Corrigendum to "Deep learning improves taphonomic resolution: high accuracy in differentiating tooth marks made by lions and jaguars". In a previous paper, we presented some convolutional neural network (CNN) models to classify images of tooth scores made by lions and jaguars through deep learning computer vision. In that work, we reached an accuracy of 82% of the testing set correctly classified. However, such an accuracy is biased, since the original sample was highly unbalanced. Therefor, now we present the results which correct the problems of the previously published models by producing more balanced classifications and also by achieving higher accuracy.

Images (.bpm) corresponding to lion and jaguar tooth scores, captured using Optika (30x) and resized and converted to grayscales to avoid bias. 

Artificial intelligence models: VGG19, Densenet 201, ResNet50, Inception V3 and InceptionResNetV2.

Programming language: Python. The architectures were trained on 70% of the original image set. The resulting models were subsequently tested against the 30% remaining sample, which was not used during the training. Training was performed through mini-batch kernels (size = 32). Testing was made using mini-batch kernels of size 20. Weight update was made using a backpropagation process for 100 epochs.