Nondestructive characterization of crystalline wafers is provided, including defect detection, identification, and counting. Certain aspects relate to development of nondestructive, high fidelity defect characterization and/or dislocation counting methods based on deep neural networks. Certain aspects relate to nondestructive methods for defect characterization of silicon carbide (SiC) wafers. By subjecting SiC wafers to nondestructive defect characterization, SiC wafers in their final state may be characterized and subsequently used for device fabrication, vastly reducing the expense of the characterization process. Nondestructive defect characterization also allows for increased sampling and improved feedback loops between crystalline growth process development and subsequent device production.

An information processing apparatus includes a reception unit configured to receive an input specifying a position of a detection target included in an image, an acquisition unit configured to acquire a storage amount of training data including a pair of information indicating the image and information indicating the position specified by the input, a training unit configured to train a training model to detect the detection target from the image based on the stored training data, and a display control unit configured to control a display unit to display the storage amount, and a reference amount of the training data set as an amount of the training data necessary for the training unit to train the training model, in a comparable way.

An embodiment provides a method for measuring particles on a wafer surface, the method including: disposing and rotating a wafer on a stage; irradiating a laser in a first region of a center of a surface of the rotating wafer, a second region between the first region and a third region, and the third region at an edge thereof; and measuring a laser reflected from the first to third regions of the wafer, wherein a second output of the laser irradiated in the second region is larger than a first output of the laser irradiated in the first region and a third output of the laser irradiated in the third region is larger than the second output of the laser irradiated in the second region.

A system and method for inspection and cosmetic grading of objects is provided. Camera and lighting assemblies capture images of an object and create a 2D composite image which is processed by an image processing module with a deep learning machine algorithm to detect surface defects in the object. Detected defects are localized and measured for depth of defect by an advanced optical sensor, providing a 3D representation of defects. A cosmetic grading algorithm determines the cosmetic grade of the object and the optimal path of disposition for the item based on the grade.

An embodiment provides a method for measuring particles on a wafer surface, the method including: disposing and rotating a wafer on a stage; irradiating a laser in a first region of a center of a surface of the rotating wafer, a second region between the first region and a third region, and the third region at an edge thereof; and measuring a laser reflected from the first to third regions of the wafer, wherein a second output of the laser irradiated in the second region is larger than a first output of the laser irradiated in the first region and a third output of the laser irradiated in the third region is larger than the second output of the laser irradiated in the second region.

Nondestructive characterization of crystalline wafers is provided, including defect detection, identification, and counting. Certain aspects relate to development of nondestructive, high fidelity defect characterization and/or dislocation counting methods based on deep neural networks. Certain aspects relate to nondestructive methods for defect characterization of silicon carbide (SiC) wafers. By subjecting SiC wafers to nondestructive defect characterization, SiC wafers in their final state may be characterized and subsequently used for device fabrication, vastly reducing the expense of the characterization process. Nondestructive defect characterization also allows for increased sampling and improved feedback loops between crystalline growth process development and subsequent device production.

A method of inspecting a semiconductor device, includes: scanning a plurality of first circuit pattern layers of the semiconductor device and generating a plurality of first images respectively corresponding the plurality of first circuit pattern layers of the semiconductor device; overlapping the plurality of first images with each other and counting a plurality of first defects in the overlapped first images; setting main inspection areas with priority orders by using position coordinates of the counted first defects; and storing the main inspection areas with the position coordinates of the counted first defects.

Enhanced evaluation of pre-owned electronic devices related services are described. Example evaluation devices (e.g. kiosks etc.) and techniques for enhanced evaluation are described. An example evaluation device includes an evaluation area in which a previously-owned electronic device (e.g. smartphone etc.) is arranged with its camera configured to capture images of the evaluation area. An example apparatus includes a previously-owned electronic device arranged with its camera configured to capture images of another previously-owned electronic device within an evaluation area. Other example implementations include detecting microdefects and/or micro-differences for identifying a device; based on an evaluation of a device, providing any of a repair quote, an insurance or warranty quote, an insurance or warranty claim, a certification, or a promise to purchase; processing evaluation session attributes based on the selected context; and providing a point-of-sale integration component configured to intercept data from a coupon reader.

There is presented a system and method for detecting mobile device fault conditions, including detecting fault conditions by software operating on the mobile device. In one embodiment, the present invention provides for systems and methods for using a neural network to detect, from an image of the device, that the mobile device has a defect, for instance a cracked or scratched screen. Systems and methods also provide for, reporting the defect status of the device, working or not, so that appropriate action may be taken by a third party.

Enhanced evaluation of pre-owned electronic devices related services are described. Example evaluation devices (e.g. kiosks etc.) and techniques for such enhanced evaluation are described. An example evaluation device includes an evaluation area in which a previously-owned electronic device (e.g. smartphone etc.) is arranged with one of its cameras configured to capture images of the evaluation area. An example apparatus includes an evaluation area, and a previously-owned electronic device arranged with one of its cameras configured to capture images of another previously-owned electronic device within the evaluation area. Other example implementations include detecting microdefects and/or micro-differences in captured images, and thereby identifying previously-owned electronic device; evaluating a previously-owned electronic device, and based on the evaluation, providing any of a repair quote, an insurance or warranty quote, an insurance or warranty claim, a certification, or a promise to purchase; selecting a context from the plurality of contexts for an evaluation, and processing evaluation session attributes based on the selected context; and providing a point-of-sale integration component configured to intercept data from a coupon reader associated with a point-of-sale system.