Structural Indexing of Infra-red Images using Statistical Histogram Comparison
نویسندگان
چکیده
This paper aims to develop simple statistical methods for indexing into an aerial image database using a cartographic model. The images contain severe distortions due to the acquisition process and the data cannot be recovered by applying a simple Euclidean transform to the model. The underlying representation of the infra-red image map within the database is based on histograms of line-segment pair relative angles. We investigate several alternative methods for histogram comparison and conclude that statistical distance measures (such as Bhattacharyya, Matusita and Divergence) provide significant performance improvements over the standard L1 and L2 norms.
منابع مشابه
Content Based Radiographic Images Indexing and Retrieval Using Pattern Orientation Histogram
Introduction: Content Based Image Retrieval (CBIR) is a method of image searching and retrieval in a database. In medical applications, CBIR is a tool used by physicians to compare the previous and current medical images associated with patients pathological conditions. As the volume of pictorial information stored in medical image databases is in progress, efficient image indexing and retri...
متن کاملQuantification of identical and unique segments in ethylene-propylene copolymers using two dimensional liquid chromatography with infra-red detection
Hyphenating High Temperature High Performance Liquid Chromatography (HT-HPLC) with High Temperature Size Exclusion Chromatography (HT-SEC) (High Temperature Two Dimensional Liquid Chromatography (HT-HPLC x HT-SEC or HT 2D-LC)) leads to an isocratic elution in the second dimension, which in turn enables to use IR detector (quantitative detection) for monitoring the eluting polymers. Experimental...
متن کاملCartographic indexing into a database of remotely sensed images
This paper aims to develop simple statistical methods for indexing line patterns. The application vehicle used in this study involves indexing into an aerial image database using a cartographic model. The images contained in the database are of urban and semi-urban areas. The cartographic model represents a road network known to appear in a subset of the images contained within the database. Th...
متن کاملAn Efficient Statistical Content-Based Color Image Indexing and Retrieval
The world has recently witnessed a tremendous development in the various fields of information technology. Traditional databases do not provide a satisfactory environment for variant media types such as audio video and still images. An efficient statistical image indexing technique has been developed. The mean, variance, and skewness of the image color histogram distributions were used as a fea...
متن کاملScene Structural Matrix for Image Indexing
In this paper, we present a new image indexing and retrieval method for image database applications. We introduce a novel image content description feature termed Scene Structural Matrix (SSM). The SSM captures the overall structural information of the scene by indexing the geometric features of the image. In this work, we also introduce a constraint adaptive image segmentation method termed Mi...
متن کامل