The work in this thesis has been dedicated to the subject of reverse engineering techniques using soft computing techniques. It particularly emphasizes on the problems of curve fitting for finding the optimal solutions. A detailed survey has been provided, in the literature review, on the subject reported by various authors (see [1-105] in Chapter 1). Although people have worked to find the direct methods for problem solving, yet an extensive study is needed for indirect solutions using heuristic like approaches. In this thesis, new reverse engineering techniques are proposed which utilize three soft computing approaches including Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Imperialist Competitive Algorithm (ICA). Spline functions have also been used to find the optimal solutions for curve fitting problems. These soft computing techniques are used to find the optimal values of shape parameters in the description of the proposed spline functions. The underlying methods of reverse engineering consist of several phases including data extraction of image outlines, detection of corner points, and fitting curve using spline functions to the detected corner points. A total of nine algorithms have been designed and implemented. These algorithms are formulated to explain the process of reverse engineering. The proposed schemes help vectorizing the generic shapes and are demonstrated with various practical examples. The examples presented illustrate very well the outcomes and the robustness of the proposed algorithms. The comparisons of the proposed schemes are made with each other as well as with some existing schemes in the literature.