On Gabor Wavelet-based Image Processing for Nissl-Stained Rat Brain Slices
نویسندگان
چکیده
This article presents our investigation on applying the Gabor waveletbased image encoding and processing technique to the nissl-stained rat brain slice images. In past, the Gabor wavelet-based method has been successfully applied to the task of face recognition. Our main question is, however, how universal the Gabor wavelet-based method is; can we apply the method to other classes of object without object-speci c optimizations? We tested a modi cation of the original face recognition system in two tasks with the brain slice images: slice classi cation and automatic slice registration. We empirically showed that the modi ed classi cation system with the voting algorithm performed very well with 100% success rate and our preliminary system for the automatic registration performs satisfactorily. Results of our similarity analyses indicated that these successful performance appeared to be attributed to information in the high-frequency range (subcortical level) rather than in the low-frequency range (cortical contour). These results not only supports universality of the Gabor wavelet-based method but
منابع مشابه
Texture Classification of Diffused Liver Diseases Using Wavelet Transforms
Introduction: A major problem facing the patients with chronic liver diseases is the diagnostic procedure. The conventional diagnostic method depends mainly on needle biopsy which is an invasive method. There are some approaches to develop a reliable noninvasive method of evaluating histological changes in sonograms. The main characteristic used to distinguish between the normal...
متن کاملAutomatic Atlas-Based Segmentation of NISSL Stained Mouse Brain Sections Using Convolutional Neural Network
In this paper, we focus on segmenting NISSL stained mouse brain images into main brain regions grey (cerebrum, brainstem, and cerebellum), fiber tracts, and ventricular systems. We feed mouse brain experimental slices acquired by the biology department and mouse brain reference slices from Allen Brain Institute into a fully convolutional neural network which is capaable of producing per-pixel p...
متن کاملP14: Segmentation Brain Tumors of FMRI Images by Gabor Wavelet Transform and Fuzzy Clustering
Today, high mortality rates due to brain tumors require early diagnosis in the early stages to treat and reduce mortality. Therefore, the use of automatic methods will be very useful for accurate examination of tumors. In recent years, the use of FMRI images has been considered for clarity and high quality for the diagnosis of tumor and the exact location of the tumor. In this study, a complete...
متن کاملImage processing by alternate dual Gabor frames
We present an application of the dual Gabor frames to image processing. Our algorithm is based on finding some dual Gabor frame generators which reconstructs accurately the elements of the underlying Hilbert space. The advantages of these duals constructed by a polynomial of Gabor frame generators are compared with their canonical dual.
متن کاملStatistical Wavelet-based Image Denoising using Scale Mixture of Normal Distributions with Adaptive Parameter Estimation
Removing noise from images is a challenging problem in digital image processing. This paper presents an image denoising method based on a maximum a posteriori (MAP) density function estimator, which is implemented in the wavelet domain because of its energy compaction property. The performance of the MAP estimator depends on the proposed model for noise-free wavelet coefficients. Thus in the wa...
متن کامل