Plant diseases pose a significant threat to agriculture worldwide, impacting both productivity and food security. Effective disease management relies on early detection and accurate diagnosis. Traditional methods, which depend on visual inspection, are often slow and subjective. However, recent advancements in computer vision and machine learning offer promising alternatives. This paper introduces the improved framework for segmentation, which integrates preprocessing and segmentation. Initial preprocessing employs median filtering for data refinement. Segmentation, utilizing the Adaptive Pixel Integration in Joint Segmentation (APIJS) approach, isolates disease-affected regions in plant images through a variant of DJS. This framework has the potential to enhance the effectiveness and accuracy of plant disease segmentation stages, hence aiding in promoting sustainable agriculture and global food security.