公开(公告)号：US20230138430A1

公开(公告)日：2023-05-04

申请号：US17848389

申请日：2022-06-24

Applicant: SEMES CO., LTD.

Inventor： Ji Hoon YOO ,  Kwang Sup KIM ,  Jong Min LEE ,  Yeon Chul SONG ,  Jun Ho OH ,  Young Ho PARK ,  Myeong Jun LIM

IPC: G06V10/774 ,  G06V10/764 ,  G06T7/00 ,  G06V10/776

Abstract: A method for generating an adaptive training image dataset capable of improving prediction accuracy is provided. The method comprises preparing a first image dataset, wherein the first image dataset includes a plurality of first images and a first class corresponding to each of the plurality of first images, performing a learning algorithm on the first image dataset to generate a first learning model, preparing a second image dataset, wherein the second image dataset includes a plurality of second images and a second class corresponding to each of the plurality of second images, inputting the second image to the first learning model to obtain a prediction class corresponding to the second image, determining which class of image the second image is similar to in case of the second class corresponding to the second image being different from the prediction class, updating the second image dataset by updating a class corresponding to the second image according to the determination result, and performing a learning algorithm on the first image dataset and the updated second image dataset to generate a second learning model.

公开(公告)号：US20230206424A1

公开(公告)日：2023-06-29

申请号：US18075412

申请日：2022-12-06

Applicant: SEMES CO., LTD.

Inventor： Myeong Jun LIM ,  Kwang Sup KIM ,  Yeon Chul SONG ,  Ji Hoon YOO ,  Jong Min LEE ,  Jun Ho OH ,  Young Ho PARK

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/187 ,  B41J2/045

CPC classification number: G06T7/001 ,  G06T7/11 ,  G06T7/187 ,  B41J2/0451 ,  B41J2/04586 ,  G06T2207/20081 ,  G06T2207/20221 ,  G06T2207/20021 ,  G06T2207/30168 ,  G06T2207/30144

Abstract: Provided are a nozzle inspection unit configured to generate a large amount of defect data to improve detection accuracy of a defective nozzle, and a substrate treatment apparatus including the same. The nozzle inspection unit includes: a data collection module configured to collect a plurality of image data related to nozzles; a data classification module configured to classify the plurality of image data according to predefined classes; a data merging module configured to merge good image data related to a normal nozzle and defect image data related to a defective nozzle from among the plurality of image data; a data training module configured to train a plurality of merged image data obtained through the data merging module; and a defect data generation module configured to generate a plurality of final image data from the plurality of merged image data based on the training result.

公开(公告)号：US20230206415A1

公开(公告)日：2023-06-29

申请号：US18076401

申请日：2022-12-07

Applicant: SEMES CO., LTD.

Inventor： Ji Hoon YOO ,  Kwang Sup KIM ,  Jong Min LEE ,  Yeon Chul SONG ,  Jun Ho OH ,  Young Ho PARK ,  Myeong Jun LIM

IPC: G06T7/00 ,  H04N1/034 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764

CPC classification number: G06T7/0002 ,  H04N1/034 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764

Abstract: Provided are a substrate inspecting unit capable of reducing image data labeling work time through training image data set verification and semi-automatic image labeling, and at the same time, improving prediction performance by improving classification accuracy for data sets, and a substrate treating apparatus including the same. The substrate inspecting unit comprises a feature extracting module for extracting a feature from training data included in each class in response to a plurality of training data related to image data of a substrate being classified according to a predefined class, a validity evaluating module for evaluating validity of the feature, a class verifying module for verifying the predefined class, and a data reconstructing module for reconstructing the plurality of training data based on a feature determined as valid and a verified class, wherein reconstructed training data is utilized when inspecting the substrate.

公开(公告)号：US20230204648A1

公开(公告)日：2023-06-29

申请号：US17837027

申请日：2022-06-10

Applicant: SEMES CO., LTD.

Inventor： Jun Ho OH ,  Kwang Sup KIM ,  Jae Hong KIM ,  Kyung Hun JANG ,  Young Ho PARK ,  Jong Min LEE ,  Yeon Chul SONG ,  Sang Min HA ,  Ji Hoon YOO ,  Myeong Jun LIM

IPC: G01R29/24

CPC classification number: G01R29/24

Abstract: A static electricity visualization apparatus capable of visually identifying a measured level of static electricity is provided. The static electricity visualization apparatus comprises a photographing unit for generating a first photographed image obtained by photographing a measurement target at a first distance from the measurement target in a first mode, and generating a second photographed image obtained by photographing the measurement target at a second distance from the measurement target in a second mode, a static electricity sensor for measuring a static electricity level of the measurement target at the second distance from the measurement target, a processor for matching the second photographed image with the first photographed image, and an output unit for outputting a static electricity visualization image that visualizes a static electricity level measured by the static electricity sensor on the first photographed image, wherein the static electricity visualization image comprises a color corresponding to the static electricity level of the measurement target measured by the static electricity sensor at a position where the second photographed image matches on the first photographed image.

公开(公告)号：US20230116619A1

公开(公告)日：2023-04-13

申请号：US17743432

申请日：2022-05-12

Applicant: SEMES CO., LTD.

Inventor： Jun Ho OH ,  Kwang Sup KIM ,  Jong Min LEE ,  Yeon Chul SONG ,  Young Ho PARK ,  Ji Hoon YOO ,  Myeong Jun LIM

IPC: G06T11/00 ,  G06T7/73 ,  G06T11/20 ,  G01R19/00

Abstract: A static electricity visualization system capable of visually confirming the level of the measured static electricity is provided. The static electricity visualization system comprises a first measuring unit for measuring a static electricity level detected at a first position of a measurement target and comprising a first mark, a photographing unit for generating a photographed image by photographing the measurement target, a processor for recognizing a first mark in the photographed image and calculating coordinates of the first mark on the photographed image, and an output unit for outputting a static electricity visualization image that visualizes the static electricity level measured by the first measuring unit in a first mode, wherein the static electricity visualization image comprises a color corresponding to a level of static electricity measured by the first measuring unit on the coordinates of the first mark of the photographed image.

公开(公告)号：US20230101546A1

公开(公告)日：2023-03-30

申请号：US17876545

申请日：2022-07-29

Applicant: SEMES CO., LTD.

Inventor： Yeon Chul SONG ,  Myeong Jun Lim ,  Kwang Sup Kim ,  Jong Min Lee ,  Jun Ho Oh ,  Ji Hoon Yoo ,  Young Ho Park

IPC: B41J2/045 ,  B41J29/20

Abstract: Provided are a control unit that predicts the life of an inkjet head unit and maximizes its life to be used, and a substrate treating apparatus including the same. The control unit performs maintenance of an inkjet head unit for discharging a substrate treatment liquid onto a substrate and comprises a count module for counting the number of discharges for each nozzle of the inkjet head unit, a comparison module for comparing the number of discharges with a reference value to determine whether the number of discharges is equal to or greater than the reference value, and an evaluation module for evaluating whether a life of the inkjet head unit has reached a usable life based on whether the number of discharges of each nozzle is equal to or greater than the reference value.