Indoor localization systems are used to locate mobile devices inside buildings where traditional solutions, such as the Global Navigation Satellite Systems (GNSS), do not work well due to the lack of direct visibility to the satellites. Fingerprinting is one of the most known solutions for indoor localization. It is based on the Received Signal Strength (RSS) of packets transmitted among mobile devices and anchor nodes. However, RSS values are known to be unstable and noisy due to obstacles and the dynamicity of the scenarios, causing inaccuracies in the position estimations. This instability and noise often cause the system to indicate a location that it is not quite sure is correct, although it is the most likely based on the calculations. This property of RSS can cause algorithms to return a localization with a low confidence level. If we could choose more reliable results, we would have an overall result with better quality. Thus, in our solution, we created a checking phase of the confidence level of the localization result. For this, we use the prediction probability provided by KNN and the novelty detection to discard classifications that are not very reliable and often wrong. In this work, we propose LocFiND (Localization using Fingerprinting and Novelty Detection), a fingerprint-based solution that uses prediction probability and novelty detection to evaluate the confidence of the estimated positions and mitigate inaccuracies caused by RSS in the localization phase. We implemented our solution in a real-world, large-scale school area using Bluetooth-based devices. Our performance evaluation shows considerable improvement in the localization accuracy and stability while discarding only a few, low confidence estimations.