The entire small intestine can be examined by this technique without pain, sedation, or air insufflations, which are inevitable in traditional endoscopy examination . Wireless capsule endoscopy (WCE) can directly take digital images in the gastrointestinal tract of a patient. It has opened a new chapter in small intestine examination. Currently, there is no standard for capsule endoscopy image interpretation and classification. Most state-of-the-art CAD methods often suffer from poor performance, high computational cost, or multiple empirical thresholds. In this paper, a new method for rapid bleeding detection in the WCE video is proposed. We group pixels through super pixel segmentation to reduce the computational complexity while maintaining high diagnostic accuracy.
Feature of each super pixel is extracted using the red ratio in RGB space and fed into support vector machine for classification. Also, the influence of edge pixels has been removed in this paper. Comparative experiments show that our algorithm is superior to the existing methods in terms of sensitivity, specificity, and accuracy.
Capsule endoscopy (CE) has been widely used to diagnose diseases in human digestive tract. This new system exploits colour texture feature, an important clue used by physicians, to analyze status of gastrointestinal tract. Combined with uniform local binary pattern, a current texture representation model, it can be applied to discriminate normal regions and bleeding regions in CE images.
Classification of bleeding regions using multilayer perception neural network is then deployed to verify performance of the proposed colour texture features.

Experimental results on our bleeding image data show that the proposed scheme is promising in detecting bleeding regions.

Open CV tool is used instead of dot net for image processing.
System is implemented on dot net frame work.

It has been reported that this new technology shows great value in evaluating bleeding, Crohn’s disease, and other diseases existing in the digestive tract.

To demonstrate the feasibility of the Existing scheme for practical usage, we calculate the average number of false positives per image.

We can see that the Existing scheme shows an encouraging number of false positives per image, and this implies that our novel
CAD system may be useful to assist bleeding detection for clinical use.
 The existing methods can be roughly classified into image based methods, pixel based methods, and patch based methods.


Takes 8 hours for the procedure to be completed

Few complications
 Stuck in a room for 8 hours
 Cannot eat or drink

Uncomfortable excreting the pill.


In this paper, we propose a new method that can detect bleeding regions from WCE video more effectively and efficiently.

We first detect the edge pixels, and then use the morphological dilation to locate and remove the edge regions. Instead of processing each pixel or dividing the image uniformly.

We group pixels adaptively based on color and location through super pixel segmentation.

High sensitivity means high capability of detecting bleeding frames. High specificity means high capability of avoiding false detection.

Accuracy is used to evaluate the overall performance of the proposed method.

Proposed to detect bleeding pixels by using probabilistic neural network (PNN).

Since the intensities bleeding and non-bleeding pixels often have overlapping in each color channel, Thresholding methods are reliable.

Proposed a patch based method based on chrominance moments combined with local binary pattern (LBP) texture features.


 No anesthia

No hospitalization necessary

Very few complications
 Painless
 No cutting
 SYSTEM : Pentium IV 2.4 GHz

HARD DISK : 40 GB

RAM : 256 MB
 Operating system : Windows 7.
 IDE : Microsoft Visual Studio 2010.

Coding Language : C#.NET.