Anemia Detection using Image Processing

Medical image processing provides state of the art techniques for the automatic diagnostic system to different diseases and is very common now days. These types of system provide cost effective health care facilities to patients. Anemia globally is prevalent most in developing countries and it is affecting 1.62 billion people, which comprises of 24.8% of the population. Like other developing countries, Pakistan has been facing problem of Anemia which is very common among women and children in Pakistan. In this paper, a non-invasive automatic detection of anemia is proposed by using image processing and pattern recognition techniques. A technique is developed to detect anemia by a digital photograph of a face image exposing conjunctiva as anemia can be identified by conjunctiva pallor. Eye region is detected by using famous object detection Viola and Jones algorithm and the method then enhances the contrast of image in preprocessing step. The conjunctiva segmentation is performed by using K-means clustering. Color based feature vector is then computed and by using these feature set, SVM classifier is applied to classify between anemic and non-anemic images. Two camps have been arranged locally to gather patients’ data containing the images and clinical HB values. The results of proposed system are correlated with the clinical values and the proposed system showed reliable results when compared with clinical findings. The proposed system showed good accuracy when compared with clinical results.