WAVELET TRANSFORM-BASED CORRELATOR FOR THE RECOGNITION OF ROTATIONALLY DISTORTED IMAGES

被引：21

作者：

AHMED, F

KARIM, MA

ALAM, MS

机构：

[1] UNIV DAYTON, CTR ELECTROOPT, DEPT ELECT ENGN, DAYTON, OH 45469 USA

[2] PURDUE UNIV, DEPT ENGN, FT WAYNE, IN 46805 USA

来源：

OPTICAL ENGINEERING | 1995年 / 34卷 / 11期

关键词：

OPTICAL REMOTE SENSING; IMAGE PROCESSING; ROTATION INVARIANCES; JOINT TRANSFORM CORRELATORS; WAVELET FEATURES; FILTER MODULATIONS; COMPOSITE REFERENCE IMAGES;

D O I：

10.1117/12.213613

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

A novel wavelet-based joint transform correlator (WJTC) for rotation-invariant pattern recognition and applications in optical image processing and remote sensing is investigated. First an optimal set of filter parameters and a mother wavelet filter are selected. These are used to extract features at different resolution from a set of rotationally distorted training images. Then a composite reference feature is formulated from these features for use in the WJTC. Simulation results for both noisy and noiseless environments are presented to verify the effectiveness of this technique.

引用

页码：3187 / 3192

页数：6

共 19 条

[1] PREPROCESSED MULTIOBJECT JOINT TRANSFORM CORRELATOR [J].