The automation of processes that handle deformable materials, and in particular Deformable Linear Objects (DLOs), such as cables, ropes, and sutures; is a challenging task. Due to their properties, it is very difficult to predict the shape of these objects, making indispensable the use of perception systems for their manipulation. However, the detection of a DLO is a non-trivial task, and it can be even more complicated when additional considerations are made, such as detecting multiple DLOs, with small distances between them or even adjacent to each other, and with occlusions and entanglements between them. In this paper, a novel machine vision approach for estimating the shape of DLOs is proposed to address all these challenges. This approach processes the different DLOs in the image sequentially, repeating the following procedure for each of them. First, the DLO is segmented by examining the colors and edges in the image. Next, the remaining pixels are analyzed using evaluation windows to identify a series of points along the DLO’s skeleton. These points are then employed to model the DLO’s shape using a polynomial function. Finally, the output is evaluated by an unsupervised self-critique module, which validates the results, or fine-tunes the system’s parameters and repeats the process. The performance of the system was tested with several wiring harnesses, detecting all their cables in homogeneous and complex backgrounds, with adjacent cables, and with occlusions. The results show an outstanding performance, with a successful shape estimation rate of more than 90% for some of the system configurations.