improvement of terrasar-x image matching using textural image features
Authors
abstract
nowadays, sar imaging systems have become more interesting for scientists. high spatial resolution of recent sar images has become a key factor for their accurate applications such as interferometry, radargrammetry and change detection. in these applications, sar image matching procedure is a critical step for conjugate point extraction which is much more difficult than the optical images. the main reasons are both high radiometric speckle noise and high geometric distortions defining by layover, shadow, and foreshortening. therefore, utilizing efficient methods to achieve a more favorable result in the sar image matching, could help us to get better output in various applications. among the sar images, study about terrasar-x is so important, because terrasar-x sensor acquires high spatial resolution images. in this paper, we used various textural image features including contrast, correlation, dissimilarity, entropy, homogeneity, optimal gradient filter, mean, second moment, variance, high pass filter and edge images. the main aim of our research was to determine how much can these features improve the sar image matching process? in our experiments, we used a small urban part of pair of terrasar-x single-look slant-range complex (ssc) images that were acquired over the city of jam, southern iran, in spotlight mode. the result shows that for some image areas with low texture, the conventional image matching algorithm (here lucas-kanade’s optical flow) is not able to detect corresponding points, while using the above textural features in image matching process causes to extract appropriate numbers of matched points.
similar resources
Vehicle Logo Recognition Using Image Matching and Textural Features
In recent years, automatic recognition of vehicle logos has become one of the important issues in modern cities. This is due to the unlimited increase of cars and transportation systems that make it impossible to be fully managed and monitored by human. In this research, an automatic real-time logo recognition system for moving cars is introduced based on histogram manipulation. In the proposed...
full textImage Colorization Using Discriminative Textural Features
This paper presents a novel approach to scribblebased image colorization. In the work reported here we have explored how to exploit the textural information to improve this process. For every scribbled image we extract the most discriminative features using linear discriminant analysis (LDA). After that, the whole image is projected onto a discriminative textural feature space. Our main contrib...
full textTextural Features for Image Classification
Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on graytone spatial dependancies, and illustrates their application in categoryidentification tasks of three different kinds of image...
full textTextural features for scribble-based image colorization
In this paper we propose how to exploit image textural features to improve scribble-based image colorization. The existing techniques work by propagating color from the user-added scribbles over the whole image. The color propagation paths are determined so as to minimize the luminance changes integrated along the path. In our method, at first linear discriminant analysis is performed over the ...
full textTextural Features for Image Database Retrieval
This paper presents two feature extraction methods and two decision methods to retrieve images having some section in them that is like the user input image. The features used are variances of gray level co-occurrences and lineangle-ratio statistics constituted by a 2-D histogram of angles between two intersecting lines and ratio of mean gray levels inside and outside the regions spanned by tho...
full textMy Resources
Save resource for easier access later
Journal title:
رادارجلد ۲، شماره ۴، صفحات ۱۲-۰
Hosted on Doprax cloud platform doprax.com
copyright © 2015-2023