Image Classification with Classic and Deep Learning Techniques
This work addresses the problem of image classification for computer vision researchers, but it is incremental as it primarily compares existing and custom methods without introducing a novel paradigm.
The paper tackled image classification by implementing and comparing classic computer vision methods like Bag of Visual Words with SVMs and deep learning techniques including Multilayer Perceptron, InceptionV3, and a custom CNN called TinyNet, achieving accuracy results ranging from 0.6 to 0.96 across different models and configurations.
To classify images based on their content is one of the most studied topics in the field of computer vision. Nowadays, this problem can be addressed using modern techniques such as Convolutional Neural Networks (CNN), but over the years different classical methods have been developed. In this report, we implement an image classifier using both classic computer vision and deep learning techniques. Specifically, we study the performance of a Bag of Visual Words classifier using Support Vector Machines, a Multilayer Perceptron, an existing architecture named InceptionV3 and our own CNN, TinyNet, designed from scratch. We evaluate each of the cases in terms of accuracy and loss, and we obtain results that vary between 0.6 and 0.96 depending on the model and configuration used.