Abstract: A method for diagnosing a reason of a malfunction is provided. The method includes: receiving a signal to be diagnosed; decomposing the signal to be diagnosed into a plurality of sub-signals; transforming each of the plurality of sub-signals into a corresponding grayscale image; and inputting the corresponding grayscale images to a neural network model, and outputting a malfunction reason classification result through the neural network model. Accordingly, the method can be used for diagnosing the reason of the malfunction and solves the problem of incapable of diagnosing the reason of the malfunction. In addition, a device and a computer-readable recording medium for diagnosing the reason of the malfunction are also provided.

Abstract: A non-intrusive detection method for detecting at least one pop-up window button of the pop-up window includes the following steps: retrieving a screen image on a display device; comparing the screen image with a preset screen image and generating a differential image area according the screen image and the preset screen image; determining the differential image area as the pop-up window when the differential image area is greater than an image area threshold value; selecting a plurality of contour lengths of the pop-up window matching up with a contour length threshold value by Canny edge detector; and analyzing the contour lengths according to Douglas-Peucker algorithm and an amount of endpoints to generate a contour edge corresponding to the pop-up window button.

Abstract: An automatically detecting method for time-varying text region of interest is disclosed. The automatically detecting method is adapted to an image processing unit of an information retrieval system, to detect a time-varying text region of interest having specific characters or character set as unit on an operation screen of a manufacturing machine, a processing machine or other equipment; furthermore, the automatically detecting method can be performed based on presence or absence of the historical screen data, and union of the detected region proposals for the time-varying text region of interest, to obtain an automatically labeled and selected time-varying text region of interest. According to the automatically detecting method, the user only needs to confirm whether the required data are labeled and selected, so it is more convenient for the user to setting data, and greatly helpful to reduce the setting time and correctly detect the required information.

Abstract: A non-transitory computer readable storage medium storing a data structure and a computer program includes: a number of stored files each of which includes a number of fields including: at least one first field and at least one second field. Said at least one first field stores tag data of a region of interest of a video file, and said at least one second field stores inference data associated with the region of interest of a video file. The computer program reads the stored files and outputs a field content of the fields of the stored files when executed by a data processing device. The present disclosure also provides an artificial intelligence inference method and system configured to perform: searching the data structure according to a query to obtain a field content, and performing analysis according to input data and the field content.

Abstract: A query-oriented event recognition system includes a capturing unit, an analyzing inference engine assembly, a synchronization processing unit and an event definition unit. The capturing unit is configured to capture at least one data flow including a plurality of time points and data, and each time points is corresponding to a data. The analysis and inference engine assembly includes a plurality of inference engines. The analysis and inference engine assembly is configured to analyze and reason the data of the time points by the inference engines to generate at least one inference data corresponding to the data at each time point. The synchronization processing unit is configured to generate an inference data set corresponding to each time point according to the data flow and the inference data. The event definition unit is configured to find an event query result matching up with the inference data set through a query statement.

Abstract: A non-intrusive detection method for detecting at least one pop-up window button of the pop-up window includes the following steps: retrieving a screen image on a display device; comparing the screen image with a preset screen image and generating a differential image area according the screen image and the preset screen image; determining the differential image area as the pop-up window when the differential image area is greater than an image area threshold value; selecting a plurality of contour lengths of the pop-up window matching up with a contour length threshold value by Canny edge detector; and analyzing the contour lengths according to Douglas-Peucker algorithm and an amount of endpoints to generate a contour edge corresponding to the pop-up window button.

Abstract: A non-intrusive shared processing method for pop-up window is applied for inhibiting or closing the pop-up window on the display device. The method includes the following steps: a non-intrusive terminal device publishing the pop-up window data to an information theme in a communication interface; a central processing device subscribing to the information theme to receive the pop-up window data and generating a decision data corresponding to the pop-up window data, and publishing the decision data to the information theme; and, the non-intrusive terminal device receiving the decision data from the information theme and inhibiting or closing the pop-up window of the display device according to the decision data. Therefore, the method of the present invention can automatically transmit the information and solution of the pop-up window to other equipments with the same type through subscription/publishing mechanism, thereby decreasing the process time.

Abstract: The present invention provides an automated optical inspection and classification apparatus based on a deep learning system, comprising a camera and a processor. The processor executes a deep learning system after loading data from a storage unit and the processor, and comprises an input layer, a neural network layer group, and a fully connected-layer group. The neural network layer group is for extracting to an input image and thereby obtaining a plurality of image features. The fully connected-layer group is for performing weight-based classification and outputting an inspection result.

Abstract: An automatically detecting method for time-varying text region of interest is disclosed. The automatically detecting method is adapted to an image processing unit of an information retrieval system, to detect a time-varying text region of interest having specific characters or character set as unit on an operation screen of a manufacturing machine, a processing machine or other equipment; furthermore, the automatically detecting method can be performed based on presence or absence of the historical screen data, and union of the detected region proposals for the time-varying text region of interest, to obtain an automatically labeled and selected time-varying text region of interest. According to the automatically detecting method, the user only needs to confirm whether the required data are labeled and selected, so it is more convenient for the user to setting data, and greatly helpful to reduce the setting time and correctly detect the required information.

Abstract: A cursor image detection comparison and feedback status determination method is disclosed. The method is based on a non-invasive data-extraction system architecture, and uses an image processing unit to perform detection comparison on a cursor image shown on an operation screen outputted from a machine controller. The method includes steps of obtaining cursor foreground and background images set by a user, and selecting an algorithm to process the cursor foreground and background images to generate a cursor mask, and reading a cursor image and applying the cursor mask on the cursor image for pattern comparison, transmitting information of a comparison result and a cursor feedback status to a software control system, so as to provide a correction system to perform a cursor process program and check whether the movement of the cursor meet a position controlled by a feedback and correction system, thereby completing closed-loop control for the cursor.

Abstract: The present invention is an automated optical inspection method using deep learning, comprising the steps of: providing a plurality of paired image combinations, wherein each said paired image combination includes at least one defect-free image and at least one defect-containing image corresponding to the defect-free image; providing a convolutional neural network to start a training mode of the convolutional neural network; inputting the plurality of paired image combinations into the convolutional neural network, and adjusting a weight of at least one fully connected layer of the convolutional neural network through backpropagation to complete the training mode of the convolutional neural network; and performing an optical inspection process using the trained convolutional neural network.

Abstract: A cursor image detection comparison and feedback status determination method is disclosed. The method is based on a non-invasive data-extraction system architecture, and uses an image processing unit to perform detection comparison on a cursor image shown on an operation screen outputted from a machine controller. The method includes steps of obtaining cursor foreground and background images set by a user, and selecting an algorithm to process the cursor foreground and background images to generate a cursor mask, and reading a cursor image and applying the cursor mask on the cursor image for pattern comparison, transmitting information of a comparison result and a cursor feedback status to a software control system, so as to provide a correction system to perform a cursor process program and check whether the movement of the cursor meet a position controlled by a feedback and correction system, thereby completing closed-loop control for the cursor.

Abstract: A method for evaluating an efficiency of a manual inspection for a defect pattern is provided according to an embodiment of the disclosure, which comprises: enabling an evaluation program; loading a test image automatically by the enabled evaluation program and displaying the test image in a user interface; detecting a user behavior of a user after the user watches the test image; generating original data according to the user behavior, wherein the original data reflects at least one of whether the user identifies the defect pattern in the test image and a type of the defect pattern identified by the user; and performing a quantitative operation on the original data to generate evaluation data corresponding to the efficiency of the manual inspection, wherein the evaluation data reflects an evaluation result corresponding to the efficiency of the manual inspection.

Abstract: A display device including a circuit substrate, a plurality of pixels, and a light-shielding layer is provided. The pixels include a plurality of light-emitting elements. The light-emitting elements are disposed on the circuit substrate and are electrically connected to the circuit substrate. The light-emitting elements in the pixels are arranged along an arrangement direction. The light-shielding layer is disposed on the circuit substrate and has a plurality of pixel apertures. The pixels are disposed in a corresponding pixel aperture. The light-shielding layer includes a plurality of first light-shielding patterns extending in the arrangement direction and a plurality of second light-shielding patterns connected to the first light-shielding patterns. The extending direction of the second light-shielding patterns is different from the extending direction of the first light-shielding patterns.

Abstract: A labeling system for defect classification having a storage unit and a processing unit is provided. The storage unit stores a defect classification module, a defect labeling module, and a catalog generation module. The processing unit performs the modules aforementioned. The defect classification module is configured to provide a defect type information. The defect labeling module marks a defect type label to at least one test object image according to an image feature and the defect type information on the at least one test object image. The catalog generation module receives the labeled test object images and moves test object images having the same defect type label to a corresponding file catalog.

Abstract: A training method of an iterative deep learning system, comprising the steps of: providing at least one unlabeled image of an object; labeling the unlabeled image of the object to produce a labeled image of the object; storing the labeled image of the object into an image database if the deep learning system is being trained with a labeled version of the unlabeled image of the object for a first time; identifying the labeled image of the object in the image database and outputting an identification result through the deep learning system; and training the deep learning system according to an error between output and expected output of the identification result; and providing another unlabeled image of the object to the trained deep learning system to identify said another unlabeled image of the object and to produce an inspection result; wherein determining whether the inspection result has satisfied a qualification condition and terminating training if the inspection result has satisfied the qualification co

Abstract: A method for evaluating an efficiency of a manual inspection for a defect pattern is provided according to an embodiment of the disclosure, which comprises: enabling an evaluation program; loading a test image automatically by the enabled evaluation program and displaying the test image in a user interface; detecting a user behavior of a user after the user watches the test image; generating original data according to the user behavior, wherein the original data reflects at least one of whether the user identifies the defect pattern in the test image and a type of the defect pattern identified by the user; and performing a quantitative operation on the original data to generate evaluation data corresponding to the efficiency of the manual inspection, wherein the evaluation data reflects an evaluation result corresponding to the efficiency of the manual inspection.

Abstract: The present invention provides an automated optical inspection and classification apparatus based on a deep learning system, comprising a camera and a processor. The processor executes a deep learning system after loading data from a storage unit and the processor, and comprises an input layer, a neural network layer group, and a fully connected-layer group. The neural network layer group is for extracting to an input image and thereby obtaining a plurality of image features. The fully connected-layer group is for performing weight-based classification and outputting an inspection result.

Abstract: The present invention is an automated optical inspection method using deep learning, comprising the steps of: providing a plurality of paired image combinations, wherein each said paired image combination includes at least one defect-free image and at least one defect-containing image corresponding to the defect-free image; providing a convolutional neural network to start a training mode of the convolutional neural network; inputting the plurality of paired image combinations into the convolutional neural network, and adjusting a weight of at least one fully connected layer of the convolutional neural network through backpropagation to complete the training mode of the convolutional neural network; and performing an optical inspection process using the trained convolutional neural network.

Abstract: A display device including a circuit substrate, a plurality of pixels, and a light-shielding layer is provided. The pixels include a plurality of light-emitting elements. The light-emitting elements are disposed on the circuit substrate and are electrically connected to the circuit substrate. The light-emitting elements in the pixels are arranged along an arrangement direction. The light-shielding layer is disposed on the circuit substrate and has a plurality of pixel apertures. The pixels are disposed in a corresponding pixel aperture. The light-shielding layer includes a plurality of first light-shielding patterns extending in the arrangement direction and a plurality of second light-shielding patterns connected to the first light-shielding patterns. The extending direction of the second light-shielding patterns is different from the extending direction of the first light-shielding patterns.