Hybrid Edge Detection and Singular Value Decomposition for Image Background Removal

Image background removal is a crucial technique for enhancing the visual impact of images or altering their composition, finding applications in various fields such as photography and computer vision. This process can be executed manually through conventional image editing software or automated using advanced image processing algorithms. In this context, we present a novel algorithm that combines edge detection and singular value decomposition (SVD) to precisely segment the primary connected object within RGB images. The proposed methodology initiates with pre-processing and edge detection, leveraging an innovative filter amalgamating Markov and Laplace filters. Subsequently, the image undergoes block division, and features are extracted through the application of SVD transformation. To ensure optimal threshold determination, a unique approach is employed, resulting in the generation of a binary image. In the final stage, morphological operations are implemented to rectify fragmented object sections, eliminate small artifacts, and fill in gaps. The binary image, when multiplied by the original image, yields a meticulously segmented color object. This paper’s distinctive contributions include the introduction of a novel threshold determination approach and the utilization of SVD for image background removal. Comparative assessments against alternative strategies consistently affirm the efficacy of our proposed technique, with accuracy measurements reaching up to 99%. The experimental results underscore the robustness and superiority of our approach, establishing it as a valuable addition to the repertoire of image background removal methodologies.