Abstract: A computer-implemented method is provided for image-based, self-guided object detection. The method includes receiving, by a processor device, a set of images. Each of the images has a respective grid thereon that is labeled regarding a respective object to be detected using grid level label data. The method further includes training, by the processor device, a grid-based object detector using the grid level label data. The method also includes determining, by the processor device, a respective bounding box for the respective object in each of the images, by applying local segmentation to each of the images. The method additionally includes training, by the processor device, a Region-based Convolutional Neural Network (RCNN) for joint object localization and object classification using the respective bounding box for the respective object in each of the images as an input to the RCNN.

Abstract: Scheduling automated visual inspection tasks includes capturing an image of a component to be inspected. A visual inspection model is formed with a model engine as a composite model of utility modules and functional modules to perform visual inspection of the image of the component. An abstract processing workflow of the visual inspection model is derived with a scheduler including dependencies between the utility modules and the functional modules. Performance of each of the functional modules is profiled with the scheduler by testing performance with available hardware resources to produce a performance profile. Parallel instances of each of the functional modules in a branch of the abstract processing workflow are scheduled with the scheduler according to the dependencies and the performance profiles. An indication of defects in the component is produced by processing the visual inspection model according to the scheduled functional modules.

Abstract: A technique includes receiving, by a computer, user input representing creation of a first programmatic description of a first test object of source code to be tested. The technique includes, in response to receiving the user input, determining, by the computer, based on other programmatic descriptions of other test objects, a recommendation of a parameter to be used in the first programmatic description to identify the first test object. The technique includes causing, by the computer, a display of the recommendation.

Abstract: Techniques for generating machine learning architectures are provided. A data set is received for training one or more machine learning (ML) models, where the data set comprises labeled exemplars for a plurality of classes. The data set is partitioned into a training set and a testing set. A first ML model is trained using the training set, and a quality of the first ML model with respect to each class of the plurality of classes is evaluated using the testing set. Upon determining that the quality of the first ML model is below a predefined threshold with respect to a first class and a second class of the plurality of classes, a subset of the training set is identified, where each exemplar in the subset corresponds to either the first class or the second class. A second ML model is trained using the subset of the training set.

Abstract: A computer implemented method for surface defect inspection that includes recording an optical image of a surface including a defect; converting the optical image including the defect into a heat map; extracting a region of interest including the defect from the heat map; and comparing the region of interest including the defect from the heat map to a binary classification model using a sliding window based voting mechanism to determine if the defect is greater than or less than a threshold failure value.

Abstract: Embodiments of the present disclosure relate to object defect detection. In an embodiment, a computer-implemented method is disclosed. According to the method, for a test image of at least one part of a target object, a reference image is generated by repeating a periodic pattern detected in the test image, the target object consisting of elements. A differential image is determined by comparing the test image and the reference image. The differential image is superimposed on a predefined grid image to obtain a superimposed image. The grid image comprises grids corresponding to elements of a reference object associated with the target object. The number of defective elements is determined in the at least one part of the target object based on the superimposed image. In other embodiments, a system and a computer program product are disclosed.

Abstract: A method, a device and a computer program product for image processing are proposed. In the method, whether a first image indicates a defect associated with a target object is determined. In response to determining that the first image indicates the defect, a second image absent from the defect is obtained based on the first image. The defect is identified by comparing the first image with the second image. In this way, the defect associated with the target object in the image can be accurately and efficiently identified or segmented.

Abstract: A method and apparatus for parallelization of data processing. The method including: parsing a data processing flow to split a write table sequence for the data processing flow; generating a plurality of instances of the data processing flow based at least in part on the split write table sequence; and scheduling the plurality of instances for parallelization of data processing.

Abstract: A method, system, and computer program product, include obtaining window status decision information based on vehicle interior background noise and determining switch status of the vehicle window(s) based on the obtained window status decision information.

Abstract: A method to train a machine learning model for in-vehicle air quality control in a knowledge-based system, executed by one or more computer processors, includes collecting data related to in-vehicle air quality from a plurality of probe cars where the data is collected by various on-board systems in each probe car. The method includes correlating the data related to in-vehicle air quality from each probe car with air quality measurements from each probe car, where the correlation is used to update the machine learning model. The method includes determining a situation when an in-vehicle air quality measurement of the air quality measurements is above a pre-determined in-vehicle air quality level and determining instructions for actions by one or more of the one or more on-board systems in each of the probe cars to maintain an in-vehicle air quality level at or below the pre-determined in-vehicle air quality level.

Abstract: Methods and systems for detecting abnormal connectivity on a product are provided. The methods receive an inspection image of the product including a defect, match the inspection image with a template image of the product to locate a corresponding normal region in the template image and obtain a differential image between the inspection image and the normal region. The method further includes forming a regional mask image from component masks. Each of the component masks includes a binary image of the template image with only one kind of components of the product remaining. The regional mask image is a region in its corresponding component mask that corresponds to the normal region. The method further includes determining, based on a calculation using the differential image and the at least one regional mask image, at least one of: connectivity relationship, connectivity type and connectivity scale of abnormal connectivity on the product.

Abstract: Techniques are provided for blockchain based a data transformation. According to one aspect, a series of Internet of Things (IoT) data is received by one or more processing units. And at least one reference data set to the received series of IoT data are attached by one or more processing units. The received series of IoT data attached are processed, by one or more processing units, with at least one transformation module to obtain a processing result of the at least one reference data set. A hash value of the processing result is calculated by one or more processing units. The hash value of the processing result and a hash value of an expected result stored in a blockchain system are compared. In respond to the hash value of the processing result being not matched with the hash value of the expected result, the decision of the at least one transformation module having been tampered with is determined by one or more processing units.

Abstract: Blockchain based IoT data management can include receiving IoT data are with one or more processing units. At least one aggregation pattern of the IoT data can be determined by one or more processing units. The IoT data can be hashed, based upon the at least one aggregation pattern to obtain hash values of the IoT data by one or more processing units. The hash values can be sent to a blockchain system for storing by one or more processing units.

Abstract: The present disclosure provides a method for characterizing ohmic contact electrode performance of a semiconductor device. The method comprises: preparing two sets of testing patterns on a semiconductor device; testing resistance values of the two sets of testing patterns respectively; calculating a sheet resistance of an ohmic contact area according to the obtained resistance values; and evaluating the ohmic contact electrode performance of the semiconductor device according to the sheet resistance of the ohmic contact electrode.

Abstract: Embodiments facilitating audio source identification are provided. A computer-implemented method comprises: receiving, by a device operatively coupled to one or more processors, an audio signal under inspection; generating, by the device, an image of time-frequency spectrum of low frequency component and high frequency component of the audio signal; and identifying, by the device, a source of the audio signal based on the generated image and one or more patterns of time-frequency spectrum, wherein each of the one or more patterns is corresponding to low frequency feature and high frequency feature of a specific audio source.

Abstract: The present disclosure relates to a method and system for generating a road network. An embodiment of the present invention provides a method comprising: identifying a target area to be refined in a road network skeleton; and refining the target area using at least one trajectory associated with the target area to generate the road network. Another embodiment of the present invention provides a corresponding system.

Abstract: The present disclosure relates to the technical field of tea brewing devices, and more particularly, to a beverage brewing device. The beverage brewing device comprises a kettle body, a heating disc, and a tea-leaf basket. The heating disc and the tea-leaf basket are located in the kettle body and an air cylinder mechanism is fixed in the kettle body. A moving piston is arranged in an inner cavity of the air cylinder mechanism, and the piston is connected to the tea-leaf basket. The air cylinder mechanism is connected to an air pump, which is used for conveying a driving gas to the air cylinder mechanism. The piston is driven by the driving gas, thereby driving the tea-leaf basket to move in the kettle body. The air cylinder mechanism may automatically drive the tea-leaf basket to move up and down, achieving a simple structure and a low cost.

Abstract: Embodiments of the present invention facilitate product defect detection. A computer-implemented method comprises: receiving, by a device operatively coupled to one or more processors, a template image of a normal product; generating, by the device, one or more geometric training parameters for transforming the template image; and transforming, by the device, the template image using the one or more geometric training parameters to generate a transformed image for training a data model, wherein the trained data model being used for aligning the template image and an image under inspection of a product.

Abstract: Embodiments facilitating audio source identification are provided. A computer-implemented method comprises: receiving, by a device operatively coupled to one or more processors, an audio signal under inspection; generating, by the device, an image of time-frequency spectrum of low frequency component and high frequency component of the audio signal; and identifying, by the device, a source of the audio signal based on the generated image and one or more patterns of time-frequency spectrum, wherein each of the one or more patterns is corresponding to low frequency feature and high frequency feature of a specific audio source.

Abstract: Examples relate to identifying heartbeat messages. In one example, a computing device may: obtain a plurality of messages that includes incoming messages and outgoing messages, each incoming message being sent from a server device to a client device, and each outgoing message being sent from the client device to the server device; identify candidate message pairs, each candidate message pair including one incoming message and one outgoing message; and identify a heartbeat message pair from the candidate message pairs based on at least one of: plurality of timestamps that includes i) incoming message timestamps that each correspond to one of the incoming messages, and ii) outgoing message timestamps that each correspond to one of the outgoing messages; a number of occurrences of each candidate message pair included a message log; or characteristics of data included in the incoming message and outgoing message of each candidate message pair.