Abstract
Machine learning is an integral technology many people utilize in all areas of human life. It is pervasive in modern living worldwide, and has multiple usages. One application is image classification, embraced across many spheres of influence such as business, finance, medicine, etc. to enhance produces, causes, efficiency, etc. This need for more accurate, detail-oriented classification increases the need for modifications, adaptations, and innovations to Deep Learning Algorithms. This article used Convolutional Neural Networks (CNN) to classify scenes in the CIFAR-10 database, and detect emotions in the KDEF database. The proposed method converted the data to the wavelet domain to attain greater accuracy and comparable efficiency to the spatial domain processing. By dividing image data into subbands, important feature learning occurred over differing low to high frequencies. The combination of the learned low and high frequency features, and processing the fused feature mapping resulted in an advance in the detection accuracy. Comparing the proposed methods to spatial domain CNN and Stacked Denoising Autoencoder (SDA), experimental findings revealed a substantial increase in accuracy.
Highlights
Machine learning has become an integral part of everyday life for many people around the world
In an effort to increase the image classification accuracy, we propose an algorithm that converts the data to the wavelet domain
The experiments and results solidify our initial claims that a wavelet-based ensemble network would perform at a greater accuracy and comparable to greater computational cost than traditional deep neural network methods
Summary
Machine learning has become an integral part of everyday life for many people around the world. The pervasiveness of this technology in modern living allows the solving of old problems in new, more efficient ways. Applying the DWT to digital images, especially at multiple resolutions, produces a wide range of usages for preprocessing and improvement. This viable mathematical tool has an efficient, highly intuitive framework for characterization and storage of multiresolution images. It provides powerful insight and into an image’s temporal and frequency characteristics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
