3 results about "Food recognition" patented technology

The application discloses an image recognition method, device and system. The method comprises the following steps: collecting a food image of food in a refrigerator through a camera installed in the refrigerator, wherein the food image comprises a food label; sending the food image to a cloud server; receiving a first recognition result returned by the cloud server, wherein the first recognition result comprises a result obtained by recognizing the food label in the food image; and displaying a food recognition result based on the first recognition result. The application solves the technical problems of complicated operation and poor user experience in food information input in the related art.

A method for treating food in an appliance (14) by at least one treatment device of the appliance (14) comprises the steps of a. providing a food recognition system with at least one camera image of a food item to be treated by the appliance (14)(S1), b. picture data about the food item by extracting a number of at least one characteristic features of the food item from the at least one camera image (S2), c. assigning a food identification to the food item based on at least one of the number of characteristic features (S4, S6), d. executing a food treatment process or program allocated to the assigned food identification (S8). According to the invention, the camera image is provided during step a. (S1) by an external camera device (12, 14), wherein the camera image provision is executed—by data retrieval by the food recognition system, and / or—by data transfer by the mobile camera device (12, 20), and / or—on the operator's initiation. Further disclosed is a food treatment system comprising an appliance (14) for treating food and an external camera device (12, 20) as well as a software application.

This invention discloses a method for food image segmentation and removal based on instance segmentation and spatial prior clustering, comprising three steps: Step 1, inferring from the photo using the YOLO instance segmentation model, extracting the segmentation mask, and cropping it into a black background image; Step 2, extracting the foreground from the image using the GrabCut algorithm, converting it to a transparent background, and generating an RGBA format image; Step 3, performing spatial partitioning on the transparent background image based on Euclidean distance transformation, using the outer perimeter as the plate prior and the center as the food prior, performing K-means clustering in the Lab color space, automatically identifying the plate and food clusters based on the spatial enrichment ratio of each cluster at the perimeter and center, and removing plate pixels based on external reachability connectivity verification, outputting a transparent background image containing only the food. This invention eliminates the need for manual region labeling or setting color thresholds, can adaptively handle plates of different colors, shapes, and sizes, is suitable for diverse dining scenarios, and supports tasks such as food recognition and nutritional estimation.