Invention Grant
US09412024B2 Visual descriptors based video quality assessment using outlier model
有权
基于视觉描述符的视频质量评估使用离群模型
- Patent Title: Visual descriptors based video quality assessment using outlier model
- Patent Title (中): 基于视觉描述符的视频质量评估使用离群模型
-
Application No.: US14027123Application Date: 2013-09-13
-
Publication No.: US09412024B2Publication Date: 2016-08-09
- Inventor: Santanu Chaudhury , Brejesh Lall , Rohit Mungre , Yogesh Singh , Shekhar Madnani
- Applicant: Interra Systems, Inc.
- Applicant Address: US CA Cupertino
- Assignee: Interra Systems, Inc.
- Current Assignee: Interra Systems, Inc.
- Current Assignee Address: US CA Cupertino
- Agency: Next IP Law Group
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/00 ; G06K9/03 ; G06K9/46
Abstract:
System and method for identifying erroneous videos and assessing video quality is provided. Feature vectors are generated corresponding to a plurality of frames associated with the one or more videos. The feature vectors are subsequently subjected to anomaly detection to obtain first and second normalized path lengths and normalized anomaly measures. The first and second normalized path lengths and normalized anomaly measures are provided to a regression model to identify the erroneous video.
Public/Granted literature
- US20150078654A1 Visual Descriptors Based Video Quality Assessment Using Outlier Model Public/Granted day:2015-03-19
Information query
