Download Full Text (1.6 MB)


Visual pollution is an impairment on an individual's ability to enjoy their surroundings. It usually takes the form of a messy and chaotic environment that can cause overstimulation of the visual senses. This includes trash, advertisements, construction, electric cables, and similar objects. Convolutional Neural Networks (CNNs) are a form of artificial intelligence that use supervised learning to process and classify images. In this research, a CNN processed images of city streets and classified them as polluted or not polluted based on the visual characteristics that it learned from during its training period. The CNN achieved a training accuracy of 98% and a validation accuracy of 80%.

Publication Date



Arts and Humanities | Business | Education | Engineering | Higher Education | Life Sciences | Medicine and Health Sciences | Physical Sciences and Mathematics | Social and Behavioral Sciences

Visual Pollution Classification using Convolutional Neural Networks



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.