Food nutrition constituent detecting method and system based on binocular camera
A technology based on binocular cameras and nutritional components, applied in the field of detection of food nutritional components based on binocular cameras, can solve problems such as system failure, difficulty in accurately calculating food nutritional components, and difficulty in dealing with errors
Inactive Publication Date: 2018-11-16
明伟杰 +8
View PDF0 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method ignores the important indicator of food size, and each user has different shooting habits, so it is difficult to accurately calculate the nutritional content of food;
[0005] Put a calibration card next to the food when shooting food, and calculate the volume of the food by comparing the length of the calibration card in the picture with the real length of the calibration card, and then calculate the nutritional content of the food; this method can be more accurate The calculation of the nutritional content of food, but its drawback is that once the user forgets to bring the calibration card, the system is completely useless, and the method is difficult to deal with the error caused by the perspective in the photo
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0063] This embodiment discloses a method for detecting food nutritional components based on a binocular camera, the steps are as follows:
[0064] Step S1, first obtain multiple pictures including food, label each picture with the food name and food location, form the first training set from the above-mentioned pictures and the food names and food locations marked in them, and then pass the first training Set the training deep learning model to obtain the first artificial intelligence model; specifically: use each picture in the first training set as the feature of the deep learning model, corresponding to the food name in each picture and the food position in each picture as the label pair depth of the deep learning model The learning model is trained to obtain the first artificial intelligence model; wherein the food position includes the coordinates of each pixel point of the food part in the picture, and the coordinates of each pixel point of the food part form a position ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a food nutrition constituent detecting method and system based on a binocular camera. A first training set is constructed and a first artificial intelligence model capable of recognizing a food name and a food position in a picture is trained; a binocular camera shoots pictures, the first artificial intelligence model identifies the food name and the food position in each picture, the food names and the food positions in each two pictures shot each time by the binocular camera form a training sample and a second training set is formed, and a second artificial intelligence model capable of identifying the quality of food in a test sample is trained; the binocular camera obtains the test sample, the test sample is inputted into the first artificial intelligence modelto obtain a food name and a food position, and the food name and the food position are inputted into the second artificial intelligence model to obtain the quality of the food; and the quality of thefood is multiplied by the unit quality nutrition constituent of the food to obtain the nutrients of the food. Therefore, the nutrition constituents of the food can be detected accurately and quickly.
Description
technical field [0001] The invention relates to a method for detecting nutritional components of food, in particular to a method and system for detecting nutritional components of food based on a binocular camera. Background technique [0002] In daily life, people pay more and more attention to the nutritional content of food, especially for special groups such as dieters, athletes, and patients. The nutritional content of food is difficult to distinguish by human eyes, so this project proposes a method to calculate the nutritional content of food through dual cameras. [0003] In the existing technology for calculating the nutritional content of food through images, there are two common and relatively mature ideas: [0004] Compare the captured food pictures with the pictures predefined by the system, and estimate the nutritional content of the food by calculating the similarity of the pictures. This method ignores the important indicator of food size, and each user has ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityApplications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G16H20/60
CPCG06N3/08G16H20/60G06V20/10G06V20/68G06N3/045G06F18/214
Inventor刘哲瑞明伟杰杨悉琪何易黄心怡陈杰彬彭俊豪沈家伊眭铭刚吴洪樟张春业李京真方博翰孙艺萌蒋邦胜黄梦琪任威达王小玲宫松何宗霖吴佳琳冯亚轩宋堅律音陈洁莹薛冬梅林汝晴林晓丽
Owner明伟杰