Method of deep neural network based on discriminable region for dish image classification

Abstract

The invention discloses a method of deep neural network based on a discriminable region for dish image classification. The method relates to the field of image processing, integrates a significant spectrum pooling operation, and fuses low-level features and high-level features in a network. The method adopts a convolution kernel filling operation, effectively preserves important information on characteristic spectra, and is matched with data dimensions of a full connection layer, so that the full connection layer can utilize a VGG-16 pre-training model at a training state, thereby improving the training efficiency and network convergence speed. Each image to be classified is subjected to normalization processing based on the model which is learned in a constructed database, the image is tested by using a trained convolutional neural network, the classification precision is measured by using Softmax loss, a classification result of the image is obtained, real categories and predicted categories of targets in all test images are compared, and a classification accuracy rate is obtained through calculation. The method is used for testing on a self-established data set CFOOD90, and theeffectiveness and the real-time performance of the method are verified.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a novel application method of a convolutional neural network for dish image classification. Background technique [0002] In recent years, healthy eating has become a social focus topic along with the fitness boom. Accurately classifying food images is an important part of intelligent healthy eating management. Although nutrition experts can give some professional dietary analysis and consultation suggestions for bodybuilders and patients to guide them in managing calories and nutrient intake, the high cost and time cost limit its popularization and development to the public. Therefore, there is an urgent need for a method that can directly automatically identify food photos taken by mobile devices such as smart phones and tablet computers, and then classify food and manage personal diets. [0003] Algorithms based on deep convolutional neural networks have made breakthrough achi...

AI Technical Summary

Problems solved by technology

[0004] Chinese dishes are rich in categories, with ever-changing ingredients, high similarity between categories, and large differences within categories. At the same time, unlike target detection, it is very difficult to classify dishes due to the lack of specific spatial features and structural information that can be used as an aid.

Images