| Summary: | 碩士 === 國立雲林科技大學 === 資訊工程研究所 === 94 === The occurrence of defect on a wafer may result in losing the yield ratio. The defective regions were usually identified through visual judgment with the aid of a scanning electron microscope. Dozens of people visually check wafers and hand-mark their defective regions leading to a significant amount of personnel cost. In addition, potential misjudgment may introduce due to human fatigue. In this thesis, a two-layer Hopfield neural network called the competitive Hopfield wafer-defect detection neural network (CHWDNN) is proposed to detect the defective regions of wafer image. The CHWDNN extends the one-layer 2-D Hopfield neural network at the original image plane to a two-layer 3-D Hopfield neural network with defect detection to be implemented on its third dimension. With the extended 3-D architecture, the network is capable of incorporating a pixel’s spatial information into a pixel-classifying procedure. The experimental results show the CHWDNN successfully identifies the defective regions on wafer images with good performances. In addition, a specific contextual Hopfield neural network called the contextual Hopfield LED die detection neural network (CHDDNN) and a LED defect inspection algorithm is presented for inspecting the die regions of LED wafer image. The experimental results show the CHDDNN successfully segment the die region on LED wafer images and the inspection algorithm can inspect the defective die correctly.
|
|---|
