Disclosed is an AI acoustic camera including an acoustic source localizing means unit of generating position-specific acoustic level data by determining a position of an acoustic source, an AI acoustic analysis unit of recognizing a type of acoustic source estimated as an abnormal acoustic source by extracting a regeneration time domain acoustic signal for the acoustic source with the determined position and AI-learning and recognizing an acoustic feature image of the extracted time domain acoustic signal, an object recognition unit of recognizing a type of object positioned in the acoustic source through image analysis of an area recognized as that the acoustic source is positioned, and a determination unit of determining the acoustic source as a true acoustic source when the type of acoustic source and the type of object have commonality.

Disclosed is an AI acoustic camera including an acoustic source localizing means unit of generating position-specific acoustic level data by determining a position of an acoustic source, an AI acoustic analysis unit of recognizing a type of acoustic source estimated as an abnormal acoustic source by extracting a regeneration time domain acoustic signal for the acoustic source with the determined position and AI-learning and recognizing an acoustic feature image of the extracted time domain acoustic signal, an object recognition unit of recognizing a type of object positioned in the acoustic source through image analysis of an area recognized as that the acoustic source is positioned, and a determination unit of determining the acoustic source as a true acoustic source when the type of acoustic source and the type of object have commonality.

An image sensor, electronic device and method thereof that performs on-sensor single object class detection using an on-sensor single object class detection deep neural network (DNN), such as a face detection DNN. The single object class detection DNN includes a pixel array layer configured to capture an image and transfer image data of the captured image, and a logic and single object class detection deep neural network (DNN) layer that receives the image data directly from the pixel array layer and outputs the image data with the single object class detection data to a communication bus of an electronic device.

Provided are a method and apparatus for recognizing an object. An object recognition method performed by an object recognition apparatus includes receiving reflected light in which light is reflected by a recognition pattern disposed on an object and passes through a lens, identifying the recognition pattern disposed on the object from the reflected light, and comparing the identified recognition pattern with recognition patterns defined for respective objects and determining an object viewed by a user based on a result of the comparison, wherein the recognition pattern is a pattern in which different colors are arranged adjacently.

A medicine administration system includes a medicine administration device, a medicine cartridge receivable with the medicine administration device, and a contrast background. The medicine cartridge is configured to retain medicine therein. The medicine administration device is configured to dispense at least some of the medicine through a dispensing end of the medicine cartridge. The contrast background is positioned relative to the medicine cartridge to permit visualization of the contrast background through the medicine within the medicine cartridge. The contrast background is configured to facilitate image processing of a captured image of the contrast background through the medicine within the medicine cartridge to determine a condition of the medicine within the medicine cartridge.

An imaging device includes an image sensing unit configured to generate image data by sensing incident light received from a scene, a line buffer configured to store image data received from the image sensing unit, an optical distortion corrector (ODC) configured to perform lens distortion correction for output pixel coordinates based on input pixel coordinates of the image data stored in the line buffer, and a read speed controller configured to control a read speed at which the image data is read from the line buffer according to the output pixel coordinates.

According to one embodiment, an electronic device includes an imaging device, and a liquid crystal panel including a display portion overlapping the imaging device, wherein the liquid crystal panel includes a first pixel overlapping the imaging device, an opening portion provided in the first pixel, a second pixel adjacent to the first pixel, and a third pixel adjacent to the second pixel, the third pixel includes a first coloring layer, a second coloring layer and a third coloring layer, and the second pixel does not include the coloring layer or includes a transparent resinous layer.

This application discloses a facial recognition method and apparatus, a device and a medium, which relates to the field of image processing. The method includes: fusing a color map and a depth map of a facial image to obtain a fused image of the facial image, the fused image including two -dimensional information and depth information of the facial image (202); dividing the fused image into blocks to obtain at least two image blocks of the fused image (204); irreversibly shuffling pixels in the at least two image blocks to obtain a pixel-confused facial image (206); and determining an object identifier corresponding to the facial image according to the pixel-confused facial image (208).

This application discloses a facial recognition method and apparatus, a device and a medium, which relates to the field of image processing. The method includes: fusing a color map and a depth map of a facial image to obtain a fused image of the facial image, the fused image including two -dimensional information and depth information of the facial image (202); dividing the fused image into blocks to obtain at least two image blocks of the fused image (204); irreversibly shuffling pixels in the at least two image blocks to obtain a pixel-confused facial image (206); and determining an object identifier corresponding to the facial image according to the pixel-confused facial image (208).

Methods and systems for filtering a trigger signal from an encoder for triggering an image capturing device. In embodiments, a trigger signal may be received as an input signal from an encoder including a sequence of pulses for triggering the image capturing device. In embodiments, an average pulse frequency of the trigger signal over a period of time may be determined based on sampling a number of pulses in the trigger signal over the period of time, and frequency restrictions may be applied to the average pulse frequency to generate a trigger frequency. In embodiments, an output frequency may be determined based on the trigger frequency, and a pulse width modulation (PWM) signal having a frequency based on the output frequency may be determined for triggering the image capturing device.