Incremental density-based clustering algorithms are designed to handle large datasets and streaming data. However, the automatic identification of critical input parameters and the merging threshold for dynamically merging clusters in incremental density-based algorithms presents a significant challenge. This paper addresses the above challenge by introducing a novel framework, termed Multi-Objective Incremental Density-Based Clustering using deep learning (MIDBC-DL). It leverages Pareto front generation by utilizing pseudo labels that captures non-linear relationships between objective functions. Furthermore, a novel evaluation metric, the Score Index (SI), is introduced to achieve a robust and balanced consideration of both compactness and separation between clusters. To validate the effectiveness of the proposed approach, experiments are conducted using five bench mark datasets — Iris, Glass, Wine, Pendigits and Shuttle. Experimental results demonstrate that MIDBC-DL achieves superior performance compared to the state-of-the-art methods. The source code is available at https://github.com/BinuJoseA/MIDBC-DL.