US 7,116,814 B2Granted

Image-based container defects detector

AssigneeChunghwa Telecom Co., Ltd.

InventorsBor-Shenn Jeng, Quen-Zong Wu, Yu-Pin Chen, Wei-Yuan Cheng

Life of this patent

Estimating the term…

Loading patent…

Abstract

The image-based container defects detector consists of a plurality of camera units, a sensor unit, a frame grabber, and an image recognizer unit. The sensor unit serves to detect the vehicles entering the inspection station, and transmit a signal to the frame grabber for capturing the vehicle image by triggering the CCD camera thereby obtaining the information about the container's defect position and size. By dexterously utilizing image processing technique, the HIS (hue, saturation and intensity) color is employed to distinguish a normal area from a defected area in the container. Then quad-tree and merge is used to segregate image roughly. As for the non-defected area becoming obscured due to noise is removed using a filter. Finally the defected area is displayed on the screen. The present invention is well-suited for after detection as well as for on-line immediate detection for defect containers.

Claims2

Dependent claims

An image-based container defects detector for finding a defect located in a defective portion of a container that also has a normal portion that is not defective, the container additionally having a container number in a container number area, said defect detector comprising:

container defect positioning program module means for capturing the container number area in a colored image of the container;
HIS (Hue, Intensity, Saturation) color transformation module means for transforming the image in color to provide a transformed image;
segmentation means for receiving the transformed image and segmenting the defective portion form the normal portion to provide a segmented image, the segmentation means including a quad-tree split module and an image merge module;
image filter module means for filtering the normal portion out of the segmented image to provide a filtered image;
and
container defect positioning module means for precisely locating the defect in the segmented image,
wherein the quad-tree split module segments the transformed image into 20×15 blocks of size 32×32 and then the blocks are selectively split by said quad-tree module into sub-blocks,
wherein the quad-tree split module utilizes HIS color variance to determine whether blocks should be split,
wherein a code number is given to each sub-block and the code number is pushed into a queue, and
wherein each code number is taken out of the queue and checked should the corresponding sub-block should be split again.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 10/256,008Filed 27 Sep 2002
Published: US 2004/0062348 A11 Apr 2004
Granted: 3 Oct 2006
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G01N 21/8903
Optical details; Scanning details: using a multiple detector array
G01N 2021/8861
Grading and classifying of flaws: determining coordinates of flaws
G01N 2021/8887
Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for…: based…
G01N
Investigating or analysing materials by determining their chemical or physical properties