Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 7

Publications

7 Image Processing Using Color and Object Information for Wireless Capsule Endoscopy

Authors: Gilwon Yoon, Yong-Gyu Lee, Jin-Hee Park

Abstract:

Wireless capsule endoscopy provides real-time images in the digestive tract. Capsule images are usually low resolution and are diverse images due to travel through various regions of human body. Color information has been a primary reference in predicting abnormalities such as bleeding. Often color is not sufficient for this purpose. In this study, we took morphological shapes into account as additional, but important criterion. First, we processed gastric images in order to indentify various objects in the image. Then, we analyzed color information in the object. In this way, we could remove unnecessary information and increase the accuracy. Compared to our previous investigations, we could handle images of various degrees of brightness and improve our diagnostic algorithm.

Keywords: Image Processing, object identification, capsule endoscopy, HSV model, Color Separation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1583
6 Algorithm for Bleeding Determination Based On Object Recognition and Local Color Features in Capsule Endoscopy

Authors: Gilwon Yoon, Yong-Gyu Lee, Jin Hee Park, Youngdae Seo

Abstract:

Automatic determination of blood in less bright or noisy capsule endoscopic images is difficult due to low S/N ratio. Especially it may not be accurate to analyze these images due to the influence of external disturbance. Therefore, we proposed detection methods that are not dependent only on color bands. In locating bleeding regions, the identification of object outlines in the frame and features of their local colors were taken into consideration. The results showed that the capability of detecting bleeding was much improved.

Keywords: Image Processing, Object recognition, Endoscopy, Bleeding, RGB

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1493
5 Biosignal Measurement using Personal Area Network based on Human Body Communication

Authors: Gilwon Yoon, Yong-Gyu Lee, Jin-Hee Park

Abstract:

In this study, we introduced a communication system where human body was used as medium through which data were transferred. Multiple biosignal sensing units were attached to a subject and wireless personal area network was formed. Data of the sensing units were shared among them. We used wideband pulse communication that was simple, low-power consuming and high data rated. Each unit functioned as independent communication device or node. A method of channel search and communication among the modes was developed. A protocol of carrier sense multiple access/collision detect was implemented in order to avoid data collision or interferences. Biosignal sensing units should be located at different locations due to the nature of biosignal origin. Our research provided a flexibility of collecting data without using electrical wires. More non-constrained measurement was accomplished which was more suitable for u-Health monitoring.

Keywords: Biosignal, human body communication, wideband pulse communication, personal area network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1805
4 Implementation of Security Algorithms for u-Health Monitoring System

Authors: Gilwon Yoon, Yong-Gyu Lee, Jiho Park

Abstract:

Data security in u-Health system can be an important issue because wireless network is vulnerable to hacking. However, it is not easy to implement a proper security algorithm in an embedded u-health monitoring because of hardware constraints such as low performance, power consumption and limited memory size and etc. To secure data that contain personal and biosignal information, we implemented several security algorithms such as Blowfish, data encryption standard (DES), advanced encryption standard (AES) and Rivest Cipher 4 (RC4) for our u-Health monitoring system and the results were successful. Under the same experimental conditions, we compared these algorithms. RC4 had the fastest execution time. Memory usage was the most efficient for DES. However, considering performance and safety capability, however, we concluded that AES was the most appropriate algorithm for a personal u-Health monitoring system.

Keywords: Data Encryption, Biosignal, Security Measures, u-health

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1716
3 Improvement of Blood Detection Accuracy using Image Processing Techniques suitable for Capsule Endoscopy

Authors: Gilwon Yoon, Yong-Gyu Lee

Abstract:

Bleeding in the digestive duct is an important diagnostic parameter for patients. Blood in the endoscopic image can be determined by investigating the color tone of blood due to the degree of oxygenation, under- or over- illumination, food debris and secretions, etc. However, we found that how to pre-process raw images obtained from the capsule detectors was very important. We applied various image process methods suitable for the capsule endoscopic image in order to remove noises and unbalanced sensitivities for the image pixels. The results showed that much improvement was achieved by additional pre-processing techniques on the algorithm of determining bleeding areas.

Keywords: Image Processing, capsule endoscopy, blood detection

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1364
2 Real-Time Image Analysis of Capsule Endoscopy for Bleeding Discrimination in Embedded System Platform

Authors: Gilwon Yoon, Yong-Gyu Lee

Abstract:

Image processing for capsule endoscopy requires large memory and it takes hours for diagnosis since operation time is normally more than 8 hours. A real-time analysis algorithm of capsule images can be clinically very useful. It can differentiate abnormal tissue from health structure and provide with correlation information among the images. Bleeding is our interest in this regard and we propose a method of detecting frames with potential bleeding in real-time. Our detection algorithm is based on statistical analysis and the shapes of bleeding spots. We tested our algorithm with 30 cases of capsule endoscopy in the digestive track. Results were excellent where a sensitivity of 99% and a specificity of 97% were achieved in detecting the image frames with bleeding spots.

Keywords: Image Processing, Bleeding, capsule endoscopy, real time analysis

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1440
1 Bleeding Detection Algorithm for Capsule Endoscopy

Authors: Gilwon Yoon, Yong-Gyu Lee

Abstract:

Automatic detection of bleeding is of practical importance since capsule endoscopy produces an extremely large number of images. Algorithm development of bleeding detection in the digestive tract is difficult due to different contrasts among the images, food dregs, secretion and others. In this study, were assigned weighting factors derived from the independent features of the contrast and brightness between bleeding and normality. Spectral analysis based on weighting factors was fast and accurate. Results were a sensitivity of 87% and a specificity of 90% when the accuracy was determined for each pixel out of 42 endoscope images.

Keywords: Image Analysis, Bleeding, capsule endoscopy, weighted spectrum

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1623