Texture based Identification and Classification of Bulk Sugary Food Objects

This paper presents a methodology for identification and classification of bulk sugary food objects. Comprising of south Indian typical sweets like Applecake, Bundeladu, Burfi, Doodhpeda, Jamun, Jilebi, Kalakand Ladakiladu, Mysorepak and Suraliholige. When these sweets arranged for display at the shops exhibit different patterns and hence texture is the basis used for recognition. The texture features are extracted using gray level co-occurrence matrix method. The multilayer feed forward neural network is developed to classify bulk sugary food objects. An analysis of the efficiency of methodology is found 90%. The work finds application in automatic monitoring /serving food in restaurants, hotels and malls by service robots.