Abstract—Gastritis is a common case when someone suffers a pain or discomfort in the upper part of an abdomen. Conventionally, visual interpretation and pathology diagnosis is employed for identifying abnormalities in a stomach. In this paper, we present a computerized visualization technique which used the image features for classification of endoscopic gastritis image. It is aims to extract features based on texture and color. Gray level co-occurrence matrix (GLCM) features are extracted on wavelet transformed images. Two levels of discrete wavelet transform applied to the antrum image. The texture features then combined with the features of Color Moment for image classification. A support vector machine (SVM) is used as a classifier in categorizing images into its classes. The endoscopic images are classified into normal and abnormal antrum. The combinations of features lead to higher classification rate.

Index Terms—Feature extraction, gastritis, SVM, texture.

Zuriani Sobri is with the Universiti Sains Malaysia, Malaysia (e-mail:zs10_eee058@student.usm.my).
Harsa Amylia Mat Sakim was with Universiti Sains Malaysia. She is now with the School of Electrical & Electronic Engineering (e-mail:amylia@eng.usm.my).

Cite: Zuriani Sobri and Harsa Amylia Mat Sakim, "Texture Color Fusion Based Features Extraction for Endoscopic Gastritis Images Classification," International Journal of Computer and Electrical Engineering vol. 4, no. 5, pp. 674-678, 2012.