The proposed methodology for image processing offers a robust and structured approach to segmenting and identifying objects within images of rheumatic heart disease. This comprehensive method starts with essential preprocessing steps, including converting images to grayscale and applying median filtering to reduce noise, thereby enhancing the visualization and smoothness of the affected areas. Edge detection is then performed using the canny algorithm, which is crucial for highlighting edges and boundaries essential for precise object delineation. Following this, Otsu’s method is applied for thresholding operations, effectively distinguishing foreground objects from the background. This step is vital for isolating the areas of interest within the image. To further refine the segmented regions, morphological operations such as erosion, dilation, opening and closing are employed. These operations help eliminate noise and unwanted artifacts, resulting in cleaner and more accurate segmentation. Connected component analysis is then utilized to label and differentiate connected regions or objects within the binary image. Finally, instance segmentation iterates through each connected component, extracting the corresponding regions to create segmented images for each object instance, with each being assigned a unique label. This detailed and systematic approach ensures accurate object segmentation, making it particularly useful for analyzing symptoms of rheumatic heart disease. The impact of this methodology lies in its ability to provide precise and reliable segmentation of medical images, which is critical for accurate diagnosis and treatment planning. By facilitating detailed image analysis and computer vision applications, this approach enhances the ability of healthcare professionals to identify and assess the severity of rheumatic heart disease, ultimately contributing to better patient outcomes.