Agency for Science, Technology and Research

Jierong Cheng

Wei Xiong

Wenyu Chen

Jia Du

Ying Sun

Ying Quan

Teck Sun Marcus Wan

Yusha Li

This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

Defect detection in image space

This disclosure relates to method and system for visual inspection of rotating components. The method includes representing rotation cycles of a rotating component as spatial features based on video or image frames, ascertaining and/or evolving Hidden Markov Model (HMM) chains for the cycles, ascertaining a count of the rotating component in the frames and/or labelling the frames with ascertained states of the HMM chains.

Method and system for visual based inspection of rotating objects

A system and a method for imaging a surface defect on an object are provided. The system includes an actuator, a sensor assembly connected to the actuator, and a processor configured to control the actuator and the sensor assembly. The sensor assembly includes at least one sensor configured to capture at least one image of the object. The processor is configured to control the actuator and the sensor assembly to identify the actuator and the sensor assembly, a region of a region of interest associated with the surface defect using an using an image of the object and to repeatedly identify at least one subsequent region of interest associated with the surface defect using at least a preceding region of interest such that the surface defect is identified according to a predetermined criterion.

System and method for imaging a surface defect on an object

Growing community of inventors

Singapore, Singapore

Jierong Cheng