Efficient method to Recognition of Anemia Images based on Moment Invariants and Decision tree classifier


Anemia is one of the common types of blood diseases, it lead to lack of number of RBCs (Red Blood Cell) and amount hemoglobin level in the blood is lower than normal.In this paper a new algorithm is presented to recognize Anemia in digital images based on moment variant. The algorithm is accomplished using the following phases: preprocessing, segmentation, feature extraction and classification (using Decision Tree), the extracted features that are used for classification are Moment Invariant and Geometric Feature. The Best obtained classification rates was 84% is obtained when using Moment Invariants features and 74 % is obtained when using Geometric Feature. Results indicate that the proposed algorithm is very effective in detection distorted red blood cells and this helps the medical technician to decide the type of Anemia in Laboratory analyzes in the hospitals.