This paper presents a neural network model based on a Convolutional Neural Network to classify food products often seen in convenience stores. The data gathered was based on crowdsourced information since there is no locally available dataset to use. We used the Xception network pre-trained on Imagenet dataset fused with a fully connected layer for our architecture. The model yielded an 86% classification accuracy for the test data which is beyond the threshold for a multiclass target of 10 items. Comparisons for different items show that the model performed best for nine out of ten items.