An Identification and Categorization of Plastic Material using Deep Learning Approach

Efforts to reduce the negative effects of plastic trash are hampered by a lack of information on the local distribution of plastic items. Scientists have created AI-based computerized management systems, including deep learning and image processing algorithms, to enhance the effectiveness of preprocessing. Artificial intelligence allows for the automatic recognition of plastic trash on conveyor belts at landfills. Yet, it might be difficult to sort out the many shades of glass and plastic within a collection. To address this, one approach is to use a convolutional neural network (CNN) with intensive training. Due to their prevalence in everyday life, plastics such as polyethylene terephthalate (PET), polypropylene (PP), high-density polyethylene (HDPE), and low-density polyethylene (LDPE) pose a significant environmental threat and necessitate the development of an automated process for sorting plastic garbage. PET plastic is difficult to biodegrade due to its robust and durable structure, which is composed of repeating units of ethylene glycol and terephthalic acid. PET detritus can accumulate in the environment due to its resistance to biodegradation, causing harm to flora, fauna, and ecosystems. The strategy that may be utilized on mobile devices has been developed to implement this procedure in filtration plants and people's homes to address the waste management problems that plague major cities.