• Ankitha H
• Smitha P Ullal
• Meera A

The goal of feature extraction is to reduce the original data set by evaluating specific features, or characteristics, that distinguish one input pattern from another. Features play a vital role in image retrieval process. In this paper we propose a system where we use Fast Discrete Curvelet transform (FDCT) and Hu moments combined to extract features from the Brain MRI Data. FDCT is a multi-scale and multi-dimensional transform where we have taken wrapping based method for our study. Fast Fuzzy C-means is used for the segmentation process. Hu moments are 7 nonlinear combinations of normalized central moments that are invariant. The methodology is applied on a data set of 155 tumor and 97 normal brain MRI images and Hu moment features are extracted. The entropy of the Curvelet reconstructed image is high, whereas FCM segmented image has low. Hence it is known that the obtained segmented image is much optimized.

Fast Discrete Curvelet Transform, Fast Fuzzy C-means, Hu moments.

"Integrating an Image Moment with Image Transform for Better Energy Optimization in MRI Brain Tumor Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.b619-b624, September-2022, Available :http://www.jetir.org/papers/JETIR2209175.pdf

"Integrating an Image Moment with Image Transform for Better Energy Optimization in MRI Brain Tumor Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppb619-b624, September-2022, Available at : http://www.jetir.org/papers/JETIR2209175.pdf