Transcription of Classification of Trash for Recyclability Status
{{id}} {{{paragraph}}}
Example: tourism industry
Classification of Trash for Recyclability Status
Classification of Trash for Recyclability StatusMindy YangStanford ThungStanford A computer vision approach to classifyinggarbage into recycling categories could be an efficientway to process waste. The objective of this project isto take images of a single piece of recycling or garbageand classify it into six classes consisting of glass, paper,metal, plastic, cardboard, and Trash . We also create adataset that contains around 400-500 images for eachclass, which was hand collected. We plan to release thisdataset for the public. The models used are support vectormachines (SVM) with scale-invariant feature transform(SIFT) features and a convolutional neural network (CNN).Our experiments showed that the SVM performed betterthan the CNN; however, the CNN was not trained to its fullcapability due to trouble finding optimal INTRODUCTIONR ecycling is necessary for a sustainable current recycling process requires recyclingfacilities to sort garbage by hand and use a seriesof large filters to separate out more defined also can be confused about how to de-termine the correct way to dispose of a large varietyof materials used
based on which class model classifies the test datum with greatest margin. The features used for the SVM were SIFT fea-tures. On a high level, the SIFT algorithm finds blob like features in an image and describes each in 128 numbers. Specifically, the SIFT algorithm passes a dif-ference of Gaussian filter that varies ˙ values as
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: