Content Based Image Retrieval (Cbir) For Storing Of Products

Ninety Nine Publication 2021-04-24

With rise in complexity of materials and lack of necessary skills among the mass population, it is necessary to find a system that can help the employees to identify the materials without the help of additional labour, training and manuals. Hence, a system has been created to identify the material and give similar materials when the model is provided with just an image of the material in question. This being an unlinked database helps in maintaining privacy of the company. Convolutional neural networks are used for object detection and then captioning is done by Recurrent neural network which also compares the generated caption with the provided database and return the best match. LSTM and NLP aid the process of caption generation and search. The dataset used is MSCOCO 2014. The evaluation metrics is BLEU which returned a score of 70.3%. The whole idea is easy to combine with concepts like KANBAN and facilitate the layout design of the company to a great flexibility. By reducing the time spent on training and sorting the efficiency of the firm is increased. The system created for identifying the material can be interlinked with centralised inventory management system to help track the material in the production process. The layout of the store was not optimised which resulted in delay in the production process. This can be rectified using a software like ARENA to design the store layout. With a system in place for material deduction the steps followed in stores can be reduced.

info:eu-repo/semantics/article; info:eu-repo/semantics/publishedVersion

Open access content. Open access content

application/pdf
English

INNNP oai:ojs2.turcomat.org:article/505
1432767758

NINETY NINE PUBN
From OAIster®, provided by the OCLC Cooperative.

edsoai.on1432767758