Loading...
Please wait, while we are loading the content...
Similar Documents
Image And Pixel Based Scheme For Bleeding Detection In Wireless Capsule Endoscopy Images
| Content Provider | Semantic Scholar |
|---|---|
| Author | Vani, V. Prashanth, K. V. |
| Copyright Year | 2016 |
| Abstract | Bleeding detection techniques that are widely used in digital image analysis can be categorized in 3 main types: image based, pixel based and patch based. For computer-aided diagnosis of bleeding detection in Wireless Capsule Endoscopy (WCE), the most efficient choice among these remains still a problem. In this work, different types of Gastro intestinal bleeding problems: Angiodysplasia, Vascular ecstasia and Vascular lesions detected through WCE are discussed. Effective image processing techniques for bleeding detection in WCE employing both image based and pixel based techniques have been presented. The quantitative analysis of the parameters such as accuracy, sensitivity and specificity shows that YIQ and HSV are suitable color models; while LAB color model incurs low value of sensitivity. Statistical based measurements achieves higher accuracy and specificity with better computation speed up as compared to other models. Classification using K-Nearest Neighbor is deployed to verify the performance. The results obtained are compared and evaluated through the confusion matrix. |
| Starting Page | 161 |
| Ending Page | 175 |
| Page Count | 15 |
| File Format | PDF HTM / HTML |
| DOI | 10.1007/978-3-319-47952-1_13 |
| Alternate Webpage(s) | https://page-one.springer.com/pdf/preview/10.1007/978-3-319-47952-1_13 |
| Alternate Webpage(s) | https://doi.org/10.1007/978-3-319-47952-1_13 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
