Recent progress based on microscopic imaging has given a significant contribution in the diagnosis of malaria infection based on blood images. Due to the requirement of prompt and accurate diagnosis of malaria, the research proposed an adaptive hybrid analysis for blood cell image segmentation and discriminant analysis for image classification. In blood cell segmentation, three designates common approaches, that are Fuzzy C-Means, KMeans and Means-Shift are adapted. Blood cell images that are infected with malaria parasites at various stages were tested. The most suitable method will be selected based on the lowest number of regions. The selected approach will be enhanced by applying Median-cut algorithm to further expand the segmentation process. The proposed adaptive hybrid method has shown a significant improvement in the number of regions. In classifying of segmented blood cell images, the images have been through the features extraction process. Eight variables have been produced from the colours and textures from the segmented blood cell images. The eight variables are Hue, Saturation, Value, Angular Second Moment, Contrast, Correlation, Inverse Different Moment, and Entropy. The discriminant result shows high percentages (90% and above) of correct classification for type 1, 2, 3, and 4. These indicated the successfulness of extracting the malaria blood cell images using adaptive segmentation algorithm.
Volume 11 | 08-Special Issue
Pages: 63-76