Assessing the Impact of Image Preprocessing on ConvNeXt Performance for Waste Classification

Abstract

Waste has become an increasingly urgent environmental issue in everyday life. The waste is constantly increasing due to population growth, urbanization, and consumption. The increasing amount of waste needs more intelligent systems to help with the management of waste, especially with the sorting of waste. Unfortunately, the absence of the public's awareness of the importance of waste management has led to the ineffective collection of waste. Thus, there is a need of classifying the waste into technological systems based on various waste types. This research has computing waste types using ConvNetX. The research methodology is based on the collection and preprocessing of data that includes different image enhancement techniques such as CLAHE and bilateral filtering. This study employed the ‘Garbage Classification Dataset’ found on Kaggle. The dataset is split into 80% of it as training data, 10% of it as testing data, and the last 10% of it as validation data. The ConvNeXt model was trained using one of the training sets after the data was split and was subsequently measured using the validation and test sets for the training of the model. This research analyzed the effects of image preprocessing by using a baseline, which was no preprocessing (Scenario 1), and then using preprocessing (Scenario 2). The results from the experiments showed Scenario 2 had a higher accuracy of 94% compared to the baseline of 90%. The use of CLAHE and bilateral filtering positively impacted the F1 score by increasing it to glass (96%) and plastic (92%) and having a full recall (100%) for metal. Scenario 2 resulted in a total training time of 20.86 minutes, and Scenario 1 was 11.83 minutes, which means that Scenario 2 had a lower computational efficiency. Nevertheless, the additional time was well spent for the considerable consistency improvement in the classification of all categories. This makes it evident that substantial image preprocessing is necessary for the model to be able to generalize and classify images with complex visual details.