Samsung Electronics Co., Ltd.

Changyong Son

Jinwoo Son

Jaejoon Han

Chang Kyu Choi

Seungju Han

Byungin Yoo

Deoksang Kim

Sangil Jung

Ki-hyun Choo

Junghoe Kim

Eunmi Oh

Dae-kyu Shin

Minsu Ko

Wonsuk Chang

Seohyung Lee

Dongwook Lee

Jaehyoung Yoo

Jihye Kim

Byung In Yoo

Jae-Joon Han

Sungun Park

Changin Choi

Hosang Sung

Hyunjeong Lee

Kangeun Lee

Changbeom Park

Donghoon Lee

Seung Wook Kim

Sungjoo Suh

Seungin Park

Seungwook Kim

Ju Hwan Song

HyunJeong Lee

Joohyeon Kim

Do-Ha Hwang

Jonghun Kim

Byounghak Jeong

Youngyo Kim

Insung Lee

Jaehyun Shin

Kyuhyuk Jung

Youngwook Ahn

Jonghoon Yoon

Hochong Park

Provided is a method and apparatus with neural network operation. The method includes generating a first intermediate operation result by performing a first-order partial operation of a neural network layer on a first input line of a first area of a frame, generating a second intermediate operation result by performing another first-order partial operation of the neural network layer on a second input line of the first area, and generating an objective operation result of the neural network layer with respect to the first area based on a second-order partial operation performed on the first intermediate operation result and the second intermediate operation result.

Method and apparatus with neural network operation

An apparatus and a method with image recognition-based security are disclosed. The method includes, for an unlocked terminal, tracking a face detected in a previous frame, detecting a background region change between the previous frame and a current frame based on a region of the tracked face, when the background region change is not detected, determining whether a state maintenance time fails to meet a preset time, in response to the state maintenance time failing to meet the preset time, determining an operation mode to be a first operation mode for determining whether recognition succeeds for the current frame, performing the first operation mode, including performing face detection with respect to the current frame, and maintaining the unlocked state of the terminal for the current frame when the face is detected as a result of the performing of the face detection, representing that the recognition succeeded for the current frame.

Apparatus and method with image recognition-based security

Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

Face verification method and apparatus

Disclosed is a face verification method and apparatus. A mobile device may include one or more processors configured to obtain one or more images for a user, ascertain whether any of the one or more images correspond to respective user distances, from the user to the mobile device, outside of a threshold range of distances, and selectively, based on a result of the ascertaining, perform verification using a first verification threshold for any of the one or more images ascertained to correspond to the respective user distances that are outside the threshold range of distances, and perform verification using a less strict second verification threshold for any of the one or more images that have been ascertained to not correspond to the respective user distances that are outside the threshold range of distances.

A method and apparatus for processing an image based on partial images. The method includes extracting a feature of a current partial processing region of an input image frame by inputting pixel data of the current partial processing region into a convolutional neural network (CNN), updating a hidden state of a recurrent neural network (RNN) for a context between the current partial processing region and at least one previous partial processing region by inputting the extracted feature into the RNN, and generating an image processing result for the input image frame based on the updated hidden state.

Method and apparatus for processing image based on partial images

Disclosed is a method and apparatus for adaptive tracking of a target object. The method includes method of tracking an object, the method including estimating a dynamic characteristic of an object in an input image based on frames of the input image, determining a size of a crop region for a current frame of the input image based on the dynamic characteristic of the object, generating a cropped image by cropping the current frame based on the size of the crop region, and generating a result of tracking the object for the current frame using the cropped image.

Method and apparatus with adaptive object tracking

A system includes: an image sensor configured to acquire an image; an image processor configured to generate a quantized image based on the acquired image using a trained quantization filter; and an output interface configured to output the quantized image.

Method and apparatus with quantized image generation

An image matching method includes extracting, from a first image of an object, a landmark patch including a landmark point of the object, extracting, from a second image of the object, a target patch corresponding to the landmark patch; and determining a target point in the second image corresponding to the landmark point based on a matching between the landmark patch and the target patch.

Device and method with image matching

An image sensor includes: a motion detection circuit configured to detect a motion in image frames; and a micro control unit (MCU) configured to adjust at least a portion of a target frame among the image frames based on whether the motion is detected, and detect whether a target object is present based on the adjusted portion of the target frame.

Image sensor and operating method of the image sensor

Disclosed is a processor-implemented data processing method in a neural network. A data processing apparatus includes at least one processor, and at least one memory configured to store instructions to be executed by the processor and a neural network, wherein the processor is configured to, based on the instructions, input an input activation map into a current layer included in the neural network, output an output activation map by performing a convolution operation between the input activation map and a weight quantized with a first representation bit number of the current layer, and output a quantized activation map by quantizing the output activation map with a second representation bit number based on an activation quantization parameter.

Method and apparatus with neural network parameter quantization

A convolutional neural network (CNN) processing method includes selecting a survival network in a precision convolutional network based on a result of performing a high speed convolution operation between an input and a kernel using a high speed convolutional network, and performing a precision convolution operation between the input and the kernel using the survival network.

Convolutional neural network (CNN) processing method and apparatus performing high speed and precision convolution operations

A processor-implemented neural network method includes: obtaining a first weight kernel of a weight model and pruning information of the first weight kernel; determining, based on the pruning information, a processing range of an input feature map for each weight element vector of the first weight kernel; performing a convolution operation between the input feature map and the first weight kernel based on the determined processing range; and generating an output feature map of a neural network layer based on an operation result of the convolution operation.

Method and apparatus with neural network operation processing

Disclosed are an image data processing method and a sensor device performing the same. The sensor device includes an image sensor configured to acquire image data, an image buffer configured to store the image data, and an image processor configured to generate image-processed data by applying a filter corresponding to a storage pattern of the image buffer to the image data stored in the image buffer.

Data processing method and sensor device for performing the same

A processor-implemented method of tracking a target object includes: extracting a feature from frames of an input image; selecting one a neural network model from among a plurality of neural network models that is provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.

Method and apparatus with target object tracking

Growing community of inventors

Anyang-si, South Korea

Changyong Son