and a fast histogram algorithm is proposed. Section 2 deals with the extraction of a “locally most representative grey value”, defined as the maximum of the local histogram density function. In Section 3 several textural features are described, which can be extracted from the local histogram by means of rank-order filtering, and their properties are discussed. Section 4 formulates some general requirements to be met by the process of image segmentation, and describes a method based upon the features introduced in the former sections. In the last section some experimental results applied to aerial views obtained with the segmentation method of Sect. 4 are reported. These test images have been analyzed within the scope of an investigation centered on terrain recognition for agricultural and ecological purposes.

Research on Low Quality Texture Image Segmentation Background

2014 ◽  
Vol 687-691 ◽  
pp. 3616-3619
Author(s):  
Ning Liu ◽  
Hong Xia Wang
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Experimental Results ◽  
Texture Image ◽  
Segmentation Method ◽  
Otsu Thresholding ◽  
Complex Background ◽  
Segmentation Methods ◽  
Texture Image Segmentation

In image processing, the texture image segmentation is one of the most important issues. Considering the problem that the traditional segmentation methods often fail to the low quality texture image segmentation, this paper proposes a modified OTSU thresholding segmentation method. Experimental results show that the proposed method not only is well adapt to the change of brightness and contrast, but also can be applied to much complex background.

An Image Segmentation Method Using Image Enhancement and PCNN with Adaptive Parameters

2012 ◽  
Vol 490-495 ◽  
pp. 1251-1255 ◽  
Author(s):  
Hong Cai ◽  
Xue Yuan Zhang ◽  
Hai Tao Dai ◽  
Dong Ming Zhou
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Image Enhancement ◽  
Adaptive Algorithm ◽  
Experimental Results ◽  
Edge Extraction ◽  
Segmentation Method ◽  
Adaptive Parameters ◽  
Selection Of ◽  
Better Than

PCNN model is particularly suitable for image segmentation and edge extraction, but its effect depends on the selection of parameters in PCNN model and network iteration settings, which needs for a large number of artificial interaction and has limited PCNN image processing practicality. In this paper, through combining statistical properties of images and PCNN model, we present an adaptive algorithm based on the distribution of pixels to replace the artificial interaction. Experimental results show that image segmentation using image enhancement and PCNN with adaptive parameters is significantly better than the traditional PCNN image segmentation and verify the effectiveness of the method.

Comparison of Thresholding and Edge Detection Segmentation Techniques

2013 ◽  
Vol 860-863 ◽  
pp. 2783-2786
Author(s):  
Yu Bing Dong ◽  
Hai Yan Wang ◽  
Ming Jing Li
Keyword(s):  
Image Segmentation ◽  
Root Mean Square Error ◽  
Edge Detection ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Experimental Results ◽  
Mean Square ◽  
Segmentation Method ◽  
Segmentation Algorithms

Edge detection and thresholding segmentation algorithms are presented and tested with variety of grayscale images in different fields. In order to analyze and evaluate the quality of image segmentation, Root Mean Square Error is used. The smaller error value is, the better image segmentation effect is. The experimental results show that a segmentation method is not suitable for all images segmentation.

Development of Cable Inspection System Based on Image Processing

2014 ◽  
Vol 602-605 ◽  
pp. 2199-2204
Author(s):  
Huan Liu ◽  
Chao Tao Liu
Keyword(s):  
Image Processing ◽  
Feature Extraction ◽  
Image Segmentation ◽  
Image Enhancement ◽  
Image Recognition ◽  
Host Computer ◽  
Inspection System ◽  
Energy Distributions ◽  
Single Motor ◽  
Image Acquisition System

A stayed cable inspection system was developed which consists of robot, host computer, cameras and image acquisition system. The robot was driven with single motor and could climb cables of various and variable diameters. Pictures of the cables’ were taken by the robot, and the defects and mars were identified automatically with image recognition. The steps of image recognition includes image de-noising, image enhancement, image segmentation, feature extraction, and recognition with the features of the images’ histogram grayscale distributions and energy distributions.

PCNN Based Welding Seam Image Segmentation Algorithm

2012 ◽  
Vol 155-156 ◽  
pp. 861-866 ◽  
Author(s):  
Bei Ji Zou ◽  
Hao Yu Zhou ◽  
Zai Liang Chen ◽  
Hao Chen ◽  
Guo Jiang Xin
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Segmentation Algorithm ◽  
Experimental Results ◽  
Spatial Proximity ◽  
Variance Ratio ◽  
Segmentation Method ◽  
Welding Seam ◽  
Pulse Coupled Neural Network ◽  
Image Segmentation Algorithm

A new welding seam image segmentation method based on pulse-coupled neural network (PCNN) is presented in this paper. The method segments image by utilizing PCNN’s specific feature that the fire of one neuron can capture firing of its adjacent neurons due to their spatial proximity and intensity similarity. The method can automatically confirm the best iteration times by comparing the maximum of variance ratio and get the best segmentation results. Experimental results show that the proposed method has good performance in both results and execution efficiency.

A Video Image Segmentation Technology Based on Adaptive Thresholding Algorithm

2013 ◽  
Vol 380-384 ◽  
pp. 1189-1192 ◽  
Author(s):  
Hai Jun Zhao
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Variance Decomposition ◽  
Optimum Number ◽  
Segmentation Method ◽  
Class Difference ◽  
Classification Image ◽  
Maximum Variance ◽  
Important Position ◽  
Thresholding Algorithm

Image segmentation is a key step in image processing and image analysis and occupies an important position in image engineering.In this paper, basing on maximum variance between-class, an adaptive and multi-objective image segmentation method is proposed. The concrete implement is to determine adaptively the optimum number of threshold of image using the idea of variance decomposition,while calculating the weighted ratio of within class difference and class difference existing in each classification image. By comparing the ratio, the optimum number of target for image can be get. The experimental results show that the sub-images after segmentation are relatively clear and the differences between classes are obvious.

Study on Otsu Threshold Method for Image Segmentation Based on Genetic Algorithm

2014 ◽  
Vol 998-999 ◽  
pp. 925-928 ◽  
Author(s):  
Zhi Bo Xu ◽  
Pei Jiang Chen ◽  
Shi Li Yan ◽  
Tai Hua Wang
Keyword(s):  
Genetic Algorithm ◽  
Image Processing ◽  
Image Segmentation ◽  
Image Process ◽  
Segmentation Method ◽  
Threshold Method ◽  
Threshold Segmentation ◽  
Maximum Variance ◽  
Segmentation Image ◽  
Selection Of

Threshold segmentation method was widely applied in image process and the selection of threshold affected the final results of image segmentation to a large extent. In order to improve the accuracy and the calculation speed of image segmentation, an Otsu threshold segmentation method based on genetic algorithm was offered. According to the threshold and the gray scale values of pixels, the pixels were divided into two categories, and then the genetic algorithm was used to find the maximum variance between clusters and obtain the optimal threshold of segmentation image. The experimental results show that this method can be used to segment the image effectively, which make the basis for image processing and analysis in the next step.

Underwater Image Segmentation Combining Dual-Band Enhancing and Edge-Grouping

2011 ◽  
Vol 121-126 ◽  
pp. 1794-1798
Author(s):  
Kun Zhao ◽  
Yi Ping Xu ◽  
Fu Yuan Peng ◽  
Guo Liang Yang ◽  
Xin Wei Wang
Keyword(s):  
Image Segmentation ◽  
Experimental Results ◽  
Dual Band ◽  
Segmentation Method ◽  
Two Stage ◽  
Underwater Environment ◽  
Underwater Image ◽  
Grouping Method ◽  
Edge Grouping ◽  
Stability And Accuracy

In order to make segmentation more robust and accurate in the underwater environment, a two-stage segmentation method is proposed in this paper. In preprocessing stage, a dual-band enhancing technique is used to preserve the target contour and at the same time eliminate the fake edges generated by the noises; in segmentation stage, edge-grouping method is chosen for its advantageous characteristics over noisy images. Experimental results show that the proposed method can get a better performance both in stability and accuracy.

Sign in / Sign up

Export Citation Format

Share Document