In this work, a novel system, which works on a multidimensional feature space and detects the prominent signal components on the spectrum with high recall and precision, is presented. The boundary hiper planes are determined by using Support Vector Machine (SVM) classifier in the multidimensional feature space. The solution to the class training set imbalance problem is investigated with multiple SVM classifiers system. By balancing the training sets by random selections, the detection performance is raised. The features that are used in the proposed system are evaluated by Forward Feature Selection algorithm with two different selection criteria. The implemented system is compared to three different thresholding based detection system and it is observed that it has better performance than thresholding based systems. It is shown with proper test sets that it can perform high performance prominent component detection highly independent of training data.