An image storage duplication detection method using recurrent learning for smart application services

Smart and intelligent application services rely on textual and visualization information for meeting user demands. Regardless of the textual data, visualization information requires large storage volumes due to its size and density. Visual information such as images and video occupies large storage space in a replicated manner. The retrieval complexity of such image inputs is considerably high, increasing the service latency. This paper introduces a novel dimension-correlated de-duplication method (DCDDM) for reducing the image replications of identical application services. The proposed method identifies the pixel dimensions of the input irrespective of its scale before storage. The pre-storage analysis correlates the dimension vectors of the stored and analyzed image using the identical feature and null properties. A trained learning paradigm is used for recurrent verification of the identical and null properties of stored and input images. The recurrent instance identifies un-matching vectors for preventing replications in storage and reducing overflow storage utilization. The proposed strategy reduces the storage rate by 16.49%, increases the detection ratio by 8.9%, reduces analysis time by 10.36%, and reduces variances by 9.04% for the various features evaluated. The findings show that the proposed method is reliable for usage in smart application services to reduce storage requirements and eliminate data duplication.