发明名称 VIDEO SURVEILLANCE SYSTEM AND METHOD FOR FRAUD DETECTION
摘要 Disclosed is a method and video surveillance system for detecting fraud. The system may receive images. The system may convert the images into binary images. Subsequently, the system may identify a reference frame amongst the binary images. The system may trigger face detection upon detecting motion within the binary images. The system may detect the motion based on a relative white pixel count of the binary image with respect to a reference image. The system may reduce a Region of Interest (RoI) window within the binary images based on a highest density of white pixel count. The system may determine whether a face is detected within the reduced RoI window. The system may determine whether mouth is detected within a lower half of the face when the face is detected. The system may detect the fraud when the face is not detected or the mouth is not detected.
申请公布号 US2016180149(A1) 申请公布日期 2016.06.23
申请号 US201514919800 申请日期 2015.10.22
申请人 Tata Consultancy Services Limited 发明人 Yesugade Snehal;Das Apurba;Dave Palak;Srivastava Srinkhala
分类号 G06K9/00;G06K9/46;G06T7/20 主分类号 G06K9/00
代理机构 代理人
主权项 1. A method for detecting fraud by a video surveillance system, the method comprising: receiving, by a processor in the video surveillance system, a plurality of images; converting, by the processor, the plurality of images, present at a predefined frame interval, into binary images; identifying, by the processor, a reference frame, from the binary images, having a relative white pixel count greater than a lower predefined threshold of the white pixel count; triggering, by the processor, face detection upon detecting motion within the binary images, wherein the motion is detected while the relative white pixel count either exceeds an upper predefined threshold or increases monotonically; reducing, by the processor, a Region of Interest (RoI) window within the binary images based on a highest density of white pixel count, wherein the highest density of white pixel count is determined by spatially sampling the binary images along columns; determining whether a face is detected, by the processor, within the reduced RoI window; determining whether mouth is detected within a lower half of the face, by the processor, when the face is detected within the reduced RoI window; and detecting the fraud, by the processor, when at least one of the face is not detected within the reduced RoI window and the mouth is not detected within the lower half of the detected face.
地址 Mumbai IN