Abstract | ||
---|---|---|
The way a human brain functions is a great wonder. Numerous diseases evolve in different sections of the brain causing various functions of human body to halt. Manual detection of brain diseases is becoming a bottleneck under the circumstance of high throughput and the complexity of brain images. Automatic recognition based on the appearances of the brain cross-sectional images is becoming a more desirable scheme. This problem, however, is very challenging due to severe variations of illumination. In this research, we propose an appearance based recognition method using orientation histograms. Furthermore, we look at the possibility of applying Principal Component Analysis to reduce the dimension of the low-level features, aiming to accelerate the speed of recognition. With the experiments on the Harvard Whole Brain Atlas images (The whole brain atlas), we show the promise of the proposed method. In our study we have observed a high classification accuracy rate when using the Orientation Histogram. |
Year | DOI | Venue |
---|---|---|
2012 | 10.5220/0003805903510355 | BIOINFORMATICS: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON BIOINFORMATICS MODELS, METHODS AND ALGORITHMS |
Keywords | Field | DocType |
Bioinformatics,SIFT,Image Processing,PCA,LDA | Data mining,Disease,Computer science,Appearance based,Computational biology | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gopi Chand Nutakki | 1 | 4 | 2.55 |
Leyla Zhuhadar | 2 | 146 | 17.53 |
Robert Wyatt | 3 | 0 | 0.34 |