Browse > Article

Organ Recognition in Ultrasound images Using Log Power Spectrum  

박수진 (LG전자 시스템IC R&D 센터)
손재곤 (삼성전자 무선사업부)
김남철 (경북대학교 전자전기공학부)
Abstract
In this paper, we propose an algorithm for organ recognition in ultrasound images using log power spectrum. The main procedure of the algorithm consists of feature extraction and feature classification. In the feature extraction, as a translation invariant feature, log power spectrum is used for extracting the information on echo of the organs tissue from a preprocessed input image. In the feature classification, Mahalanobis distance is used as a measure of the similarity between the feature of an input image and the representative feature of each class. Experimental results for real ultrasound images show that the proposed algorithm yields the improvement of maximum 30% recognition rate than the recognition algorithm using power spectrum and Euclidean distance, and results in better recognition rate of 10-40% than the recognition algorithm using weighted quefrency complex cepstrum.
Keywords
ultrasound image; log power spectrum; organ recognition; convolution model;
Citations & Related Records
연도 인용수 순위
  • Reference
1 /
[ L.R.Rabiner;R.W.Schafer ] / Digital Processing of Speech Signals
2 Power spectrum equalization for ultrasonud restoration /
[ D.Iraca;L.Landimi;L.Verazzani ] / IEEE Trans. Ultrasonics, Ferroelectronics, and Frequecny Control   ScienceOn
3 Content-based ultrasound image retrieval using magnitude frequency spectrum /
[ J.G.Son;S.H.Kim;N.C.Kim ] / Proc. SPIE Proc. Medical Imaging
4 /
[ S.Saito;K.Nakata ] / Fundamentals of Speech signal Processing
5 Classification performance and reproducibility of new parameters for quantitative ultrasoud tissue characterization /
[ R.Mia ] / D.Sc. dissertation, George Washington University
6 /
[ R.O.Duda;P.E.Hart;D.G.Stork ] / Pattern Classification
7 An approach to image classification in ultrasound, /
[ M.H.Loew;R.Mia;Zhenyu Guo ] / Proc. Applied Imagery Pattern Recognition Workshop
8 Signal Modeling techniques in speech recognition /
[ J.W.Picone ] / Proc. of the IEEE   ScienceOn
9 Signal acquisition and Processing in medical diagnostic ultrasound /
[ J.U.Quistgaard ] / IEEE Signal Processing mag   ScienceOn
10 Abdomial organ recognition using 3D mathematical morphology /
[ T.Kaneko;L.Gu;H.Fujimoto ] / Proc. IEEE Int. Conf. Pattern Recognition
11 Ultrasonic characterization of tissue structure in the vivo human liver and spleen /
[ L.A.Fellingham;F.G.Sommer ] / IEEE Trans. Sonics and Ultrasonics
12 Application of autoregressive spectral analyisis to cespstraal estimation of mean scatter spacing /
[ K.A.Wear;R.F.Wagner;M.F.Insana;T.J.Hall ] / IEEE Trans Ultrasonics, Ferroelectrics, and Frequency Control   ScienceOn
13 Restoration of medical ultrasound images using two-dimensional homomorphic deconvolution /
[ Torfinn Taxt ] / IEEE Trans. Ultrasonics, Ferroelectronics, and Frequency Control   ScienceOn
14 Knowledge-based classification and tissue labeling of MR images of human brain /
[ C.Li;D.B.Goldgof;L.O.Hall ] / IEEE Trans. Medical Imaging   ScienceOn
15 Doppler Ultrasoud /
[ H.F.routh ] / IEEE Engineering in Medicine and Biology Magazine
16 Digital processing for improvement of ultrasonic abdominal images /
[ C.N.Liu;M.Fastemi;R.C.WAAG ] / IEEE Trans. Medical Imaging
17 /
[ D.OShaughnessy ] / Spech Communications
18 Efficient cepstral normalization for robust speech recognition /
[ F.Liu;R.M.Stem;X.Huang;A.Acero ] / Proc. 6th ARPA Wordshop on Human Language Technology
19 Estimating mean scatterer spacing with the frequency-smoothed spectral autocorrelation function /
[ T.Varghese;K.D.Donohue ] / IEEE Trans. Ultrasonics, Ferroelectrics, and Frequency Control   ScienceOn
20 Syntacic pattern recognition for X-ray diagnosis of pancreatic cancer /
[ M.Ogiela;R.Tadeusiewicz ] / IEEE Engineering in medicine and Biology Magazine   ScienceOn