Hybrid Approach for Food Recognition Using Various Filters

  • swati jadon Assistant Professor GIET RTU kota


Food image recognition system has various applications now a day. In this paper we have used machine learning supervised approach and Support Vector Machine to classify different food images. SVM has being classified to detect and recognize food images with least modification. By applying various filters like texture filter, segmentation method, clustering and SVM approach we have achieved more accuracy then other machine learning approaches with manually extract features. Sustenance is an indivisible piece of people groups lives. we tend to apply an convolution neural network(CNN) to the undertakings of analyst work and perceiving sustenance pictures. Be clarification for the wide decent variety of styles of nourishment, picture acknowledgment of sustenance things is typically unpleasantly difficulties. Nevertheless, profound learning has been demonstrated starting late to be a genuinely extreme picture acknowledgment framework, and CNN could be a dynamic approach to manage profound learning. CNN showed on a very basic level higher precision than did old-fashioned help vector-machine-based courses with carefully assembled decisions. For sustenance picture disclosure, CNN likewise demonstrated fundamentally count higher precision than a standard technique. Generally higher precision than standard techniques.
Keywords: CNN, texture filter, k-mean clustering, segmentation


Download data is not yet available.
How to Cite
SHARMA, P., jadon, swati, & SHARMA, A. (2022). Hybrid Approach for Food Recognition Using Various Filters. International Journal of Advanced Computer Technology, 11(1), 1-5. Retrieved from https://ijact.org/index.php/ijact/article/view/98