For semiconductor applications, billions of objects are manufactured for a single device such as central processingunit (CPU), storage drive or graphical processing unit (GPU). In order to obtain functional devices, each individual element of the device has to follow precise specifications at nanoscale. For that, it is essential to obtainefficiently a pipeline to automate measurements on a set of similar images of semiconductor objects capturedwith electron microscopy. Generally, the pipeline consists to annotate an object in a image and then take themeasurements of the object. Manually images annotation is extremely time consuming. In this paper, we proposea semi-automatic method to annotate an object in a microscopy image based on deep learning with the precisionof the measurement. The approach is a deep learning contour-based method able first to detect the object andafter find the contour thanks to a constraint loss function. This constraint improves the quality of boundarydetail of the vertices of each object by matching the predicted vertices and the most likely ground truth. Theloss is computed during training for each object using a proximal way of our dataset. The experiments showedthat our approaches can achieve a state-of-the-art performance on several microscopy images dataset.