Abstract: Certain cooking items still fall under the same classifications. The problem is that the general public has limited access to updated records. The objective of this study is to ascertain the difficulty of automatically identifying a meal in a photograph for cooking and then automatically generating the appropriate recipe. Due to significant overlaps in food dishes and the possibility that meals from various categories may simply resemble one another visually, the chosen job is more challenging than previous supervised classification difficulties (also known as high intra-class similarity). Convolutional Neural Networks (or CNNs for short) are used to distinguish objects or food courts while concurrently looking for adjacent neighbours (Next-Neighbour Classification).
|
DOI:
10.17148/IJARCCE.2022.11752
