One impeding factor for determining the correct number of solar filaments in H- αα solar images is its broken appearance, which, in turn, affects the accuracy of tracking it and extracting its attributes accurately. By integrating image processing (IP) and artificial intelligence techniques, these fragmented threads have been more effectively merged. In this paper, different IP methods are utilized to extract the filament attributes, where these attributes act as inputs to a neural network to obtain a 92% true-positive rate. The method introduced in this work is fully automated and not threshold-based—unlike in previous works.