WAVELET TRANSFORM IN IMAGE RECOGNITION

Texture segmentation and classification form a very important topic of the interdisciplinary area of signal and image processing with many applications in satellite image processing, biomedical image analysis, environmental engineering and microscopic image processing. The paper presents selected mathematical methods used for image segmentation and application of wavelet transform for the following segments classification by multiresolution decomposition of segments boundary signals. The wavelet transform approach has been adopted here and used for feature extraction allowing its use for image de-noising and resolution enhancement as well. Results of feature extraction obtained by the discrete wavelet transform are compared with that obtained by the discrete Fourier transform. Feature classification is then achieved by self-organizing neural networks. Proposed methods has been verified for simulated structures and then used for analysis of microscopic images of crystals of different shape and size. 1