Invention Application
- Patent Title: JOINT-BASED ITEM RECOGNITION
- Patent Title (中): 基于联合的项目识别
-
Application No.: US14963026Application Date: 2015-12-08
-
Publication No.: US20160203525A1Publication Date: 2016-07-14
- Inventor: Kota Hara , Vignesh Jagadeesh , Robinson Piramuthu
- Applicant: eBay Inc.
- Main IPC: G06Q30/02
- IPC: G06Q30/02 ; G06K9/66 ; G06T3/40 ; G06K9/00 ; G06K9/62 ; G06T11/60

Abstract:
For an input image of a person, a set of object proposals are generated in the form of bounding boxes. A pose detector identifies coordinates in the image corresponding to locations on the person's body, such as the waist, head, hands, and feet of the person. A convolutional neural network receives the portions of the input image defined by the bounding boxes and generates a feature vector for each image portion. The feature vectors are input to one or more support vector machine classifiers, which generate an output representing a probability of a match with an item. The distance between the bounding box and a joint associated with the item is used to modify the probability. The modified probabilities for the support vector machine are then compared with a threshold and each other to identify the item.
Public/Granted literature
- US11120478B2 Joint-based item recognition Public/Granted day:2021-09-14
Information query