Improved Information for Endoscopy Diseases Using K-Mean and Super-Pixel Segmentation in Wireless Endoscopy Dataset

Abstract

Wireless Capsule Endoscopy (WCE) needs computerized method to reduce the review time for its large image detain this paper, we propose an improved Bag Of Feature (BOF) method to assist classification of polyps in WCE images. Instead of utilizing a single Scale-Invariant Feature Transform (SIFT) feature in the traditional BoF method, we extract different textural features from the neighborhoods of the key points and integrate them together as synthetic descriptors to carry out classification tasks. Specifically, we study influence of the number of visual words, the patch size and different classification methods in terms of classification performance. Comprehensive experimental results reveal that the best classification performance is obtained with the integrated feature strategy using the SIFT and the Complete Local Binary Pattern (CLBP) feature, the visual words with a length of 120, the patch size of 8*8, and the Support Vector Machine (SVM). The achieved classification accuracy reaches 93.2%, confirming that the proposed scheme is promising for classification of polyps in WCE images To locate and identify next stages of ulcer and tuberculosis using Gaussian kernel algorithm, canny edge detection and k-mean algorithm for clustering .This can be implemented using dot net and c-sharp languages.

Authors and Affiliations

Vinitha M. K, Vishalini. S, Sushmitha. L, Lalitha. S. D

Keywords

Related Articles

Modulus of Elasticity and Flexural Strength of Concrete with Industrial By-Products

The study is to make use of industrial waste and to reduce the cement usage in the concrete by using the industrial wastes Ground Granulated Blast Furnace Slag (GGBS), Metakaolin and copper slag. GGBS and Metakaolin is...

Survey of Cloud Security Techniques

Cloud storage is use to reduce the cost of storage in I.T fields and other benefits such as data accessibility through internet. Ensuring the security of cloud server is important so store sensitive data for example con...

Human Identification System Based On Iris Scan

Biometrics includes various technologies for uniquely identifying an individual person in accordance with an examination of particular attributes of either the person’s interior or exterior eye. The technologies have ma...

Sign Language Recognition for Deaf Sign User

Sign language recognition is one of the most growing fields of research today and it is the most natural way of communication for the people with hearing problems. A hand gesture recognition system can provide an opport...

Closed Loop control of Hybrid Frequency Modulation of Integrated Boost Resonant Converter

The paper deals with a unique modulation method for extending the input range of pulse-width modulation (PWM)-integrated resonant converters, such as the isolated boost resonant converter, while maintaining high convers...

Download PDF file
  • EP ID EP21902
  • DOI -
  • Views 273
  • Downloads 3

How To Cite

Vinitha M. K, Vishalini. S, Sushmitha. L, Lalitha. S. D (2016). Improved Information for Endoscopy Diseases Using K-Mean and Super-Pixel Segmentation in Wireless Endoscopy Dataset. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 4(4), -. https://europub.co.uk/articles/-A-21902