公开(公告)号：EP2327057A4

公开(公告)日：2017-11-22

申请号：EP09816484

申请日：2009-09-18

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  MAUL TOMAS HENRIQUE ,  LAI WENG KIN

IPC: G06K9/00 ,  G08B13/196

CPC classification number: G06K9/00348 ,  G06K9/00771 ,  G08B13/19615

Abstract: With the growing market for video surveillance in security area, there is a need for an automated system which provides a way to track and detect human intention based on a particular human motion. The present invention relates to a system and a method for identifying human behavioral intention based on effective motion analysis wherein, the system obtains a sequence of raw images taken from live scene and processes the raw images in an activity analysis component. The activity analysis component is further provided with an activity enrollment component and activity detection component.

公开(公告)号：MY194055A

公开(公告)日：2022-11-10

申请号：MYPI2017000524

申请日：2017-04-07

Applicant: MIMOS BERHAD

Inventor： HASMARINA BINTI HASAN ,  LIANG KIM MENG ,  HAMAM MOKAYED ,  HUM YAN CHAI ,  HON HOCK WOON

IPC: G06T7/00 ,  G06K9/00

Abstract: The present invention relates to a method for recognising special license plate (1000) by separating input of a binarised plate image into alphabet part and numeric part (1100); computing width to height ratio of the alphabet part (1200); determining whether the width to height ratio of the alphabet part is more or less than a predetermined ratio (1300); computing density of white pixel of a vertical histogram projection to recognise standard cursive plate of special license plate (1400) if the width to height ratio of the alphabet part is less than the predetermined ratio; and computing density of white pixel of the vertical histogram projection to recognise non-standard cursive plate of special license plate (1500) if the width to height ratio of the alphabet part is more than the predetermined ratio.

公开(公告)号：MY173744A

公开(公告)日：2020-02-18

申请号：MYPI20092455

申请日：2009-06-15

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  ZULAIKHA KADIM ,  AHMED BAHAA AL-DEEN ,  LIM MEI KUAN ,  TANG SZE LING

Abstract: A method to determine point-of-sight from a sequence of image is described with the following steps. First, visual fixation of human is determined from a sequence of image (20). Then, gaze intersection of visual fixation is detected (40). Multiscale weight is then computed (61) which assign weightage to each pixel which reflect the significance of a particular point, assuming that a point nearer to the detected intersection has a higher possibility of being point-of-sight. Every weightage map is next superimposed and new weightage point for every coordinate is accumulated (62). Later, the master point-of-sight map is updated (63) and harmonized (64). A high value of weightage indicates high probability of point-of-sight. Finally, the weightage of each pixel in the master point-of-sight map is analyzed and compared against predefined rules to indicate the level of suspiciousness in the scene and actuate alert accordingly 80.

公开(公告)号：MY173003A

公开(公告)日：2019-12-18

申请号：MYPI20093678

申请日：2009-09-04

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  ZULAIKHA KADIM ,  LIM MEI KUAN ,  TANG SZE LING

IPC: A61B3/113

Abstract: A method of providing a signal to predict trajectory path of an object from a sequence of image is described. The image is analyzed by first collecting common paths (16) of a scene. Then, objects entering the scene are analyzed to determine gaze direction of object (50). Later, a frame-based probability of predicted path based on gaze direction of object in each frame (70) is determined. Next, block-based probability of predicted path based on intervals of a number of frames (74) is determined. The trajectory path can be predicted from highest probability and common path (76).

公开(公告)号：MY167109A

公开(公告)日：2018-08-10

申请号：MYPI20095129

申请日：2009-12-02

Applicant: MIMOS BERHAD

Inventor： LIM MEI KUAN ,  LIANG KIM MENG ,  ZULAIKHA KADIM ,  TANG SZE LING

IPC: G06K9/46 ,  G06T7/40

Abstract: A method of identity recognition via human (subject) lip images is proposed. The method includes registration (140) of templates (135) of the lip images for known subjects for later matching with lip images from subjects for identification, by digitally matching (740) with the registered templates (135). The lip portions are divided in four quadrants (410-440) for feature extraction which permits template matching (740) even when only partial Hp images are available for identification. The method includes classifying (220) the lips into categories, for defined characteristic features to be extracted, where the different categories of lips (310-350) contain different prominent features that are unique for representation. The feature extraction from the quadrants may be done in different orientations (610-640). The acquisition of the lip images (110,710) is by available image sensor technologies such as optical imaging, thermal imaging, ultrasonic imaging, passive capacitance and active capacitance imaging.

公开(公告)号：MY184604A

公开(公告)日：2021-04-07

申请号：MYPI2013702295

申请日：2013-11-28

Applicant: MIMOS BERHAD

Inventor： YUEN SHANG LI ,  CHOONG TECK LIONG ,  HON HOCK WOON ,  HASMARINA BINTI HASAN ,  LIANG KIM MENG

Abstract: The present invention relates to a method for estimating a possible route of an incomplete tag access information. The method comprises the steps of by a Region Ontology Generator (30), creating a region ontology for each tag access information received by the Region Ontology Generator (30), setting the row and column of the region ontology according to the connected region identification by the Region Ontology Generator (30), filling up the region ontology with tag identification numbers and need tag values by the Region Ontology Generator (30), generating intensity profile data of a user based on historical access frequency data by an Intensity Profiling Module (50), searching for probable route taken by the user based on the region ontology by a Probably Route Searching Module (70) and estimating the best route based on the probable route found and intensity profile data by a Best Route Estimation module (80). FIG. 1

公开(公告)号：MY181097A

公开(公告)日：2020-12-17

申请号：MYPI2015704495

申请日：2015-12-09

Applicant: MIMOS BERHAD

Inventor： HAMAM MOKAYED ,  NG HOOI SIN ,  LIANG KIM MENG ,  HON HOCK WOON ,  HUM YAN CHAI

Abstract: The present invention relates to a system and method that is capable of identifying the base colour of a plate from one or more images which are applicable in determining the types of vehicles based on the base colour of the vehicle license plate. In particular, this invention enables taxis in Malaysia which have license plates with a white background and black characters, and normal vehicles in Malaysia which carry license plates with black background and white characters to be identified. (The Most Illustrative Drawing: Figure 1).

公开(公告)号：MY180638A

公开(公告)日：2020-12-03

申请号：MYPI20090890

申请日：2009-03-05

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG

IPC: G06K9/00

Abstract: The present invention discloses an authentication method and system to identify a user. This method includes the steps of capturing an image of at least one fingerprint of a hand by performing a and shaking process using an imaging scanner (102); and matching the captured image of the fingerprint by a feature matching component (308) with a stored image from a database (106) of the fingerprint for identifying the user. The main feature of this method is that the fingerprint is aligned in a standard location and orientation by an alignment component (204) prior to being matched with the stored image for ensuring that all fingers are placed side by side in a vertical position.

公开(公告)号：MY168010A

公开(公告)日：2018-10-11

申请号：MYPI20083220

申请日：2008-08-22

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG

Abstract: A METHOD TO RECOGNIZE FINGERPRINT IS DESCRIBED. FINGERPRINT IMAGE 102 IS NORMALIZED BEFORE ACQUIRING MINUTIAE POINTS. THE EXTRACTED MINUTIAE POINTS ARE REPRESENTED IN A SINGLE SIGNATURE 147. MINUTIAE POINTS FROM MORE THAN ONE FINGERPRINT CAN BE STORED IN THE FINGERPRINT SIGNATURE. THE SIGNATURE IS CREATED BY INTEGRATING THE EXTRACTED MINUTIAE POINTS OF EACH FINGERPRINT AND USING GEOMETRIC SHAPE FILTERS TO CREATE MINUTIAE CURVES 145. THE NUMBER OF RING IN THE FILTER USED CORRESPONDS TO THE NUMBER OF MINUTIAE CURVES CREATED. IN A FINGERPRINT MATCHING PROCESS, TWO FINGERPRINT SIGNATURES ARE COMPARED. A MATCHING SCORE IS COMPUTED BASED ON THE CURVE MINUTIAE ANALYSIS USED TO MATCH TWO MINUTIAE CURVE 145B, 145B. EACH MINUTIAE CURVE COMPARISON CREATES A MATCHING SCORE. A TOTAL MATCHING SCORE IS COMPUTED TO MATCH TWO FINGERPRINT SIGNATURES. FIG. 9

公开(公告)号：MY168006A

公开(公告)日：2018-10-11

申请号：MYPI20084561

申请日：2008-11-13

Applicant: MIMOS BERHAD

Inventor： LIANG KIM MENG ,  ZULAIKHA KADIM

IPC: G06K9/00 ,  G06T5/00

Abstract: APPARATUS AND METHOD TO VALIDATE FACE IMAGE FOR FACE BIOMETRIC APPLICATION THE PRESENT INVENTION RELATES GENERALLY TO AN APPARATUS AND METHOD FOR 5 ENSURING A FACE IMAGE IS SUITABLE TO BE USED AS AN INPUT FOR FACE BIOMETRIC APPLICATION BY MEANS OF SIMULTANEOUSLY CAPTURING A PLURALITY OF FACE IMAGES (10) IN DIFFERENT ORIENTATIONS USING AN IMAGE CAPTURING DEVICE (2) HAVING THREE IMAGE SENSORS (2A) (213) (2C) AND THEREAFTER PROCESSING THE SAID IMAGES (10) TRANSFORMING IT INTO A FINAL FACE IMAGE (18) SUITABLE AS INPUT IMAGE FOR ENROLMENT 0 INTO FACE BIOMETRIC SYSTEM. (THE MOST ILLUSTRATIVE