In this post, I am going to explain a end-to-end use case of deep learning image classification in order to automate the process of classifying defective and non-defective castings in foundry. Casting Process: Casting is one of the major manufacturing process in which molten metal is poured in to a cavity called mould and allowed to cool till it gets solidified into product. Casting defects: These are the defects in the cast product occurred during the casting process and they are undesirable.There are many types of defect in casting like blow hole, pin hole, burr, shrinkage defects, mould material defects, pouring metal defects, metallurgical defects etc. Casting defects are undesirable and cause loss to the manufacturer, therefore the quality department have to do visual inspection of the products and separate the defective one from the good castings. The visual inspection is labour intensive and time consuming, therefore Convolution Neural Networks (CNN) could be used to automate this process by image classification. The figure 1. shows the Casting Inspector app developed in this project.

In this article, we will discuss how Convolutional Neural Networks (CNN) classify objects from images (Image Classification) from a bird's eye view. First, let us cover a few basics. Let us start with the difference between an image and an object from a computer-vision context. What we see above is an image. We can see 3 objects inside – 1 cat and 2 dogs.

Classical machine learning and deep learning have fantastic applications. One of these applications is the multiclass classification where the last layer may have more than one node (or neuron) predictor. For instance, the most popular multiclass classifier in machine learning is the MNIST digits classifier whilst for deep learning, there is the must try version of MNIST which is the dogs and cats classifier. Now, which one is the best to predict other types of object, insects for example? Thus, I took seven classes of insects (actually, it was six because spiders are not insects but arachnids. The seven chosen classes are: beetles, cockroaches, dragonflies, flies, spiders, termites, and thrips.

I have to admit my initial thoughts of deep learning were pessimistic and in order to not succumb to impostor syndrome, I put off learning any new techniques in the growing sub field of machine learning, until recently. After attending & speaking at Data Day Texas and listening to Lukas Biewald's Keynote titled: Deep Learning in the Real World, I began to see through the complexities of Deep Learning and understand the real world applications. My favorite example from the keynote was Coca Cola deploying a deep learning model to easily capture under the cap promotional codes. I left the conference with some initial ideas about detecting deer in my backyard using a web cam and running a image classification algorithm as my first step into learning by doing. For this image classification project I leveraged a pre-trained model from the R interface to Keras, that had been previously trained on a similar task.